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/agent-anatomy/claude/commitgit clone --depth 1 https://github.com/agent-anatomy/claudeWhat 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 | $0.00005 | $0.00258 |
| Opus 5 | $0.00003 | $0.00129 |
| Sonnet 5 | $0.00001 | $0.00052 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
commit 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 yesterday.
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
Stage and commit the current changes.
Steps
- Run
git status— understand what changed - Run
git diff— read the actual changes - Stage relevant files by name (never
git add -Ablindly) - Write the commit message following the rules below
- Commit
Commit message rules
- One sentence, imperative mood ("Add X", "Fix Y", "Remove Z")
- Focus on the why or what, not the mechanics
- No
Co-Authored-Bylines - No AI attribution ("Generated by", "Claude", etc.)
- No trailing blank lines or extra metadata
Format
Subject only when self-explanatory:
Add rate limiting to the auth endpoint
Subject + body when context is non-obvious:
Switch session store from memory to Redis
Memory store resets on every deploy, logging out all active users.
What NOT to do
- No "Updated files" or "Made changes"
- No listing every file touched
- No referencing the task/ticket in the subject (put it in body if needed)
- No co-author or AI attribution lines
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.
- yesterday First seen · 39 lines · 5 tokens per session scan A 13b414b5c1ce
commit is a command published in the GitHub repository agent-anatomy/claude (2 stars, last pushed 4mo ago), licensed MIT. It adds 5 tokens to every session and 258 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
create-pr
Create a pull request following the official template.
review-code
Read ALL memory bank code rules + best practices, check the files that changed, and APPLY fixes so they adhere. The active counterpart to /scan (which is read-only). Use after an AI session, before commit, to make changed files compliant.
generate-agents
Command "generate-agents" from chohra-med/expo_boilerplate, covering invocation, how it works, the concern each agent gets (one per agent), rules for the injected block (every agent) and idempotent + the loop.
learn
Command "learn" from chohra-med/expo_boilerplate, covering command: learn — the learning loop (feedback → rules), when to run it, invocation, the loop (6 steps) and 1 — capture.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.
audit
Command "audit" from chohra-med/expo_boilerplate, covering invocation, checks and output.