53 files changed, 1597 insertions(+), 1038 deletions(-)

M ARCHITECTURE.md
M CHANGELOG.md
M CONTRIBUTING.md
M SKILL.md
M VERSION
M autoplan/SKILL.md
M autoplan/SKILL.md.tmpl
M benchmark/SKILL.md
M browse/SKILL.md
M canary/SKILL.md
M codex/SKILL.md
M connect-chrome/SKILL.md
M cso/SKILL.md
M cso/SKILL.md.tmpl
M design-consultation/SKILL.md
M design-consultation/SKILL.md.tmpl
M design-html/SKILL.md
M design-review/SKILL.md
M design-review/SKILL.md.tmpl
M design-shotgun/SKILL.md
M document-release/SKILL.md
M document-release/SKILL.md.tmpl
M investigate/SKILL.md
M land-and-deploy/SKILL.md
M learn/SKILL.md
M office-hours/SKILL.md
M office-hours/SKILL.md.tmpl
M package.json
M plan-ceo-review/SKILL.md
M plan-ceo-review/SKILL.md.tmpl
M plan-design-review/SKILL.md
M plan-design-review/SKILL.md.tmpl
M plan-eng-review/SKILL.md
M plan-eng-review/SKILL.md.tmpl
M qa-only/SKILL.md
M qa-only/SKILL.md.tmpl
M qa/SKILL.md
M qa/SKILL.md.tmpl
M retro/SKILL.md
M retro/SKILL.md.tmpl
M review/SKILL.md
M scripts/resolvers/learnings.ts
M scripts/resolvers/preamble.ts
M setup-browser-cookies/SKILL.md
M setup-deploy/SKILL.md
M ship/SKILL.md
M test/gen-skill-docs.test.ts
M test/helpers/touchfiles.ts
M test/skill-e2e-bws.test.ts
M test/skill-e2e-learnings.test.ts
M test/skill-e2e.test.ts
M test/skill-validation.test.ts
M test/touchfiles.test.ts

@@ 217,7 217,7 @@ Every skill starts with a `{{PREAMBLE}}` block that runs before the skill's own 
 
 1. **Update check** — calls `gstack-update-check`, reports if an upgrade is available.
 2. **Session tracking** — touches `~/.gstack/sessions/$PPID` and counts active sessions (files modified in the last 2 hours). When 3+ sessions are running, all skills enter "ELI16 mode" — every question re-grounds the user on context because they're juggling windows.
-3. **Contributor mode** — reads `gstack_contributor` from config. When true, the agent files casual field reports to `~/.gstack/contributor-logs/` when gstack itself misbehaves.
+3. **Operational self-improvement** — at the end of every skill session, the agent reflects on failures (CLI errors, wrong approaches, project quirks) and logs operational learnings to the project's JSONL file for future sessions.
 4. **AskUserQuestion format** — universal format: context, question, `RECOMMENDATION: Choose X because ___`, lettered options. Consistent across all skills.
 5. **Search Before Building** — before building infrastructure or unfamiliar patterns, search first. Three layers of knowledge: tried-and-true (Layer 1), new-and-popular (Layer 2), first-principles (Layer 3). When first-principles reasoning reveals conventional wisdom is wrong, the agent names the "eureka moment" and logs it. See `ETHOS.md` for the full builder philosophy.
 

