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/queelius/claude-anvilWrote 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/queelius/claude-anvil/review)<a href="https://agentmods.dev/commands/queelius/claude-anvil/review"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/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/queelius/claude-anvil/review"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/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 | $0.00012 | $0.00488 |
| Opus 5.5 | $0.00005 | $0.00195 |
| Sonnet 5.5 | $0.00002 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
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 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.
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
/bookwright:review
Launch the reviewer orchestrator. Dispatches all four review specialists in parallel: spec-auditor, quality-auditor, math-auditor, cross-ref-auditor. Synthesizes the findings into a unified report.
Scope
section <path>: one section. Single-pass review by all four auditors.chapter <name>: all sections of the named chapter.part <name>: all chapters of the named Part.book: everything (heavy; do not use casually).
If the reviewer returns a decisions-needed YAML block instead of a report (it stops when the scope is ambiguous, since subagents cannot ask questions), ask the author with AskUserQuestion: one question per item, using its question, its options (label as the option, consequence as the description), and the recommended option listed first with "(Recommended)". Batch at most 4 questions per call and group items that touch the same section. Then relaunch the reviewer with the chosen scope.
Output
A unified review report saved to docs/superpowers/reviews/YYYY-MM-DD-<scope>.md, with sections from each auditor: spec compliance, quality (cold-read), math correctness, cross-references. To apply fixes, run /bookwright:revise (the rewriter orchestrator: fix-then-verify per finding, paired revision report); /bookwright:iterate loops review and revise to convergence. /bookwright:integrate is read-only verification, not a fix path.
Distinction from /bookwright:check and /bookwright:integrate
/bookwright:checkis fast, mechanical, no judgment./bookwright:reviewis heavy, editorial, full multi-agent dispatch./bookwright:reviseapplies a review report's findings (fix-then-verify)./bookwright:iterateloops review and revise until convergence./bookwright:integrateis per-Part or full-book verification with a written integration-pass record.
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 Changed · +2 lines 58cce4ddbc12
- 1mo ago First seen · 29 lines · 12 tokens per session scan A 08807ddf258f
review is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 488 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
audit-plugin
Deep quality audit of all skills, agents, and commands for inconsistencies, gaps, duplication, and token waste.
ia-document-release
Post-ship documentation sync. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, and optionally bumps the version.
ia-review
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees.
ia-verify
Run pre-PR verification chain: build, types, lint, tests, security scan, diff review.
announce
Draft X/Twitter announcement post (or thread) for the latest plugin release.
write-skill
Author a new skill from scratch with paired trigger fixtures and full validation. Use when adding a skill that has no upstream skills.sh source (discipline, meta, or internal-pattern skills).