Claude Cookbooks is a collection of code examples and guides that show developers how to build applications with the Claude API. Users consult its notebooks and recipes to learn techniques such as classification and retrieval-augmented generation. The catalogue add-ons provide commands, skills, agents, hooks, settings, and instructions related to using these examples.
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.
npx skills add anthropics/claude-cookbooks --skill cookbook-auditgit clone --depth 1 https://github.com/anthropics/claude-cookbooksWrote 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/skills/anthropics/claude-cookbooks/cookbook-audit)<a href="https://agentmods.dev/skills/anthropics/claude-cookbooks/cookbook-audit"><img src="https://agentmods.dev/badge/skills/anthropics/claude-cookbooks/cookbook-audit/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/skills/anthropics/claude-cookbooks/cookbook-audit"><img src="https://agentmods.dev/badge/skills/anthropics/claude-cookbooks/cookbook-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 27 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00026 | $0.02724 |
| Opus 5.5 | $0.00010 | $0.01090 |
| Sonnet 5.5 | $0.00005 | $0.00545 |
| Haiku 4.5 | $0.00003 | $0.00272 |
Grade A, and why
cookbook-audit 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 3d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- cookbook-audit — 100% identical, 4 lines differ
- cookbook-audit — 100% identical, 4 lines differ
- cookbook-audit — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cookbook Audit
Instructions
Review the requested Cookbook notebook using the guidelines and rubrics in style_guide.md. Provide a score based on scoring guidelines and recommendations on improving the cookbook.
The style guide provides detailed templates and examples for:
- Problem-focused introductions with Terminal Learning Objectives (TLOs) and Enabling Learning Objectives (ELOs)
- Prerequisites and setup patterns
- Core content structure
- Conclusions that map back to learning objectives
IMPORTANT: Always read style_guide.md first before conducting an audit. The style guide contains the canonical templates and good/bad examples to reference.
Workflow
Follow these steps for a comprehensive audit:
- Read the style guide: First review
style_guide.mdto understand current best practices - Identify the notebook: Ask user for path if not provided
- Run automated checks: Use
python3 validate_notebook.py <path>to catch technical issues and generate markdown- The script automatically runs detect-secrets to scan for hardcoded API keys and credentials
- Uses custom patterns defined in
scripts/detect-secrets/plugins.py - Checks against baseline at
scripts/detect-secrets/.secrets.baseline
- Review markdown output: The script generates a markdown file in the
tmp/folder for easier review (saves context vs raw .ipynb)- The tmp/ folder is gitignored to avoid committing review artifacts
- Markdown includes code cells but excludes outputs for cleaner review
- Manual review: Read through the markdown version evaluating against style guide and rubric
- Score each dimension: Apply scoring guidelines objectively
- Generate report: Follow the audit report format below
- Provide specific examples: Show concrete improvements with line references using the style guide templates
Audit Report Format
Present your audit using this structure:
Executive Summary
- Overall Score: X/20
- Key Strengths (2-3 bullet points)
- Critical Issues (2-3 bullet points)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed aba609bd9deb
- 1mo ago First seen · 273 lines · 26 tokens per session scan A 63b4c68ffe7e
cookbook-audit is a skill published in the GitHub repository anthropics/claude-cookbooks (53,844 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 2,724 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…