@@ 1,5 1,23 @@
 # Changelog
 
+## [0.14.6.0] - 2026-03-31 — Recursive Self-Improvement
+
+gstack now learns from its own mistakes. Every skill session captures operational failures (CLI errors, wrong approaches, project quirks) and surfaces them in future sessions. No setup needed, just works.
+
+### Added
+
+- **Operational self-improvement.** When a command fails or you hit a project-specific gotcha, gstack logs it. Next session, it remembers. "bun test needs --timeout 30000" or "login flow requires cookie import first" ... the kind of stuff that wastes 10 minutes every time you forget it.
+- **Learnings summary in preamble.** When your project has 5+ learnings, gstack shows the top 3 at the start of every session so you see them before you start working.
+- **13 skills now learn.** office-hours, plan-ceo-review, plan-eng-review, plan-design-review, design-review, design-consultation, cso, qa, qa-only, and retro all now read prior learnings AND contribute new ones. Previously only review, ship, and investigate were wired.
+
+### Changed
+
+- **Contributor mode replaced.** The old contributor mode (manual opt-in, markdown reports to ~/.gstack/contributor-logs/) never fired in 18 days of heavy use. Replaced with automatic operational learning that captures the same insights without any setup.
+
+### Fixed
+
+- **learnings-show E2E test slug mismatch.** The test seeded learnings at a hardcoded path but gstack-slug computed a different path at runtime. Now computes the slug dynamically.
+
 ## [0.14.5.0] - 2026-03-31 — Ship Idempotency + Skill Prefix Fix
 
 Re-running `/ship` after a failed push or PR creation no longer double-bumps your version or duplicates your CHANGELOG. And if you use `--prefix` mode, your skill names actually work now.

