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.
git 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/commands/anthropics/claude-cookbooks/review-pr)<a href="https://agentmods.dev/commands/anthropics/claude-cookbooks/review-pr"><img src="https://agentmods.dev/badge/commands/anthropics/claude-cookbooks/review-pr/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/anthropics/claude-cookbooks/review-pr"><img src="https://agentmods.dev/badge/commands/anthropics/claude-cookbooks/review-pr.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 | $0.00013 | $0.00715 |
| Opus 5 | $0.00006 | $0.00358 |
| Sonnet 5 | $0.00003 | $0.00143 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
review-pr 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 13d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
$ARGUMENTS: The PR number or URL to review
Your task
Review the specified pull request and provide feedback.
Step 1: Checkout the PR
First, checkout the PR using:
gh pr checkout $ARGUMENTS
Step 2: Gather PR context
Get the PR details:
gh pr view $ARGUMENTS
gh pr diff $ARGUMENTS
Step 3: Review the code changes
Use the Task tool with subagent_type: "code-reviewer" to perform a thorough code review of the changes. Pass the diff and changed files to the agent for analysis.
The code-reviewer agent will analyze:
- Code quality and best practices
- Potential bugs or issues
- Security concerns
- Performance considerations
- Documentation and comments
Step 4: Present the review
After the code review is complete, present the review to the user using this format:
## PR Review
**Recommendation**: APPROVE | REQUEST_CHANGES | COMMENT
### Summary
[1-2 sentence overview of what this PR does]
### Actionable Feedback (N items)
- [ ] `file.py:42` - Description of issue or required change
- [ ] `notebook.ipynb` (in cell with `some_code = ...`) - Description
### Detailed Review
#### Code Quality
[Analysis of code patterns, readability, maintainability]
#### Security
[Any security considerations]
#### Suggestions
[Optional improvements]
#### Positive Notes
[What was done well]
Guidelines:
- Use checkboxes for actionable items so authors can track progress
- For Jupyter notebooks, reference code snippets instead of cell numbers
- Be specific with file:line references where possible
Step 5: Ask about posting the review
Use the AskUserQuestion tool to ask the user:
- Whether they want to post this review to GitHub
- What review action to take: APPROVE, REQUEST_CHANGES, or COMMENT
Step 6: Post the review (if approved)
If the user confirms, post the review using:
gh pr review $ARGUMENTS --body "YOUR_REVIEW_BODY" --approve|--request-changes|--comment
When posting to GitHub, wrap the Detailed Review section in a collapsible <details> tag to reduce noise:
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.
- 13d ago First seen · 120 lines · 13 tokens per session scan A 2e6578f10177
review-pr is a command published in the GitHub repository anthropics/claude-cookbooks (52,628 stars, last pushed 8d ago), licensed MIT. It adds 13 tokens to every session and 715 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.