Enable GBrain auto-memory for Claude and Codex hosts

cso/SKILL.md

@@ -556,7 +556,21 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
+## Brain Context Load
 
+Before starting this skill, search your brain for relevant context:
+
+1. Extract 2-4 keywords from the user's request (nouns, error names, file paths, technical terms).
+   Search GBrain: `gbrain search "keyword1 keyword2"`
+   Example: for "the login page is broken after deploy", search `gbrain search "login broken deploy"`
+   Search returns lines like: `[slug] Title (score: 0.85) - first line of content...`
+2. If few results, broaden to the single most specific keyword and search again.
+3. For each result page, read it: `gbrain get_page "<page_slug>"`
+   Read the top 3 pages for context.
+4. Use this brain context to inform your analysis.
+
+If GBrain is not available or returns no results, proceed without brain context.
+Any non-zero exit code from gbrain commands should be treated as a transient failure.
 
 # /cso — Chief Security Officer Audit (v2)
 
@@ -1220,7 +1234,28 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **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.
 
+## Save Results to Brain
+
+After completing this skill, persist the results to your brain for future reference:
+
+Save the security audit as a brain page:
+```bash
+gbrain put_page --title "Security Audit: <date>" --tags "security-audit,<date>" <<'EOF'
+<findings and remediation status in markdown>
+EOF
+```
+
+After saving the page, extract and enrich mentioned entities: for each actual person name or company/organization name found in the output, `gbrain search "<entity name>"` to check if a page exists. If not, create a stub page:
+```bash
+gbrain put_page --title "<Person or Company Name>" --tags "entity,person" --content "Stub page. Mentioned in <skill name> output."
+```
+Only extract actual person names and company/organization names. Skip product names, section headings, technical terms, and file paths.
+
+Throttle errors appear as: exit code 1 with stderr containing "throttle", "rate limit", "capacity", or "busy". If GBrain returns a throttle or rate-limit error on any save operation, defer the save and move on. The brain is busy — the content is not lost, just not persisted this run. Any other non-zero exit code should also be treated as a transient failure.
+
+Add backlinks to related brain pages if they exist. If GBrain is not available, skip this step.
 
+After brain operations complete, note in your completion output: how many pages were found in the initial search, how many entities were enriched, and whether any operations were throttled. This helps the user see brain utilization over time.
 
 ## Important Rules
 

design-consultation/SKILL.md

@@ -705,7 +705,21 @@ If `DESIGN_NOT_AVAILABLE`: Phase 5 falls back to the HTML preview page (still go
 
 ---
 
+## Brain Context Load
 
+Before starting this skill, search your brain for relevant context:
+
+1. Extract 2-4 keywords from the user's request (nouns, error names, file paths, technical terms).
+   Search GBrain: `gbrain search "keyword1 keyword2"`
+   Example: for "the login page is broken after deploy", search `gbrain search "login broken deploy"`
+   Search returns lines like: `[slug] Title (score: 0.85) - first line of content...`
+2. If few results, broaden to the single most specific keyword and search again.
+3. For each result page, read it: `gbrain get_page "<page_slug>"`
+   Read the top 3 pages for context.
+4. Use this brain context to inform your analysis.
+
+If GBrain is not available or returns no results, proceed without brain context.
+Any non-zero exit code from gbrain commands should be treated as a transient failure.
 
 ## Prior Learnings
 
@@ -1274,7 +1288,28 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **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.
 