@@ 20,26 20,19 @@ Now edit any `SKILL.md`, invoke it in Claude Code (e.g. `/review`), and see your
 bin/dev-teardown               # deactivate — back to your global install
 ```
 
-## Contributor mode
+## Operational self-improvement
 
-Contributor mode turns gstack into a self-improving tool. Enable it and Claude Code
-will periodically reflect on its gstack experience — rating it 0-10 at the end of
-each major workflow step. When something isn't a 10, it thinks about why and files
-a report to `~/.gstack/contributor-logs/` with what happened, repro steps, and what
-would make it better.
+gstack automatically learns from failures. At the end of every skill session, the agent
+reflects on what went wrong (CLI errors, wrong approaches, project quirks) and logs
+operational learnings to `~/.gstack/projects/{slug}/learnings.jsonl`. Future sessions
+surface these learnings automatically, so gstack gets smarter on your codebase over time.
 
-```bash
-~/.claude/skills/gstack/bin/gstack-config set gstack_contributor true
-```
-
-The logs are for **you**. When something bugs you enough to fix, the report is
-already written. Fork gstack, symlink your fork into the project where you hit
-the issue, fix it, and open a PR.
+No setup needed. Learnings are logged automatically. View them with `/learn`.
 
 ### The contributor workflow
 
-1. **Use gstack normally** — contributor mode reflects and logs issues automatically
-2. **Check your logs:** `ls ~/.gstack/contributor-logs/`
+1. **Use gstack normally** — operational learnings are captured automatically
+2. **Check your learnings:** `/learn` or `ls ~/.gstack/projects/*/learnings.jsonl`
 3. **Fork and clone gstack** (if you haven't already)
 4. **Symlink your fork into the project where you hit the bug:**
    ```bash

@@ 25,7 25,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 46,8 45,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"gstack","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"gstack","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 65,6 64,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 208,24 210,6 @@ This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLIN
 
 The user always has context you don't. Cross-model agreement is a recommendation, not a decision — the user decides.
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 251,6 235,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 269,22 271,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 1,1 1,1 @@
-0.14.5.0
+0.14.6.0

@@ 34,7 34,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 55,8 54,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"autoplan","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"autoplan","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 74,6 73,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 300,24 302,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 343,6 327,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 361,22 363,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 698,7 700,6 @@ Read each file using the Read tool:
 - AskUserQuestion Format
 - Completeness Principle — Boil the Lake
 - Search Before Building
-- Contributor Mode
 - Completion Status Protocol
 - Telemetry (run last)
 - Step 0: Detect base branch

@@ 202,7 202,6 @@ Read each file using the Read tool:
 - AskUserQuestion Format
 - Completeness Principle — Boil the Lake
 - Search Before Building
-- Contributor Mode
 - Completion Status Protocol
 - Telemetry (run last)
 - Step 0: Detect base branch

@@ 27,7 27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 48,8 47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"benchmark","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"benchmark","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 67,6 66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 210,24 212,6 @@ This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLIN
 
 The user always has context you don't. Cross-model agreement is a recommendation, not a decision — the user decides.
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 253,6 237,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 271,22 273,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 27,7 27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 48,8 47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"browse","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"browse","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 67,6 66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 210,24 212,6 @@ This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLIN
 
 The user always has context you don't. Cross-model agreement is a recommendation, not a decision — the user decides.
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 253,6 237,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 271,22 273,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 27,7 27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 48,8 47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"canary","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"canary","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 67,6 66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 275,24 277,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 318,6 302,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 336,22 338,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 28,7 28,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 49,8 48,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"codex","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"codex","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 68,6 67,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 294,24 296,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 337,6 321,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 355,22 357,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 25,7 25,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 46,8 45,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"connect-chrome","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"connect-chrome","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 65,6 64,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 291,24 293,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 334,6 318,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 352,22 354,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 31,7 31,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 52,8 51,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"cso","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"cso","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 71,6 70,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 279,24 281,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 322,6 306,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 340,22 342,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 488,6 490,44 @@ grep -q "laravel" composer.json 2>/dev/null && echo "FRAMEWORK: Laravel"
 
 This is NOT a checklist — it's a reasoning phase. The output is understanding, not findings.
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ### Phase 1: Attack Surface Census
 
 Map what an attacker sees — both code surface and infrastructure surface.


@@ 1007,6 1047,31 @@ Write findings to `.gstack/security-reports/{date}-{HHMMSS}.json` using this sch
 
