RomanNum3ral
/
gstack
mirror of https://github.com/garrytan/gstack.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

feat(brain): wire 5 planning skill templates with BRAIN_* placeholders (T6) 

Adds three placeholders to each of the 5 planning SKILL.md.tmpl files:
  {{BRAIN_PREFLIGHT}}     — top of skill body, before first interactive
                            section. Loads the per-skill digest subset
                            (5 files for office-hours, 2 for plan-eng-
                            review, etc.) into the prompt context before
                            any AskUserQuestion fires.
  {{BRAIN_WRITE_BACK}}    — end of skill, before refresh hook. Phase 2
                            calibration write path; gated on personal
                            policy + BRAIN_CALIBRATION_WRITEBACK flag.
  {{BRAIN_CACHE_REFRESH}} — end of skill, after write-back. Non-blocking
                            background refresh so next invocation gets
                            warm cache.

Files touched (templates + regenerated SKILL.md):
  office-hours/SKILL.md.tmpl
  plan-ceo-review/SKILL.md.tmpl
  plan-eng-review/SKILL.md.tmpl
  plan-design-review/SKILL.md.tmpl
  plan-devex-review/SKILL.md.tmpl
  (matching .md files regenerated via bun run gen:skill-docs)

All 5 generated SKILL.md files now contain the rendered ## Brain Context
(preflight) section + write-back guidance + background-refresh hook. The
resolver renders only for skills in SKILL_DIGEST_SUBSETS — these 5 + an
empty string for any other skill that drops in the placeholders.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-05-26 23:12:27 -07:00
parent 5373bc32ae
commit 71ee115bf5
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
10 changed files with 465 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