+## Save Results to Brain
+
+After completing this skill, persist the results to your brain for future reference:
+
+Save the design system as a brain page:
+```bash
+gbrain put_page --title "Design System: <project name>" --tags "design-system,<project-slug>" <<'EOF'
+<design decisions in markdown>
+EOF
+```
+
+After saving the page, extract and enrich mentioned entities: for each actual person name or company/organization name found in the output, `gbrain search "<entity name>"` to check if a page exists. If not, create a stub page:
+```bash
+gbrain put_page --title "<Person or Company Name>" --tags "entity,person" --content "Stub page. Mentioned in <skill name> output."
+```
+Only extract actual person names and company/organization names. Skip product names, section headings, technical terms, and file paths.
+
+Throttle errors appear as: exit code 1 with stderr containing "throttle", "rate limit", "capacity", or "busy". If GBrain returns a throttle or rate-limit error on any save operation, defer the save and move on. The brain is busy — the content is not lost, just not persisted this run. Any other non-zero exit code should also be treated as a transient failure.
+
+Add backlinks to related brain pages if they exist. If GBrain is not available, skip this step.
 
+After brain operations complete, note in your completion output: how many pages were found in the initial search, how many entities were enriched, and whether any operations were throttled. This helps the user see brain utilization over time.
 
 ## Important Rules
 

design-review/SKILL.md

@@ -574,7 +574,21 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
+## Brain Context Load
 
+Before starting this skill, search your brain for relevant context:
+
+1. Extract 2-4 keywords from the user's request (nouns, error names, file paths, technical terms).
+   Search GBrain: `gbrain search "keyword1 keyword2"`
+   Example: for "the login page is broken after deploy", search `gbrain search "login broken deploy"`
+   Search returns lines like: `[slug] Title (score: 0.85) - first line of content...`
+2. If few results, broaden to the single most specific keyword and search again.
+3. For each result page, read it: `gbrain get_page "<page_slug>"`
+   Read the top 3 pages for context.
+4. Use this brain context to inform your analysis.
+
+If GBrain is not available or returns no results, proceed without brain context.
+Any non-zero exit code from gbrain commands should be treated as a transient failure.
 
 # /design-review: Design Audit → Fix → Verify
 
@@ -1753,7 +1767,28 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **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.
 
+## Save Results to Brain
+
+After completing this skill, persist the results to your brain for future reference:
+
+Save the skill output as a brain page if the results are worth preserving:
+```bash
+gbrain put_page --title "<descriptive title>" --tags "<relevant,tags>" <<'EOF'
+<content in markdown>
+EOF
+```
+
+After saving the page, extract and enrich mentioned entities: for each actual person name or company/organization name found in the output, `gbrain search "<entity name>"` to check if a page exists. If not, create a stub page:
+```bash
+gbrain put_page --title "<Person or Company Name>" --tags "entity,person" --content "Stub page. Mentioned in <skill name> output."
+```
+Only extract actual person names and company/organization names. Skip product names, section headings, technical terms, and file paths.
+
+Throttle errors appear as: exit code 1 with stderr containing "throttle", "rate limit", "capacity", or "busy". If GBrain returns a throttle or rate-limit error on any save operation, defer the save and move on. The brain is busy — the content is not lost, just not persisted this run. Any other non-zero exit code should also be treated as a transient failure.
+
+Add backlinks to related brain pages if they exist. If GBrain is not available, skip this step.
 
+After brain operations complete, note in your completion output: how many pages were found in the initial search, how many entities were enriched, and whether any operations were throttled. This helps the user see brain utilization over time.
 
 ## Additional Rules (design-review specific)
 

hosts/claude.ts

@@ -24,7 +24,7 @@ const claude: HostConfig = {
 
   pathRewrites: [],  // Claude is the primary host — no rewrites needed
   toolRewrites: {},
-  suppressedResolvers: ['GBRAIN_CONTEXT_LOAD', 'GBRAIN_SAVE_RESULTS'],
+  suppressedResolvers: [],
 
   runtimeRoot: {
     globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],

hosts/codex.ts

@@ -37,8 +37,6 @@ const codex: HostConfig = {
     'CODEX_SECOND_OPINION',   // review.ts:257 — Codex can't invoke itself
     'CODEX_PLAN_REVIEW',      // review.ts:541 — Codex can't invoke itself
     'REVIEW_ARMY',            // review-army.ts:180 — Codex shouldn't orchestrate
-    'GBRAIN_CONTEXT_LOAD',
-    'GBRAIN_SAVE_RESULTS',
   ],
 
   runtimeRoot: {

investigate/SKILL.md

@@ -580,7 +580,23 @@ Fixing symptoms creates whack-a-mole debugging. Every fix that doesn't address r
 