 If `.gstack/` is not in `.gitignore`, note it in findings — security reports should stay local.
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"cso","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Important Rules
 
 - **Think like an attacker, report like a defender.** Show the exploit path, then the fix.

@@ 102,6 102,8 @@ grep -q "laravel" composer.json 2>/dev/null && echo "FRAMEWORK: Laravel"
 
 This is NOT a checklist — it's a reasoning phase. The output is understanding, not findings.
 
+{{LEARNINGS_SEARCH}}
+
 ### Phase 1: Attack Surface Census
 
 Map what an attacker sees — both code surface and infrastructure surface.


@@ 598,6 600,8 @@ Write findings to `.gstack/security-reports/{date}-{HHMMSS}.json` using this sch
 
 If `.gstack/` is not in `.gitignore`, note it in findings — security reports should stay local.
 
+{{LEARNINGS_LOG}}
+
 ## Important Rules
 
 - **Think like an attacker, report like a defender.** Show the exploit path, then the fix.

@@ 32,7 32,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 53,8 52,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"design-consultation","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"design-consultation","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 72,6 71,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 298,24 300,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 341,6 325,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 359,22 361,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 558,6 560,44 @@ If `DESIGN_NOT_AVAILABLE`: Phase 5 falls back to the HTML preview page (still go
 
 ---
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Phase 1: Product Context
 
 Ask the user a single question that covers everything you need to know. Pre-fill what you can infer from the codebase.


@@ 1062,6 1102,31 @@ After shipping DESIGN.md, if the session produced screen-level mockups or page l
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"design-consultation","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Important Rules
 
 1. **Propose, don't present menus.** You are a consultant, not a form. Make opinionated recommendations based on the product context, then let the user adjust.

@@ 79,6 79,8 @@ If `DESIGN_NOT_AVAILABLE`: Phase 5 falls back to the HTML preview page (still go
 
 ---
 
+{{LEARNINGS_SEARCH}}
+
 ## Phase 1: Product Context
 
 Ask the user a single question that covers everything you need to know. Pre-fill what you can infer from the codebase.


@@ 419,6 421,8 @@ After shipping DESIGN.md, if the session produced screen-level mockups or page l
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Important Rules
 
 1. **Propose, don't present menus.** You are a consultant, not a form. Make opinionated recommendations based on the product context, then let the user adjust.

@@ 32,7 32,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 53,8 52,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"design-html","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"design-html","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 72,6 71,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 280,24 282,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 323,6 307,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 341,22 343,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 32,7 32,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 53,8 52,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 72,6 71,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 298,24 300,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 341,6 325,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 359,22 361,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 728,6 730,44 @@ echo "REPORT_DIR: $REPORT_DIR"
 
 ---
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Phases 1-6: Design Audit Baseline
 
 ## Modes


@@ 1394,6 1434,31 @@ If the repo has a `TODOS.md`:
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"design-review","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Additional Rules (design-review specific)
 
 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.

@@ 97,6 97,8 @@ echo "REPORT_DIR: $REPORT_DIR"
 
 ---
 
+{{LEARNINGS_SEARCH}}
+
 ## Phases 1-6: Design Audit Baseline
 
 {{DESIGN_METHODOLOGY}}


@@ 287,6 289,8 @@ If the repo has a `TODOS.md`:
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Additional Rules (design-review specific)
 
 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.

@@ 29,7 29,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 50,8 49,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"design-shotgun","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"design-shotgun","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 69,6 68,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 277,24 279,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 320,6 304,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 338,22 340,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 29,7 29,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 50,8 49,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"document-release","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"document-release","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 69,6 68,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 277,24 279,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 320,6 304,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 338,22 340,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 531,7 533,7 @@ Read each documentation file and cross-reference it against the diff. Use these 
 - Walk through the setup instructions as if you are a brand new contributor.
 - Are the listed commands accurate? Would each step succeed?
 - Do test tier descriptions match the current test infrastructure?
-- Are workflow descriptions (dev setup, contributor mode, etc.) current?
+- Are workflow descriptions (dev setup, operational learnings, etc.) current?
 - Flag anything that would fail or confuse a first-time contributor.
 
 **CLAUDE.md / project instructions:**

@@ 108,7 108,7 @@ Read each documentation file and cross-reference it against the diff. Use these 
 - Walk through the setup instructions as if you are a brand new contributor.
 - Are the listed commands accurate? Would each step succeed?
 - Do test tier descriptions match the current test infrastructure?
-- Are workflow descriptions (dev setup, contributor mode, etc.) current?
+- Are workflow descriptions (dev setup, operational learnings, etc.) current?
 - Flag anything that would fail or confuse a first-time contributor.
 
 **CLAUDE.md / project instructions:**

@@ 44,7 44,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 65,8 64,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"investigate","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"investigate","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 84,6 83,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 292,24 294,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 335,6 319,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 353,22 355,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 618,7 620,8 @@ this session, log it for future sessions:
 ```
 
