Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/brain-bootstrap/claude-code-brain-bootstrap/reviewgit clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrapWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.00547 |
| Opus 5 | $0.00008 | $0.00273 |
| Sonnet 5 | $0.00003 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perform a full MR review on the current branch.
ultrathink — use extended reasoning for thorough cross-layer analysis.
Pre-loaded context
Branch: !git branch --show-current
Diff stat: !git --no-pager diff main...HEAD --stat 2>/dev/null || echo "Not on a feature branch"
Commits: !git --no-pager log main...HEAD --oneline 2>/dev/null || echo "N/A"
Instructions
Read these files first:
claude/rules.md(review protocol)claude/architecture.md(system context)claude/tasks/lessons.md(past mistakes to avoid)
Step 0 — Lessons pre-scan: Before running the checklist, scan claude/tasks/lessons.md for entries whose file paths, module names, or topic keywords overlap with the files in the diff. Extract matching lessons and prepend them as project-specific check items at the top of your review (e.g. "⚠️ Lesson: hooks must be executable — check .claude/hooks/*.sh"). These lessons represent real mistakes from this project that the standard 10-point protocol won't catch.
Then execute the review protocol:
- Ticket re-read — If a ticket reference exists in the branch name, find and read it. Verify every scenario is addressed.
- Diff analysis — Run
git --no-pager diff main...HEAD --statto identify all changed files. Then read the full diff. - Cross-layer consistency — For every new field/constant, grep across all layers. Report any gaps.
- Enum completeness — For any modified switch/case, verify all enum values are handled.
- Transaction safety — Trace every write caller. Confirm read callers don't write.
- Race condition analysis — Trace concurrent flows.
- Test scenario completeness — Verify every new branch/case has a dedicated test.
- Pre-existing vs introduced — Run linter on changed files. Distinguish pre-existing from introduced warnings.
- Cross-branch merge safety — Check if other branches are in flight that touch the same files.
- 100/100 confidence gate — Present a confidence score for each item. Do NOT generate MR description until all pass.
- Generate MR description — Write to
claude/tasks/mr-description-<branch>.mdusing the template fromclaude/templates.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 39 lines · 16 tokens per session scan A 310253d48589
review is a command published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 547 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
setup-content
Lesson command — 教材コンテンツの初回セットアップ.
new-workshop
Spin up a new workshop launch package by answering 8 questions. Generates a complete folder with branded landing page, install guide, 21-email campaign, DM outreach, VSL script, agenda, Notion master doc, and 4 phase-walkthrough video compositions. Reads your BUSINESS-BRAIN.md for voice + brand. Triggers on "new…
harness-onboarding
Generate a human-readable onboarding document from HARNESS.md, AGENTS.md, and REFLECTIONLOG.md — a friendly guide for new team members.
ome-evolve
Analyze local memory for learning and skill candidates.