91
office-hours/SKILL.md
View File

@ -770,6 +770,44 @@ You are a **YC office hours partner**. Your job is to ensure the problem is unde
## Brain Context (preflight)
Before asking any clarifying questions, load the brain's structured context
for this project. The cache layer handles staleness, refresh, and stale-but-
usable fallback automatically. Skip questions whose answers are already
present in the loaded context; ground recommendations in what the brain
already knows about the user, the product, the goals, and recent decisions.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
{
printf '## Brain Context\n\n'
printf '\n### %s\n\n' "product"
~/.claude/skills/gstack/bin/gstack-brain-cache get product --project "$SLUG" 2>/dev/null || printf '_(no product digest available yet)_\n'
printf '\n### %s\n\n' "goals"
~/.claude/skills/gstack/bin/gstack-brain-cache get goals --project "$SLUG" 2>/dev/null || printf '_(no goals digest available yet)_\n'
printf '\n### %s\n\n' "user-profile"
~/.claude/skills/gstack/bin/gstack-brain-cache get user-profile 2>/dev/null || printf '_(no user-profile digest available yet)_\n'
printf '\n### %s\n\n' "recent-decisions"
~/.claude/skills/gstack/bin/gstack-brain-cache get recent-decisions --project "$SLUG" 2>/dev/null || printf '_(no recent-decisions digest available yet)_\n'
printf '\n### %s\n\n' "salience"
~/.claude/skills/gstack/bin/gstack-brain-cache get salience --project "$SLUG" 2>/dev/null || printf '_(no salience digest available yet)_\n'
} > /tmp/.gstack-brain-context-$$.md 2>/dev/null
[ -s /tmp/.gstack-brain-context-$$.md ] && cat /tmp/.gstack-brain-context-$$.md
rm -f /tmp/.gstack-brain-context-$$.md 2>/dev/null || true
```
**How to use this context:**
- If `product` digest names the value prop, target user, or stage — don't re-ask.
- If `goals` digest lists active goals — frame recommendations against them.
- If `recent-decisions` digest names a prior scope/architecture choice — flag if this plan contradicts.
- If `user-profile` digest carries calibration pattern statements ("tends to over-engineer security") — surface them when relevant.
- If a digest is `(no X digest available yet)`, treat that section as cold; ask the user.
**Privacy:** Salience digest is filtered by allowlist (D9 default: `projects/`,
`gstack/`, `concepts/` only). Personal/family/therapy content never leaks here.
## Phase 1: Context Gathering
Understand the project and the area the user wants to change.
@ -1703,6 +1741,59 @@ Present the reviewed design doc to the user via AskUserQuestion:
## Brain Calibration Write-Back (Phase 2 / gated)
When the skill makes a typed prediction worth tracking (scope decision,
TTHW target, architectural bet, wedge commitment), it MAY write a
`kind=bet` take to the brain so a calibration profile builds over time.
**Gated on two things:**
1. Brain trust policy for the active endpoint is `personal` (check via
`~/.claude/skills/gstack/bin/gstack-config get brain_trust_policy@<endpoint-hash>`).
Shared brains skip write-back to avoid polluting team calibration.
2. Feature flag `BRAIN_CALIBRATION_WRITEBACK` is set (today: false; flips
to true when upstream gbrain v0.42+ ships `takes_add` MCP op).
When both gates pass, the write-back path uses `mcp__gbrain__takes_add`
to record a take with weight 0.9 (per SKILL_CALIBRATION_WEIGHTS).
If the MCP op is unavailable, fall back to `mcp__gbrain__put_page` with