 ---
 
+## Brain Context Load
 
+Before starting this skill, search your brain for relevant context:
+
+1. Extract 2-4 keywords from the user's request (nouns, error names, file paths, technical terms).
+   Search GBrain: `gbrain search "keyword1 keyword2"`
+   Example: for "the login page is broken after deploy", search `gbrain search "login broken deploy"`
+   Search returns lines like: `[slug] Title (score: 0.85) - first line of content...`
+2. If few results, broaden to the single most specific keyword and search again.
+3. For each result page, read it: `gbrain get_page "<page_slug>"`
+   Read the top 3 pages for context.
+4. Use this brain context to inform your analysis.
+
+If GBrain is not available or returns no results, proceed without brain context.
+Any non-zero exit code from gbrain commands should be treated as a transient failure.
+
+If the user's request is about tracking, extracting, or researching structured data (e.g., "track this data", "extract from emails", "build a tracker"), route to GBrain's data-research skill instead: `gbrain call data-research`. This skill has a 7-phase pipeline optimized for structured data extraction.
 
 ## Phase 1: Root Cause Investigation
 
@@ -792,7 +808,28 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **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.
 
+## Save Results to Brain
+
+After completing this skill, persist the results to your brain for future reference:
+
+Save the root cause analysis as a brain page:
+```bash
+gbrain put_page --title "Investigation: <issue summary>" --tags "investigation,<affected-files>" <<'EOF'
+<investigation findings in markdown>
+EOF
+```
+
+After saving the page, extract and enrich mentioned entities: for each actual person name or company/organization name found in the output, `gbrain search "<entity name>"` to check if a page exists. If not, create a stub page:
+```bash
+gbrain put_page --title "<Person or Company Name>" --tags "entity,person" --content "Stub page. Mentioned in <skill name> output."
+```
+Only extract actual person names and company/organization names. Skip product names, section headings, technical terms, and file paths.
+
+Throttle errors appear as: exit code 1 with stderr containing "throttle", "rate limit", "capacity", or "busy". If GBrain returns a throttle or rate-limit error on any save operation, defer the save and move on. The brain is busy — the content is not lost, just not persisted this run. Any other non-zero exit code should also be treated as a transient failure.
+
+Add backlinks to related brain pages if they exist. If GBrain is not available, skip this step.
 
+After brain operations complete, note in your completion output: how many pages were found in the initial search, how many entities were enriched, and whether any operations were throttled. This helps the user see brain utilization over time.
 
 ---
 

office-hours/SKILL.md

@@ -623,7 +623,21 @@ You are a **YC office hours partner**. Your job is to ensure the problem is unde
 
 ---
 
+## Brain Context Load
 
+Before starting this skill, search your brain for relevant context:
+
+1. Extract 2-4 keywords from the user's request (nouns, error names, file paths, technical terms).
+   Search GBrain: `gbrain search "keyword1 keyword2"`
+   Example: for "the login page is broken after deploy", search `gbrain search "login broken deploy"`
+   Search returns lines like: `[slug] Title (score: 0.85) - first line of content...`
+2. If few results, broaden to the single most specific keyword and search again.
+3. For each result page, read it: `gbrain get_page "<page_slug>"`
+   Read the top 3 pages for context.
+4. Use this brain context to inform your analysis.
+
+If GBrain is not available or returns no results, proceed without brain context.
+Any non-zero exit code from gbrain commands should be treated as a transient failure.
 