 **Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
-(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
 
 **Sources:** `observed` (you found this in the code), `user-stated` (user told you),
 `inferred` (AI deduction), `cross-model` (both Claude and Codex agree).

@@ 26,7 26,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 47,8 46,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"land-and-deploy","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"land-and-deploy","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 66,6 65,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 292,24 294,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 335,6 319,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 353,22 355,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 29,7 29,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 50,8 49,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"learn","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"learn","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 69,6 68,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 277,24 279,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 320,6 304,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 338,22 340,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 

@@ 36,7 36,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 57,8 56,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"office-hours","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"office-hours","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 76,6 75,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 302,24 304,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 345,6 329,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 363,22 365,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 1549,6 1551,31 @@ The design doc at `~/.gstack/projects/` is automatically discoverable by downstr
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"office-hours","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Important Rules
 
 - **Never start implementation.** This skill produces design docs, not code. Not even scaffolding.

@@ 757,6 757,8 @@ The design doc at `~/.gstack/projects/` is automatically discoverable by downstr
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Important Rules
 
 - **Never start implementation.** This skill produces design docs, not code. Not even scaffolding.

@@ 1,6 1,6 @@
 {
   "name": "gstack",
-  "version": "0.14.5.0",
+  "version": "0.14.6.0",
   "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
   "license": "MIT",
   "type": "module",

@@ 32,7 32,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 53,8 52,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"plan-ceo-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"plan-ceo-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 72,6 71,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 298,24 300,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 341,6 325,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 359,22 361,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 1637,6 1639,31 @@ If promoted, copy the CEO plan content to `docs/designs/{FEATURE}.md` (create th
 * After each section, pause and wait for feedback.
 * Use **CRITICAL GAP** / **WARNING** / **OK** for scannability.
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"plan-ceo-review","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Mode Quick Reference
 ```
   ┌────────────────────────────────────────────────────────────────────────────────┐

@@ 779,6 779,8 @@ If promoted, copy the CEO plan content to `docs/designs/{FEATURE}.md` (create th
 * After each section, pause and wait for feedback.
 * Use **CRITICAL GAP** / **WARNING** / **OK** for scannability.
 
+{{LEARNINGS_LOG}}
+
 ## Mode Quick Reference
 ```
   ┌────────────────────────────────────────────────────────────────────────────────┐

@@ 30,7 30,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 51,8 50,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"plan-design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"plan-design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 70,6 69,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 296,24 298,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 339,6 323,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 357,22 359,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 944,6 946,44 @@ descriptions of what 10/10 looks like.
 
 ## Review Sections (7 passes, after scope is agreed)
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ### Pass 1: Information Architecture
 Rate 0-10: Does the plan define what the user sees first, second, third?
 FIX TO 10: Add information hierarchy to the plan. Include ASCII diagram of screen/page structure and navigation flow. Apply "constraint worship" — if you can only show 3 things, which 3?


@@ 1300,6 1340,31 @@ plan's living status.
 - Always place it as the very last section in the plan file. If it was found mid-file,
   move it: delete the old location and append at the end.
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"plan-design-review","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Next Steps — Review Chaining
 
 After displaying the Review Readiness Dashboard, recommend the next review(s) based on what this design review discovered. Read the dashboard output to see which reviews have already been run and whether they are stale.

@@ 256,6 256,8 @@ descriptions of what 10/10 looks like.
 
 ## Review Sections (7 passes, after scope is agreed)
 
+{{LEARNINGS_SEARCH}}
+
 ### Pass 1: Information Architecture
 Rate 0-10: Does the plan define what the user sees first, second, third?
 FIX TO 10: Add information hierarchy to the plan. Include ASCII diagram of screen/page structure and navigation flow. Apply "constraint worship" — if you can only show 3 things, which 3?


@@ 431,6 433,8 @@ Substitute values from the Completion Summary:
 
 {{PLAN_FILE_REVIEW_REPORT}}
 
+{{LEARNINGS_LOG}}
+
 ## Next Steps — Review Chaining
 
 After displaying the Review Readiness Dashboard, recommend the next review(s) based on what this design review discovered. Read the dashboard output to see which reviews have already been run and whether they are stale.

@@ 31,7 31,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 52,8 51,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"plan-eng-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"plan-eng-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 71,6 70,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 297,24 299,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 340,6 324,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 358,22 360,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 1249,6 1251,31 @@ plan's living status.
 - Always place it as the very last section in the plan file. If it was found mid-file,
   move it: delete the old location and append at the end.
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"plan-eng-review","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Next Steps — Review Chaining
 
 After displaying the Review Readiness Dashboard, check if additional reviews would be valuable. Read the dashboard output to see which reviews have already been run and whether they are stale.

@@ 287,6 287,8 @@ Substitute values from the Completion Summary:
 
 {{PLAN_FILE_REVIEW_REPORT}}
 
+{{LEARNINGS_LOG}}
+
 ## Next Steps — Review Chaining
 
 After displaying the Review Readiness Dashboard, check if additional reviews would be valuable. Read the dashboard output to see which reviews have already been run and whether they are stale.