a gstack:takes fence block (documented but uglier path).
Mandatory take frontmatter shape:
```yaml
kind: bet
holder: <user identity from whoami>
claim: <one-line prediction the skill is making>
weight: 0.9
since_date: <today's date>
expected_resolution: <date in 1-3 months depending on skill>
source_skill: office-hours
```
After write, invalidate the affected digests so the next preflight reflects
the new state:
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
~/.claude/skills/gstack/bin/gstack-brain-cache invalidate product --project "$SLUG" 2>/dev/null || true
~/.claude/skills/gstack/bin/gstack-brain-cache invalidate goals --project "$SLUG" 2>/dev/null || true
~/.claude/skills/gstack/bin/gstack-brain-cache invalidate competitive-intel --project "$SLUG" 2>/dev/null || true
```
## Brain Cache Background Refresh
After the skill's work completes (and telemetry has logged), kick a
background refresh of any cache digest that's getting close to its TTL.
This is non-blocking — the user doesn't wait. Next invocation benefits
from the warm cache.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
(~/.claude/skills/gstack/bin/gstack-brain-cache refresh --project "$SLUG" 2>/dev/null &) || true
```
---
## Phase 6: Handoff — The Relationship Closing

6
office-hours/SKILL.md.tmpl
View File

@ -71,6 +71,8 @@ You are a **YC office hours partner**. Your job is to ensure the problem is unde
{{GBRAIN_CONTEXT_LOAD}}
{{BRAIN_PREFLIGHT}}
## Phase 1: Context Gathering
Understand the project and the area the user wants to change.
@ -647,6 +649,10 @@ Present the reviewed design doc to the user via AskUserQuestion:
{{GBRAIN_SAVE_RESULTS}}
{{BRAIN_WRITE_BACK}}
{{BRAIN_CACHE_REFRESH}}
---
## Phase 6: Handoff — The Relationship Closing

89
plan-ceo-review/SKILL.md
View File

@ -1033,6 +1033,42 @@ smarter on their codebase over time.
## Brain Context (preflight)
Before asking any clarifying questions, load the brain's structured context
for this project. The cache layer handles staleness, refresh, and stale-but-
usable fallback automatically. Skip questions whose answers are already
present in the loaded context; ground recommendations in what the brain
already knows about the user, the product, the goals, and recent decisions.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
{
printf '## Brain Context\n\n'
printf '\n### %s\n\n' "product"
~/.claude/skills/gstack/bin/gstack-brain-cache get product --project "$SLUG" 2>/dev/null || printf '_(no product digest available yet)_\n'
printf '\n### %s\n\n' "goals"
~/.claude/skills/gstack/bin/gstack-brain-cache get goals --project "$SLUG" 2>/dev/null || printf '_(no goals digest available yet)_\n'
printf '\n### %s\n\n' "recent-decisions"
~/.claude/skills/gstack/bin/gstack-brain-cache get recent-decisions --project "$SLUG" 2>/dev/null || printf '_(no recent-decisions digest available yet)_\n'
printf '\n### %s\n\n' "user-profile"
~/.claude/skills/gstack/bin/gstack-brain-cache get user-profile 2>/dev/null || printf '_(no user-profile digest available yet)_\n'
} > /tmp/.gstack-brain-context-$$.md 2>/dev/null
[ -s /tmp/.gstack-brain-context-$$.md ] && cat /tmp/.gstack-brain-context-$$.md
rm -f /tmp/.gstack-brain-context-$$.md 2>/dev/null || true
```
**How to use this context:**
- If `product` digest names the value prop, target user, or stage — don't re-ask.
- If `goals` digest lists active goals — frame recommendations against them.
