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/statusgit 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 | $0.00019 | $0.01003 |
| Opus 5 | $0.00010 | $0.00502 |
| Sonnet 5 | $0.00004 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade B, and why
status scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -rEc '\{\{[A-Z_]+\}\}' CLAUDE.md claude/ .claude/ 2>/dev/null | awk -F: '{s+=$2} END {print s+0}' How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Status Dashboard
Give me a one-glance status report of the Claude Code setup for this repo.
Run these checks in order and report each as ✅ / ⚠️ / ❌:
1. CLAUDE.md line budget
wc -l < CLAUDE.md 2>/dev/null || echo "MISSING"
- ✅ ≤ 200 lines · ⚠️ 201–240 · ❌ > 240 or missing
2. Unfilled placeholders
grep -rEc '\{\{[A-Z_]+\}\}' CLAUDE.md claude/ .claude/ 2>/dev/null | awk -F: '{s+=$2} END {print s+0}'
- ✅ 0 (end-user repo) · ⚠️ > 0 (bootstrap still has unfilled slots)
3. Lessons file size
wc -l < claude/tasks/lessons.md 2>/dev/null || echo "0"
- ✅ ≤ 400 lines · ⚠️ 401–500 · ❌ > 500 (archive to
claude/tasks/lessons-archive-YYYY.md)
4. Hooks executability
for h in .claude/hooks/*.sh; do test -x "$h" || echo "NOT_EXEC: $h"; done
echo "HOOKS_DONE"
- ✅ all executable · ❌ any NOT_EXEC line
5. jq availability (3 safety hooks depend on it)
command -v jq &>/dev/null && echo "PRESENT" || echo "MISSING"
- ✅ present · ⚠️ missing —
brew install jq
6. Plugin states
Check each binary/tool and report installed/missing:
echo "rtk:$(command -v rtk &>/dev/null && echo installed || echo missing)"
echo "codebase-memory-mcp:$(command -v codebase-memory-mcp &>/dev/null && echo installed || echo missing)"
echo "ccc:$(command -v ccc &>/dev/null && echo installed || echo missing)"
echo "code-review-graph:$(command -v code-review-graph &>/dev/null && echo installed || echo missing)"
echo "graphify:$(command -v graphify &>/dev/null && echo installed || echo missing)"
- ✅ installed · ⚠️ missing (run
bash claude/scripts/setup-plugins.shto install)
Also check claude-mem if the claude CLI is available:
command -v claude &>/dev/null && (claude plugin list 2>/dev/null | grep -qi 'claude-mem' && echo "claude-mem:installed" || echo "claude-mem:missing") || echo "claude-mem:no-cli"
7. Knowledge graph
test -f graphify-out/GRAPH_REPORT.md && echo "PRESENT" || echo "MISSING"
- ✅ present · ⚠️ missing — run
/graphify .to build (first run ~5 min)
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 · 100 lines · 19 tokens per session scan B fbfb81c941e8
status is a command published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 1,003 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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"".