@@ 27,7 27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 48,8 47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"qa-only","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"qa-only","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 67,6 66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 293,24 295,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 336,6 320,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 354,22 356,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 487,6 489,44 @@ mkdir -p "$REPORT_DIR/screenshots"
 
 ---
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Test Plan Context
 
 Before falling back to git diff heuristics, check for richer test plan sources:


@@ 811,6 851,31 @@ Report filenames use the domain and date: `qa-report-myapp-com-2026-03-12.md`
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"qa-only","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Additional Rules (qa-only specific)
 
 11. **Never fix bugs.** Find and document only. Do not read source code, edit files, or suggest fixes in the report. Your job is to report what's broken, not to fix it. Use `/qa` for the test-fix-verify loop.

@@ 49,6 49,8 @@ mkdir -p "$REPORT_DIR/screenshots"
 
 ---
 
+{{LEARNINGS_SEARCH}}
+
 ## Test Plan Context
 
 Before falling back to git diff heuristics, check for richer test plan sources:


@@ 97,6 99,8 @@ Report filenames use the domain and date: `qa-report-myapp-com-2026-03-12.md`
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Additional Rules (qa-only specific)
 
 11. **Never fix bugs.** Find and document only. Do not read source code, edit files, or suggest fixes in the report. Your job is to report what's broken, not to fix it. Use `/qa` for the test-fix-verify loop.

@@ 33,7 33,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 54,8 53,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"qa","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"qa","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 73,6 72,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 299,24 301,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 342,6 326,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 360,22 362,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 717,6 719,44 @@ mkdir -p .gstack/qa-reports/screenshots
 
 ---
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Test Plan Context
 
 Before falling back to git diff heuristics, check for richer test plan sources:


@@ 1218,6 1258,31 @@ If the repo has a `TODOS.md`:
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"qa","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Additional Rules (qa-specific)
 
 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.

@@ 90,6 90,8 @@ mkdir -p .gstack/qa-reports/screenshots
 
 ---
 
+{{LEARNINGS_SEARCH}}
+
 ## Test Plan Context
 
 Before falling back to git diff heuristics, check for richer test plan sources:


@@ 315,6 317,8 @@ If the repo has a `TODOS.md`:
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Additional Rules (qa-specific)
 
 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.

@@ 27,7 27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 48,8 47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"retro","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"retro","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 67,6 66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 275,24 277,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 318,6 302,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 336,22 338,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 481,6 483,44 @@ Usage: /retro [window | compare | global]
 
 **If the first argument is `global`:** Skip the normal repo-scoped retro (Steps 1-14). Instead, follow the **Global Retrospective** flow at the end of this document. The optional second argument is the time window (default 7d). This mode does NOT require being inside a git repo.
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ### Step 1: Gather Raw Data
 
 First, fetch origin and identify the current user:


@@ 710,7 750,8 @@ this session, log it for future sessions:
 ```
 
 **Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
-(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
 
 **Sources:** `observed` (you found this in the code), `user-stated` (user told you),
 `inferred` (AI deduction), `cross-model` (both Claude and Codex agree).

@@ 58,6 58,8 @@ Usage: /retro [window | compare | global]
 
 **If the first argument is `global`:** Skip the normal repo-scoped retro (Steps 1-14). Instead, follow the **Global Retrospective** flow at the end of this document. The optional second argument is the time window (default 7d). This mode does NOT require being inside a git repo.
 
+{{LEARNINGS_SEARCH}}
+
 ### Step 1: Gather Raw Data
 
 First, fetch origin and identify the current user:

@@ 30,7 30,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 51,8 50,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 70,6 69,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 296,24 298,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 339,6 323,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 357,22 359,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 1229,7 1231,8 @@ this session, log it for future sessions:
 ```
 
 **Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
-(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
 
 **Sources:** `observed` (you found this in the code), `user-stated` (user told you),
 `inferred` (AI deduction), `cross-model` (both Claude and Codex agree).