- If `recent-decisions` digest names a prior scope/architecture choice — flag if this plan contradicts.
- If `user-profile` digest carries calibration pattern statements ("tends to over-engineer security") — surface them when relevant.
- If a digest is `(no X digest available yet)`, treat that section as cold; ask the user.
**Privacy:** Salience digest is filtered by allowlist (D9 default: `projects/`,
`gstack/`, `concepts/` only). Personal/family/therapy content never leaks here.
## Step 0: Nuclear Scope Challenge + Mode Selection
### 0A. Premise Challenge
@ -2085,6 +2121,59 @@ already knows. A good test: would this insight save time in a future session? If
## Brain Calibration Write-Back (Phase 2 / gated)
When the skill makes a typed prediction worth tracking (scope decision,
TTHW target, architectural bet, wedge commitment), it MAY write a
`kind=bet` take to the brain so a calibration profile builds over time.
**Gated on two things:**
1. Brain trust policy for the active endpoint is `personal` (check via
`~/.claude/skills/gstack/bin/gstack-config get brain_trust_policy@<endpoint-hash>`).
Shared brains skip write-back to avoid polluting team calibration.
2. Feature flag `BRAIN_CALIBRATION_WRITEBACK` is set (today: false; flips
to true when upstream gbrain v0.42+ ships `takes_add` MCP op).
When both gates pass, the write-back path uses `mcp__gbrain__takes_add`
to record a take with weight 0.8 (per SKILL_CALIBRATION_WEIGHTS).
If the MCP op is unavailable, fall back to `mcp__gbrain__put_page` with
a gstack:takes fence block (documented but uglier path).
Mandatory take frontmatter shape:
```yaml
kind: bet
holder: <user identity from whoami>
claim: <one-line prediction the skill is making>
weight: 0.8
since_date: <today's date>
expected_resolution: <date in 1-3 months depending on skill>
source_skill: plan-ceo-review
```
After write, invalidate the affected digests so the next preflight reflects
the new state:
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
~/.claude/skills/gstack/bin/gstack-brain-cache invalidate product --project "$SLUG" 2>/dev/null || true
~/.claude/skills/gstack/bin/gstack-brain-cache invalidate goals --project "$SLUG" 2>/dev/null || true
~/.claude/skills/gstack/bin/gstack-brain-cache invalidate competitive-intel --project "$SLUG" 2>/dev/null || true
```
## Brain Cache Background Refresh
After the skill's work completes (and telemetry has logged), kick a
background refresh of any cache digest that's getting close to its TTL.
This is non-blocking — the user doesn't wait. Next invocation benefits
from the warm cache.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
(~/.claude/skills/gstack/bin/gstack-brain-cache refresh --project "$SLUG" 2>/dev/null &) || true
```
## Mode Quick Reference
```
┌────────────────────────────────────────────────────────────────────────────────┐

6
plan-ceo-review/SKILL.md.tmpl
View File

@ -222,6 +222,8 @@ Feed into the Premise Challenge (0A) and Dream State Mapping (0C). If you find a
{{GBRAIN_CONTEXT_LOAD}}
{{BRAIN_PREFLIGHT}}
## Step 0: Nuclear Scope Challenge + Mode Selection
### 0A. Premise Challenge
@ -854,6 +856,10 @@ If promoted, copy the CEO plan content to `docs/designs/{FEATURE}.md` (create th
{{GBRAIN_SAVE_RESULTS}}
{{BRAIN_WRITE_BACK}}
{{BRAIN_CACHE_REFRESH}}
## Mode Quick Reference
```
┌────────────────────────────────────────────────────────────────────────────────┐

