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/maintaingit 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 | $0.00014 | $0.00396 |
| Opus 5 | $0.00007 | $0.00198 |
| Sonnet 5 | $0.00003 | $0.00079 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
maintain 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.
What it actually says
Run a knowledge base maintenance cycle: $ARGUMENTS
Instructions
Mode selection
| Argument | Action |
|---|---|
full or (empty) |
Run ALL checks below sequentially |
paths |
Verify all file paths in claude/*.md still exist |
lessons |
Check claude/tasks/lessons.md line count; archive if >500 |
inventory |
Verify claude/README.md tables match actual files |
stale |
Grep all knowledge files for stale references |
Steps for full mode
- Verify file paths — Grep file paths from
claude/*.mdand verify they exist on disk - Verify lookup table — Compare
CLAUDE.mdlookup entries againstls claude/*.md - Verify rules inventory — Compare
.claude/rules/*.mdagainst README - Verify commands inventory — Compare
.claude/commands/*.mdagainst README - Lessons health —
wc -l claude/tasks/lessons.md— if >500 lines, archive older entries - Stale references — Grep for deleted symbols, old paths, stale field names
- CLAUDE.md size — Verify
wc -l CLAUDE.md≤ 200 lines - Rule sizes — Verify each
.claude/rules/*.md≤ 40 lines - Report — Present summary with issues found and fixes applied
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 · 34 lines · 14 tokens per session scan A 45dd0c6c39ed
maintain is a command published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 396 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
learn
Force claude-smart to extract learnings from this session now.
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
memory-store
Store an insight, decision, or pattern to memory.
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).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".