 ## Phase 1: Context Gathering
 
@@ -1536,7 +1550,28 @@ Present the reviewed design doc to the user via AskUserQuestion:
 - B) Revise — specify which sections need changes (loop back to revise those sections)
 - C) Start over — return to Phase 2
 
+## Save Results to Brain
+
+After completing this skill, persist the results to your brain for future reference:
+
+Save the design document as a brain page:
+```bash
+gbrain put_page --title "Office Hours: <project name>" --tags "design-doc,<project-slug>" <<'EOF'
+<design doc content in markdown>
+EOF
+```
+
+After saving the page, extract and enrich mentioned entities: for each actual person name or company/organization name found in the output, `gbrain search "<entity name>"` to check if a page exists. If not, create a stub page:
+```bash
+gbrain put_page --title "<Person or Company Name>" --tags "entity,person" --content "Stub page. Mentioned in <skill name> output."
+```
+Only extract actual person names and company/organization names. Skip product names, section headings, technical terms, and file paths.
+
+Throttle errors appear as: exit code 1 with stderr containing "throttle", "rate limit", "capacity", or "busy". If GBrain returns a throttle or rate-limit error on any save operation, defer the save and move on. The brain is busy — the content is not lost, just not persisted this run. Any other non-zero exit code should also be treated as a transient failure.
+
+Add backlinks to related brain pages if they exist. If GBrain is not available, skip this step.
 
+After brain operations complete, note in your completion output: how many pages were found in the initial search, how many entities were enriched, and whether any operations were throttled. This helps the user see brain utilization over time.
 
 ---
 

plan-ceo-review/SKILL.md

@@ -888,7 +888,21 @@ matches a past learning, display:
 This makes the compounding visible. The user should see that gstack is getting
 smarter on their codebase over time.
 
+## Brain Context Load
 
+Before starting this skill, search your brain for relevant context:
+
+1. Extract 2-4 keywords from the user's request (nouns, error names, file paths, technical terms).
+   Search GBrain: `gbrain search "keyword1 keyword2"`
+   Example: for "the login page is broken after deploy", search `gbrain search "login broken deploy"`
+   Search returns lines like: `[slug] Title (score: 0.85) - first line of content...`
+2. If few results, broaden to the single most specific keyword and search again.
+3. For each result page, read it: `gbrain get_page "<page_slug>"`
+   Read the top 3 pages for context.
+4. Use this brain context to inform your analysis.
+
+If GBrain is not available or returns no results, proceed without brain context.
+Any non-zero exit code from gbrain commands should be treated as a transient failure.
 
 ## Step 0: Nuclear Scope Challenge + Mode Selection
 
@@ -1831,7 +1845,28 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **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.
 
+## Save Results to Brain
+
+After completing this skill, persist the results to your brain for future reference:
+
+Save the CEO plan as a brain page:
+```bash
+gbrain put_page --title "CEO Plan: <feature name>" --tags "ceo-plan,<feature-slug>" <<'EOF'
+<scope decisions and vision in markdown>
+EOF
+```
+
+After saving the page, extract and enrich mentioned entities: for each actual person name or company/organization name found in the output, `gbrain search "<entity name>"` to check if a page exists. If not, create a stub page:
+```bash
+gbrain put_page --title "<Person or Company Name>" --tags "entity,person" --content "Stub page. Mentioned in <skill name> output."
+```
+Only extract actual person names and company/organization names. Skip product names, section headings, technical terms, and file paths.
+
+Throttle errors appear as: exit code 1 with stderr containing "throttle", "rate limit", "capacity", or "busy". If GBrain returns a throttle or rate-limit error on any save operation, defer the save and move on. The brain is busy — the content is not lost, just not persisted this run. Any other non-zero exit code should also be treated as a transient failure.
+
+Add backlinks to related brain pages if they exist. If GBrain is not available, skip this step.
 
+After brain operations complete, note in your completion output: how many pages were found in the initial search, how many entities were enriched, and whether any operations were throttled. This helps the user see brain utilization over time.
 
 ## Mode Quick Reference
 ```