85
plan-design-review/SKILL.md
View File

@ -963,6 +963,40 @@ MUST be saved to `~/.gstack/projects/$SLUG/designs/`, NEVER to `.context/`,
`docs/designs/`, `/tmp/`, or any project-local directory. Design artifacts are USER
data, not project files. They persist across branches, conversations, and workspaces.
## Brain Context (preflight)
Before asking any clarifying questions, load the brain's structured context
for this project. The cache layer handles staleness, refresh, and stale-but-
usable fallback automatically. Skip questions whose answers are already
present in the loaded context; ground recommendations in what the brain
already knows about the user, the product, the goals, and recent decisions.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
{
printf '## Brain Context\n\n'
printf '\n### %s\n\n' "product"
~/.claude/skills/gstack/bin/gstack-brain-cache get product --project "$SLUG" 2>/dev/null || printf '_(no product digest available yet)_\n'
printf '\n### %s\n\n' "brand"
~/.claude/skills/gstack/bin/gstack-brain-cache get brand --project "$SLUG" 2>/dev/null || printf '_(no brand digest available yet)_\n'
printf '\n### %s\n\n' "recent-decisions"
~/.claude/skills/gstack/bin/gstack-brain-cache get recent-decisions --project "$SLUG" 2>/dev/null || printf '_(no recent-decisions digest available yet)_\n'
} > /tmp/.gstack-brain-context-$$.md 2>/dev/null
[ -s /tmp/.gstack-brain-context-$$.md ] && cat /tmp/.gstack-brain-context-$$.md
rm -f /tmp/.gstack-brain-context-$$.md 2>/dev/null || true
```
**How to use this context:**
- If `product` digest names the value prop, target user, or stage — don't re-ask.
- If `goals` digest lists active goals — frame recommendations against them.
- If `recent-decisions` digest names a prior scope/architecture choice — flag if this plan contradicts.
- If `user-profile` digest carries calibration pattern statements ("tends to over-engineer security") — surface them when relevant.
- If a digest is `(no X digest available yet)`, treat that section as cold; ask the user.
**Privacy:** Salience digest is filtered by allowlist (D9 default: `projects/`,
`gstack/`, `concepts/` only). Personal/family/therapy content never leaks here.
## Step 0: Design Scope Assessment
### 0A. Initial Design Rating
@ -1825,6 +1859,57 @@ 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.
## Brain Calibration Write-Back (Phase 2 / gated)
When the skill makes a typed prediction worth tracking (scope decision,
TTHW target, architectural bet, wedge commitment), it MAY write a
`kind=bet` take to the brain so a calibration profile builds over time.
**Gated on two things:**
1. Brain trust policy for the active endpoint is `personal` (check via
`~/.claude/skills/gstack/bin/gstack-config get brain_trust_policy@<endpoint-hash>`).
Shared brains skip write-back to avoid polluting team calibration.
2. Feature flag `BRAIN_CALIBRATION_WRITEBACK` is set (today: false; flips
to true when upstream gbrain v0.42+ ships `takes_add` MCP op).
When both gates pass, the write-back path uses `mcp__gbrain__takes_add`
to record a take with weight 0.5 (per SKILL_CALIBRATION_WEIGHTS).
If the MCP op is unavailable, fall back to `mcp__gbrain__put_page` with
a gstack:takes fence block (documented but uglier path).
Mandatory take frontmatter shape:
```yaml
kind: bet
holder: <user identity from whoami>
claim: <one-line prediction the skill is making>
weight: 0.5
since_date: <today's date>
expected_resolution: <date in 1-3 months depending on skill>
source_skill: plan-design-review
```
After write, invalidate the affected digests so the next preflight reflects
the new state:
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
~/.claude/skills/gstack/bin/gstack-brain-cache invalidate brand --project "$SLUG" 2>/dev/null || true
```
## Brain Cache Background Refresh
After the skill's work completes (and telemetry has logged), kick a
background refresh of any cache digest that's getting close to its TTL.
This is non-blocking — the user doesn't wait. Next invocation benefits
from the warm cache.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
(~/.claude/skills/gstack/bin/gstack-brain-cache refresh --project "$SLUG" 2>/dev/null &) || true
```
## 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.

6
plan-design-review/SKILL.md.tmpl
View File

@ -138,6 +138,8 @@ Report findings before proceeding to Step 0.
{{DESIGN_SETUP}}
{{BRAIN_PREFLIGHT}}
## Step 0: Design Scope Assessment
### 0A. Initial Design Rating
@ -448,6 +450,10 @@ Substitute values from the Completion Summary:
{{LEARNINGS_LOG}}
