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/init)<a href="https://agentmods.dev/commands/queelius/claude-anvil/init"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/init/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/init"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/init.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 | $0.00023 | $0.00596 |
| Opus 5.5 | $0.00009 | $0.00238 |
| Sonnet 5.5 | $0.00005 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
init 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.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bookwright:init
Scaffold a fresh book project at the current working directory (or a named subdirectory). Asks the user for a notebook stack choice and persists the choice to docs/superpowers/bookwright.config.yaml.
What it creates
book/withchapters/,frontmatter/,appendices/,parts/,alex.sty(or empty placeholder for project's own notation),preamble.tex,references.bib,book.tex,Makefile.notebooks/(Jupyter) ORrmd/(R Markdown) ORqmd/(Quarto) per user choice.papers/(empty; user can git-subtree-add source papers later).docs/superpowers/specs/anddocs/superpowers/plans/.docs/superpowers/bookwright.config.yamlrecording the notebook stack choice and other project settings (key:notebook_stack: python-uv | r-renv | quarto | none;nonemeans prose-only and notebook-author is never dispatched).book/CLAUDE.mdrecording the build command (matching the Makefile), the banned-phrase list, label-naming conventions, and the notebook directory. Five agents read this file; a project without it breaks the drafting chain.
Steps
- Ask the user (via AskUserQuestion) which notebook stack: Python+uv+Jupyter / R+renv+RMarkdown / Quarto / none.
- Create the directory tree.
- Write a minimal
book.texthat includes emptyparts/part1.texand references it. - Write a minimal
Makefilewith the standard cleanall + biber + pdflatex pipeline. - Write the
bookwright.config.yamlrecording user choices. - Write
book/CLAUDE.mdwith: the build command from the Makefile, the banned-phrase list (seed from the soul conventions or leave a TODO section), label-naming conventions, and the notebook directory chosen in step 1. - Write a README in the new project root summarizing the layout.
- Initialize git if not already initialized; commit the scaffold.
- Report success and suggest next steps:
/bookwright:design master(or/bookwright:design part1).
Dependencies
- The
soulplugin should be installed in the user's Claude environment for the soul-voice hook to fire on .tex writes in the new project.initshould remind the user of this if not already done.
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 · 35 lines · 23 tokens per session scan A a573a0d124df
init is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 596 once invoked, about $0.0001 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
ia-verify
Run pre-PR verification chain: build, types, lint, tests, security scan, diff review.
ia-test-browser
Run browser tests on pages affected by current PR or branch.
announce
Draft X/Twitter announcement post (or thread) for the latest plugin release.
ia-agent-native-audit
Score each of the 5 agent-native principles (parity, granularity, composability, emergent capability, improvement-over-time) against a codebase and report gaps.
release
Generate changelog, bump version, and create git tag.
sm-swab
Run slop-mop's iterative development loop for this repository.