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/plugins/queelius/claude-anvil/bookwright)<a href="https://agentmods.dev/plugins/queelius/claude-anvil/bookwright"><img src="https://agentmods.dev/badge/plugins/queelius/claude-anvil/bookwright/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/plugins/queelius/claude-anvil/bookwright"><img src="https://agentmods.dev/badge/plugins/queelius/claude-anvil/bookwright.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bookwright 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
{
"name": "bookwright",
"version": "0.2.3",
"description": "Documentation-first methodology and multi-agent toolchain for technical non-fiction long-form manuscripts. The Bernoulli-textbook approach: design spec and chapter plans drive the manuscript.",
"author": {
"name": "Alexander Towell",
"email": "[email protected]",
"url": "https://metafunctor.com"
},
"repository": "https://github.com/queelius/claude-anvil",
"license": "MIT",
"keywords": [
"non-fiction",
"textbook",
"monograph",
"writing",
"editorial",
"multi-agent",
"latex",
"jupyter"
]
}
What it installs
The manifest is a name and a version. 3 skills, 11 commands, 11 agents, 1 hook travel with it, and installing the plugin installs all of them — 1,999 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cross-reference-discipline A 49 tokens
- Skill textbook-methodology A 57 tokens
- Skill notebook-paired-with-prose A 58 tokens
- Command init A 23 tokens
- Command help A 11 tokens
- Command check A 14 tokens
- Command design A 17 tokens
- Command draft A 15 tokens
- Command integrate A 13 tokens
- Command iterate A 16 tokens
- Command plan A 12 tokens
- Command review A 12 tokens
- Command notebook A 16 tokens
- Command revise A 19 tokens
- Agent reviewer A 325 tokens
- Agent rewriter A 345 tokens
- Agent writer A 368 tokens
- Agent cross-ref-auditor A 48 tokens
- Agent math-auditor A 39 tokens
- Agent notebook-author A 46 tokens
- Agent quality-auditor A 44 tokens
- Agent section-writer A 45 tokens
- Agent spec-auditor A 44 tokens
- Agent iterator A 322 tokens
- Agent source-reformulator A 41 tokens
- Hook PostToolUse A not measured
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 · 23 lines scan A dfb57a593950
bookwright is a plugin published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
kindle-dedrm
Manage the Kindle for PC 2.8.0 + Calibre DeDRM workflow for personal-use ebook DRM removal on books the user owns (Windows only). Action router with setup, sync, update, cleanup, and status, each state mutation paired with a documented compensating reversal.
brand-docs
AI on-brand document generator for Claude Code & Codex: turn a company's Word, PowerPoint or Excel template into unlimited on-brand .docx/.pptx/.xlsx. Extracts a reusable Brand Profile once - off-brand output impossible by construction. Skills: brand-docx, brand-pptx, brand-xlsx.
researcher
Create distinctive HTML one-pagers with curated aesthetics, converts to PDF.
kolmopdf
High-fidelity PDF to Markdown parsing, layout-preserving PDF translation, and Markdown→DOCX/HTML/PDF/LaTeX conversion. Handles formulas, tables, and multi-column layouts that the built-in Read tool struggles with.
pdf-text-router
A Claude Code hook that routes each Read on a PDF to the path that actually works.
canvas-design
Create beautiful visual art in PNG and PDF documents using design philosophy. Use for posters, art pieces, designs, or other static visual works with museum-quality craftsmanship.