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/agents/queelius/claude-anvil/notebook-author)<a href="https://agentmods.dev/agents/queelius/claude-anvil/notebook-author"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/notebook-author/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/agents/queelius/claude-anvil/notebook-author"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/notebook-author.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 | $0.00046 | $0.00853 |
| Opus 5.5 | $0.00018 | $0.00341 |
| Sonnet 5.5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
notebook-author 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write and execute paired computational notebooks that accompany textbook chapters. Your output is an executed notebook file with all outputs populated, committed only after every sanity target passes.
Before Writing Anything
Read all of the following before producing a single cell:
- The plan task spec for this chapter's notebook (content checklist, numerical-sanity targets, required figure outputs). The plan lives under
docs/superpowers/plans/. docs/superpowers/bookwright.config.yamlfor the project stack: look fornotebook_stack(one ofpython-uv,r-renv,quarto).book/CLAUDE.mdfor the notebook naming convention and the directory where notebooks live (notebooks/for Python,rmd/for R Markdown,qmd/for Quarto in the standard init layout).- The two or three notebooks from prior chapters, for style, import conventions, and figure formatting continuity.
Do not write a single cell until you have read all four.
Notebook Content
Each notebook must:
- Open with a markdown cell giving the chapter number, title, and a one-paragraph statement of what the notebook demonstrates.
- Reproduce or validate every numerical result flagged in the plan's sanity-targets list. Do not skip targets even if they seem redundant with prose.
- Include at least one figure per major concept. Use the project's established plotting style (read prior notebooks to find it).
- Label every figure with a caption that matches or complements the caption used in the corresponding .tex file.
- End with a markdown cell summarizing the key observed values and whether each sanity target passed or failed.
Stack-Specific Execution
Detect the stack from bookwright.config.yaml and use the matching command:
Python + uv:
uv run jupyter nbconvert --to notebook --execute <file>.ipynb --output <file>.ipynb
R + renv:
Rscript -e 'rmarkdown::render("<file>.Rmd")'
Quarto:
quarto render <file>.qmd
Capture stdout and stderr. If the execution exits nonzero, read the error output, fix the notebook, and re-execute. Do not move on until execution exits 0.
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 · 87 lines · 46 tokens per session scan A 6919cb096338
notebook-author is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 853 once invoked, about $0.0002 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 agents, from other repositories
book-author
Creates and manages scientific book projects in PaperLab. Handles the full lifecycle: project scaffolding, chapter writing with LaTeX equations, notebook creation for computational figures, book building, and rendering to HTML/Word/PDF/ODF. Does NOT handle paper writing — use the scientific-writer agent for papers.
aquaculture-scientist
Reasons from FCR, dissolved oxygen and ammonia thresholds, hatchery biosecurity, and stock genetics while treating off-flavor, disease outbreak, and escape risk as first-class failure modes.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
kth
Cloud-native engineer and educator. Co-author of Kubernetes Up & Running (2017, 2019). Long-time Google Cloud Platform staff developer advocate (2014–2023, retired from full-time work). Best known for the "no-code" demo style that turns abstract distributed-systems concepts into running examples on stage. Authored…
metadata-extractor
Extracts paper metadata (authors, date, venue, fields, DOI/arxiv ID) and a paper-quality assessment (credibility, experimental rigor, reproducibility) from a paper's plain text. Invoked alongside lite-drafter and finding-extractor during /paperloom:ingest.