@@ 80,7 80,8 @@ ${binDir}/gstack-learnings-log '{"skill":"${ctx.skillName}","type":"TYPE","key":
 \`\`\`
 
 **Types:** \`pattern\` (reusable approach), \`pitfall\` (what NOT to do), \`preference\`
-(user stated), \`architecture\` (structural decision), \`tool\` (library/framework insight).
+(user stated), \`architecture\` (structural decision), \`tool\` (library/framework insight),
+\`operational\` (project environment/CLI/workflow knowledge).
 
 **Sources:** \`observed\` (you found this in the code), \`user-stated\` (user told you),
 \`inferred\` (AI deduction), \`cross-model\` (both Claude and Codex agree).

@@ 8,9 8,8 @@ import type { TemplateContext } from './types';
  * repo mode detection, and telemetry.
  *
  * Telemetry data flow:
- *   1. If _TEL != "off": local JSONL append to ~/.gstack/analytics/ (inline, inspectable)
+ *   1. Always: local JSONL append to ~/.gstack/analytics/ (inline, inspectable)
  *   2. If _TEL != "off" AND binary exists: gstack-telemetry-log for remote reporting
- *   When telemetry is off, nothing is written anywhere. Clean trust contract.
  */
 
 function generatePreambleBash(ctx: TemplateContext): string {


@@ 34,7 33,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(${ctx.paths.binDir}/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(${ctx.paths.binDir}/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")


@@ 55,8 53,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: \${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "\${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"${ctx.skillName}","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"${ctx.skillName}","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do


@@ 74,6 72,9 @@ _LEARN_FILE="\${GSTACK_HOME:-$HOME/.gstack}/projects/\${SLUG:-unknown}/learnings
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ${ctx.paths.binDir}/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi


@@ 379,27 380,7 @@ jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg b
 \`\`\``;
 }
 
-function generateContributorMode(): string {
-  return `## Contributor Mode
-
-If \`_CONTRIB\` is \`true\`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write \`~/.gstack/contributor-logs/{slug}.md\`:
-\`\`\`
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-\`\`\`
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.`;
-}
-
-function generateCompletionStatus(): string {
+function generateCompletionStatus(ctx: TemplateContext): string {
   return `## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:


@@ 425,6 406,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 \`\`\`
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+\`\`\`bash
+${ctx.paths.binDir}/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+\`\`\`
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.


@@ 443,22 442,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \\
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \\
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \\
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \\
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 \`\`\`
 
 Replace \`SKILL_NAME\` with the actual skill name from frontmatter, \`OUTCOME\` with
 success/error/abort, and \`USED_BROWSE\` with true/false based on whether \`$B\` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Mode Safe Operations
 


@@ 572,7 571,7 @@ Avoid filler, throat-clearing, generic optimism, founder cosplay, and unsupporte
 
 // Preamble Composition (tier → sections)
 // ─────────────────────────────────────────────
-// T1: core + upgrade + lake + telemetry + voice(trimmed) + contributor + completion
+// T1: core + upgrade + lake + telemetry + voice(trimmed) + completion
 // T2: T1 + voice(full) + ask + completeness
 // T3: T2 + repo-mode + search
 // T4: (same as T3 — TEST_FAILURE_TRIAGE is a separate {{}} placeholder, not preamble)


@@ 597,8 596,7 @@ export function generatePreamble(ctx: TemplateContext): string {
     generateVoiceDirective(tier),
     ...(tier >= 2 ? [generateAskUserFormat(ctx), generateCompletenessSection()] : []),
     ...(tier >= 3 ? [generateRepoModeSection(), generateSearchBeforeBuildingSection(ctx)] : []),
-    generateContributorMode(),
-    generateCompletionStatus(),
+    generateCompletionStatus(ctx),
   ];
   return sections.join('\n\n');
 }