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.
git clone --depth 1 https://github.com/agent-anatomy/claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/agent-anatomy/claude/review)<a href="https://agentmods.dev/commands/agent-anatomy/claude/review"><img src="https://agentmods.dev/badge/commands/agent-anatomy/claude/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/agent-anatomy/claude/review"><img src="https://agentmods.dev/badge/commands/agent-anatomy/claude/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00005 | $0.00087 |
| Opus 5.5 | $0.00002 | $0.00035 |
| Sonnet 5.5 | $0.00001 | $0.00017 |
| Haiku 4.5 | $0.00001 | $0.00009 |
Grade A, and why
review 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 1mo 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
Review the staged changes before I commit.
Check for:
- Bugs or logic errors
- Security issues (injection, exposed secrets, unsafe input handling)
- Missing edge cases
- Code style inconsistencies with the rest of the project
- Anything that should be tested but isn't
Be specific. Point to line numbers. Don't summarize what the code does — I can read it.
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.
- 1mo ago First seen · 15 lines · 5 tokens per session scan A 9411a36d0e04
review is a command published in the GitHub repository agent-anatomy/claude (4 stars, last pushed 6mo ago), licensed MIT. It adds 5 tokens to every session and 87 once invoked, about $0.0000 per session on Opus 5.5. 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
align
Context-aware alignment. In plan mode it audits the active plan and folds the amendments in. Otherwise it reviews the branch, a named branch, or a pull request against Ion's principles, authors a fix plan, and after approval implements and commits the fixes.
review
Unified review orchestrator — detect changes, dispatch reviewers, validate findings, optionally post GitHub inline comments.
ship-csk
DoD gate + commit proposal (waits for approval).
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…
work-pr
Creates a complete and well-documented Pull Request.
pr-enhance
Write or improve a pull request description, checklist, and review aids.