check

An automated checking command for a book section, chapter, part, or complete project.

In plain words
What is it for?
Use it to build the book, audit chapter page counts, check cross-references, verify recurring themes, and detect leaked LaTeX commands or banned writing patterns.
Why use it?
It catches mechanical problems such as failed builds, unresolved references, incorrect page lengths, missing topic threads, and formatting-rule violations.

Command

Part of the bookwright plugin — 3 skills, 11 commands, 11 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add commands/queelius/claude-anvil/check
Clone the repo
git clone --depth 1 https://github.com/queelius/claude-anvil

Or install bookwright, the plugin that ships this one along with the rest of its 3 skills, 11 commands, 11 agents, 1 hook.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00407
Opus 5 $0.00007 $0.00204
Sonnet 5 $0.00003 $0.00081
Haiku 4.5 $0.00001 $0.00041

Measured 2d ago against content hash ccb6f1279b24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check 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.

bookwright/commands/check.md · 30 lines

What it actually says

/bookwright:check

Run mechanical diagnostics. No editorial judgment; checks that can be automated.

What it runs

  1. Build the book: cd book && make cleanall && make. Expects exit 0.
  2. Cross-reference resolution: grep "undefined" book/book.log | grep -iE "reference|citation" (LaTeX writes "LaTeX Warning: Reference `x' on page N undefined", so the literal string "Reference undefined" never appears). Expects only the documented baseline.
  3. Per-chapter page-count audit: read book.toc, compute per-chapter page spans, compare to the per-chapter targets in the plan files. Expects each chapter within plus-or-minus 30 percent of its target.
  4. Running-thread inventory: for each thread named in the master spec, grep chapter files for thread keywords; verify the thread carries across the chapters the spec assigned it to.
  5. Soul-voice audit: re-run the soul-voice hook's pattern checks across all chapter .tex files (the hook runs at edit time, but /check re-runs as a defense-in-depth audit).
  6. LaTeX-macro-leak audit: re-run the macro-leak hook's pattern checks.

Scope

  • section <path>: only the named section file.
  • chapter <name>: all section files in book/chapters/<chapter>/.
  • part <name>: all chapters in the named Part.
  • book: everything (default if no scope given).

Output

A short bullet report: each check's PASS/FAIL/NOTE. On FAIL, surface the specific lines or refs. No fix attempted; this is read-only diagnostics.

Changes

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.

  1. 2d ago First seen · 30 lines · 14 tokens per session scan A ccb6f1279b24

Subscribe to this mod's changes

check is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 407 once invoked, about $0.0001 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.