{{BRAIN_WRITE_BACK}}
{{BRAIN_CACHE_REFRESH}}
## 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.

87
plan-devex-review/SKILL.md
View File

@ -956,6 +956,42 @@ Note the product type; it influences which persona options are offered in Step 0
---
## Brain Context (preflight)
Before asking any clarifying questions, load the brain's structured context
for this project. The cache layer handles staleness, refresh, and stale-but-
usable fallback automatically. Skip questions whose answers are already
present in the loaded context; ground recommendations in what the brain
already knows about the user, the product, the goals, and recent decisions.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
{
printf '## Brain Context\n\n'
printf '\n### %s\n\n' "product"
~/.claude/skills/gstack/bin/gstack-brain-cache get product --project "$SLUG" 2>/dev/null || printf '_(no product digest available yet)_\n'
printf '\n### %s\n\n' "developer-persona"
~/.claude/skills/gstack/bin/gstack-brain-cache get developer-persona --project "$SLUG" 2>/dev/null || printf '_(no developer-persona digest available yet)_\n'
printf '\n### %s\n\n' "recent-decisions"
~/.claude/skills/gstack/bin/gstack-brain-cache get recent-decisions --project "$SLUG" 2>/dev/null || printf '_(no recent-decisions digest available yet)_\n'
printf '\n### %s\n\n' "competitive-intel"
~/.claude/skills/gstack/bin/gstack-brain-cache get competitive-intel --project "$SLUG" 2>/dev/null || printf '_(no competitive-intel digest available yet)_\n'
} > /tmp/.gstack-brain-context-$$.md 2>/dev/null
[ -s /tmp/.gstack-brain-context-$$.md ] && cat /tmp/.gstack-brain-context-$$.md
rm -f /tmp/.gstack-brain-context-$$.md 2>/dev/null || true
```
**How to use this context:**
- If `product` digest names the value prop, target user, or stage — don't re-ask.
- If `goals` digest lists active goals — frame recommendations against them.
- If `recent-decisions` digest names a prior scope/architecture choice — flag if this plan contradicts.
- If `user-profile` digest carries calibration pattern statements ("tends to over-engineer security") — surface them when relevant.
- If a digest is `(no X digest available yet)`, treat that section as cold; ask the user.
**Privacy:** Salience digest is filtered by allowlist (D9 default: `projects/`,
`gstack/`, `concepts/` only). Personal/family/therapy content never leaks here.
## Step 0: DX Investigation (before scoring)
The core principle: **gather evidence and force decisions BEFORE scoring, not during
@ -2003,6 +2039,57 @@ 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.
## Brain Calibration Write-Back (Phase 2 / gated)
When the skill makes a typed prediction worth tracking (scope decision,
TTHW target, architectural bet, wedge commitment), it MAY write a
`kind=bet` take to the brain so a calibration profile builds over time.
**Gated on two things:**
1. Brain trust policy for the active endpoint is `personal` (check via
`~/.claude/skills/gstack/bin/gstack-config get brain_trust_policy@<endpoint-hash>`).
Shared brains skip write-back to avoid polluting team calibration.
2. Feature flag `BRAIN_CALIBRATION_WRITEBACK` is set (today: false; flips
to true when upstream gbrain v0.42+ ships `takes_add` MCP op).
When both gates pass, the write-back path uses `mcp__gbrain__takes_add`
to record a take with weight 0.6 (per SKILL_CALIBRATION_WEIGHTS).
If the MCP op is unavailable, fall back to `mcp__gbrain__put_page` with
a gstack:takes fence block (documented but uglier path).
Mandatory take frontmatter shape:
```yaml
kind: bet
holder: <user identity from whoami>
claim: <one-line prediction the skill is making>
weight: 0.6
since_date: <today's date>
expected_resolution: <date in 1-3 months depending on skill>
source_skill: plan-devex-review
```
After write, invalidate the affected digests so the next preflight reflects
the new state:
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
~/.claude/skills/gstack/bin/gstack-brain-cache invalidate developer-persona --project "$SLUG" 2>/dev/null || true
```
## Brain Cache Background Refresh
After the skill's work completes (and telemetry has logged), kick a
background refresh of any cache digest that's getting close to its TTL.
This is non-blocking — the user doesn't wait. Next invocation benefits
from the warm cache.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
(~/.claude/skills/gstack/bin/gstack-brain-cache refresh --project "$SLUG" 2>/dev/null &) || true
```
## Next Steps — Review Chaining
After displaying the Review Readiness Dashboard, recommend next reviews:

