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/bootstrapgit 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 | $0.00022 | $0.01047 |
| Opus 5 | $0.00011 | $0.00524 |
| Sonnet 5 | $0.00004 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade C, and why
bootstrap scanned grade C 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- If **MISSING**: the scaffolding was cleaned up after a previous bootstrap. Tell the user to re-install: `git clone https://github.com/brain-bootstrap/claude-code-brain-bootstrap.git /tmp/brain && bash /tmp/brain/instal How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-configure Claude Code for this repository: $ARGUMENTS
ultrathink — use extended reasoning for thorough repository analysis and safe merging.
⚠️ AUTONOMOUS EXECUTION: Run all phases A to Z without stopping. NO "shall I proceed?", NO confirmation prompts, NO pauses between phases. If user asks a question mid-bootstrap, answer briefly then continue. ONLY stop for genuine blockers (missing file, script failure).
Instructions
Step 0 — Verify scaffolding exists (MUST do first): Run this bash command to check if the bootstrap scaffolding is present:
test -f claude/bootstrap/PROMPT.md && echo "FOUND" || echo "MISSING"
- If FOUND: read
claude/bootstrap/PROMPT.mdusing the read_file tool (use the exact pathclaude/bootstrap/PROMPT.md), then execute the bootstrap process autonomously. - If MISSING: the scaffolding was cleaned up after a previous bootstrap. Tell the user to re-install:
git clone https://github.com/brain-bootstrap/claude-code-brain-bootstrap.git /tmp/brain && bash /tmp/brain/install.sh . && rm -rf /tmp/brain— then run/bootstrapagain.
⚠️ Do NOT use file search to find PROMPT.md — newly installed files may not be in the git index yet. Use
test -forread_filewith the exact path.
Quick summary of phases:
- Discovery — Run
bash claude/scripts/discover.sh(single script, ~2s) → detects stack + plugins + FRESH/UPGRADE mode - Smart Merge (UPGRADE only) — Normalize directory structure, enhance CLAUDE.md, deep-merge settings.json, add missing commands/hooks/agents without touching existing ones
- Population Step 1 — Run
bash claude/scripts/populate-templates.sh(batch replacement, ~3s) → fills ~70 mechanical placeholders - Population Step 2 — YOU fill architecture.md, CLAUDE.md sections, domain docs (creative work)
- Plugins — Install claude-mem (skip if already installed), disable by default (quota protection), verify present
- Validate + Report — Run
bash claude/scripts/post-bootstrap-validate.sh(unified check, ~10s) → generate bootstrap-report.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 · 55 lines · 22 tokens per session scan C a9d0a865ea7f
bootstrap is a command published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 1,047 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
restart
Restart the claude-mnemonic worker process. Use this command when experiencing issues with the memory system.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.