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 skills/brain-bootstrap/claude-code-brain-bootstrap/cleanupnpx skills add brain-bootstrap/claude-code-brain-bootstrap --skill cleanupgit 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 | $0.00037 | $0.00518 |
| Opus 5 | $0.00018 | $0.00259 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade C, and why
cleanup 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.
- NEVER run `rm -rf /` What it actually says
Cleanup Skill
Clean up workspace artifacts based on the requested scope.
Usage
/cleanup # Default: show what can be cleaned
/cleanup build # Remove build artifacts
/cleanup deps # Remove dependency directories (node_modules, venv, etc.)
/cleanup all # Full clean: deps + build artifacts
/cleanup cache # Clear build tool caches
/cleanup docker # docker system prune -f (no named volumes removed)
/cleanup tasks # Remove obsolete task files (lessons.md is NEVER deleted)
/cleanup reinstall # Full reinstall: clean deps → install
Instructions
Determine action from $ARGUMENTS:
| Argument | Action |
|---|---|
build or dist |
Remove all build artifacts (dist/, build/, .next/, target/) |
deps |
Remove dependency directories (node_modules/, venv/, .venv/, target/) |
all |
Full clean: deps + build artifacts, then reinstall |
cache |
Clear build tool caches (.turbo/, .cache/, __pycache__/, .mypy_cache/) |
docker |
docker system prune -f (does NOT remove named volumes) |
tasks |
Clean obsolete task files (see rules below) |
reinstall |
Full reinstall: clean deps → install |
Tasks file cleanup rules:
- NEVER delete
claude/tasks/lessons.md(accumulated wisdom) - NEVER delete
claude/tasks/CLAUDE_ERRORS.md(bug history) claude/tasks/todo.mdcan be archived if no active taskclaude/tasks/mr-description-*.mdcan be deleted after MR is mergedclaude/tasks/ticket-*.mdcan be deleted after ticket is created
Safety rules:
- NEVER run
rm -rf / - NEVER delete
.envor.env.*files - For
all: confirm before deleting dependencies ifpackage.json/pyproject.tomlshows install script hooks - For
docker: confirm before running prune in production-adjacent environments
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 · 49 lines · 37 tokens per session scan C e9de30bf9fa6
cleanup is a skill published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 518 once invoked, about $0.0002 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 skills, from other repositories
implement
TRIGGER when: user asks to implement, fix, build, or work on something — whether from a docs/wip plan OR a standalone task (bug fix, GitHub issue, one-off change). Examples: "work on task 1", "fix this bug", "implement feature X from the issue". Provides structured execution with profile detection, dependency…
review-spec
Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync. Detects spec deviations, missing implementations, doc inconsistencies, and outdated docs in design and implementation documentation.
chain-of-verification
Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.
review-code
Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.
review-design
Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency, and technical soundness. Use after design completes and before starting implement.
design
Use in pre-implementation (idea-to-design) stages to understand spec/requirements and create a correct implementation plan before writing actual code. Turns ideas into a fully-formed PRD/design/specification and implementation-plan. Creates design docs and task lists in docs/wip/.