6
plan-devex-review/SKILL.md.tmpl
View File

@ -136,6 +136,8 @@ Note the product type; it influences which persona options are offered in Step 0
---
{{BRAIN_PREFLIGHT}}
## Step 0: DX Investigation (before scoring)
The core principle: **gather evidence and force decisions BEFORE scoring, not during
@ -787,6 +789,10 @@ If any AskUserQuestion goes unanswered, note here. Never silently default.
{{LEARNINGS_LOG}}
{{BRAIN_WRITE_BACK}}
{{BRAIN_CACHE_REFRESH}}
## Next Steps — Review Chaining
After displaying the Review Readiness Dashboard, recommend next reviews:

83
plan-eng-review/SKILL.md
View File

@ -738,6 +738,38 @@ When evaluating architecture, think "boring by default." When reviewing tests, t
* For particularly complex designs or behaviors, embed ASCII diagrams directly in code comments in the appropriate places: Models (data relationships, state transitions), Controllers (request flow), Concerns (mixin behavior), Services (processing pipelines), and Tests (what's being set up and why) when the test structure is non-obvious.
* **Diagram maintenance is part of the change.** When modifying code that has ASCII diagrams in comments nearby, review whether those diagrams are still accurate. Update them as part of the same commit. Stale diagrams are worse than no diagrams — they actively mislead. Flag any stale diagrams you encounter during review even if they're outside the immediate scope of the change.
## Brain Context (preflight)
Before asking any clarifying questions, load the brain's structured context
for this project. The cache layer handles staleness, refresh, and stale-but-
usable fallback automatically. Skip questions whose answers are already
present in the loaded context; ground recommendations in what the brain
already knows about the user, the product, the goals, and recent decisions.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
{
printf '## Brain Context\n\n'
printf '\n### %s\n\n' "product"
~/.claude/skills/gstack/bin/gstack-brain-cache get product --project "$SLUG" 2>/dev/null || printf '_(no product digest available yet)_\n'
printf '\n### %s\n\n' "recent-decisions"
~/.claude/skills/gstack/bin/gstack-brain-cache get recent-decisions --project "$SLUG" 2>/dev/null || printf '_(no recent-decisions digest available yet)_\n'
} > /tmp/.gstack-brain-context-$$.md 2>/dev/null
[ -s /tmp/.gstack-brain-context-$$.md ] && cat /tmp/.gstack-brain-context-$$.md
rm -f /tmp/.gstack-brain-context-$$.md 2>/dev/null || true
```
**How to use this context:**
- If `product` digest names the value prop, target user, or stage — don't re-ask.
- If `goals` digest lists active goals — frame recommendations against them.
- If `recent-decisions` digest names a prior scope/architecture choice — flag if this plan contradicts.
- If `user-profile` digest carries calibration pattern statements ("tends to over-engineer security") — surface them when relevant.
- If a digest is `(no X digest available yet)`, treat that section as cold; ask the user.
**Privacy:** Salience digest is filtered by allowlist (D9 default: `projects/`,
`gstack/`, `concepts/` only). Personal/family/therapy content never leaks here.
## BEFORE YOU START:
### Design Doc Check
@ -1669,6 +1701,57 @@ already knows. A good test: would this insight save time in a future session? If
## Brain Calibration Write-Back (Phase 2 / gated)
When the skill makes a typed prediction worth tracking (scope decision,
TTHW target, architectural bet, wedge commitment), it MAY write a
`kind=bet` take to the brain so a calibration profile builds over time.
**Gated on two things:**
1. Brain trust policy for the active endpoint is `personal` (check via
`~/.claude/skills/gstack/bin/gstack-config get brain_trust_policy@<endpoint-hash>`).
Shared brains skip write-back to avoid polluting team calibration.
2. Feature flag `BRAIN_CALIBRATION_WRITEBACK` is set (today: false; flips
to true when upstream gbrain v0.42+ ships `takes_add` MCP op).
When both gates pass, the write-back path uses `mcp__gbrain__takes_add`
to record a take with weight 0.7 (per SKILL_CALIBRATION_WEIGHTS).
If the MCP op is unavailable, fall back to `mcp__gbrain__put_page` with
a gstack:takes fence block (documented but uglier path).
Mandatory take frontmatter shape:
```yaml
kind: bet
holder: <user identity from whoami>
claim: <one-line prediction the skill is making>
weight: 0.7
since_date: <today's date>
expected_resolution: <date in 1-3 months depending on skill>
source_skill: plan-eng-review
```
After write, invalidate the affected digests so the next preflight reflects
the new state:
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
# (no per-skill invalidation targets configured)
```
## Brain Cache Background Refresh
After the skill's work completes (and telemetry has logged), kick a
background refresh of any cache digest that's getting close to its TTL.
This is non-blocking — the user doesn't wait. Next invocation benefits
from the warm cache.
```bash
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
(~/.claude/skills/gstack/bin/gstack-brain-cache refresh --project "$SLUG" 2>/dev/null &) || true
```
## 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.

6
plan-eng-review/SKILL.md.tmpl
View File

@ -75,6 +75,8 @@ When evaluating architecture, think "boring by default." When reviewing tests, t
* For particularly complex designs or behaviors, embed ASCII diagrams directly in code comments in the appropriate places: Models (data relationships, state transitions), Controllers (request flow), Concerns (mixin behavior), Services (processing pipelines), and Tests (what's being set up and why) when the test structure is non-obvious.
* **Diagram maintenance is part of the change.** When modifying code that has ASCII diagrams in comments nearby, review whether those diagrams are still accurate. Update them as part of the same commit. Stale diagrams are worse than no diagrams — they actively mislead. Flag any stale diagrams you encounter during review even if they're outside the immediate scope of the change.
{{BRAIN_PREFLIGHT}}
## BEFORE YOU START:
### Design Doc Check
@ -321,6 +323,10 @@ Substitute values from the Completion Summary:
{{GBRAIN_SAVE_RESULTS}}
{{BRAIN_WRITE_BACK}}
{{BRAIN_CACHE_REFRESH}}
## 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.