cext-review-toolkit: Instructions file for Claude Code

CLAUDE.md

cext-review-toolkit CLAUDE.md is an instructions file for Claude Code from ReviewToolkits/cext-review-toolkit. It costs 2,660 tokens per session, scanned A, original, MIT.

Development instructions for a Claude Code plug-in that reviews C and C++ extensions written for Python. It explains the project, required tools, commands, and tests.

In plain words
What is it for?
Use it when developing or testing this extension-review plug-in, or when checking code that connects native C or C++ modules to Python.
Why use it?
It gives contributors the context and commands needed to work on the project correctly. The review tool helps identify unsafe Python/C API use, memory bugs, compatibility problems, and correctness issues.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is ReviewToolkits/cext-review-toolkit's own configuration. It tells Claude Code how to work on cext-review-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cext-review-toolkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ReviewToolkits/cext-review-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ReviewToolkits/cext-review-toolkit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ReviewToolkits/cext-review-toolkit

Made for: Claude Code.

Wrote 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.

agentmods badge for cext-review-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/reviewtoolkits/cext-review-toolkit/claude-md/github.svg)](https://agentmods.dev/instructions/reviewtoolkits/cext-review-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/reviewtoolkits/cext-review-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/reviewtoolkits/cext-review-toolkit/claude-md/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.

agentmods 80×15 button for cext-review-toolkit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/reviewtoolkits/cext-review-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/reviewtoolkits/cext-review-toolkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,660 This file is loaded in full into every session.
When invoked 2,660 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02660 $0.02660
Opus 5 $0.01330 $0.01330
Sonnet 5 $0.00532 $0.00532
Haiku 4.5 $0.00266 $0.00266

Measured 8d ago against content hash a2b6fcce00f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cext-review-toolkit CLAUDE.md 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 8d 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.

CLAUDE.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — cext-review-toolkit development guide

Project overview

cext-review-toolkit is a Claude Code plugin for reviewing CPython C extensions. It finds API misuse, memory safety bugs, compatibility issues, and correctness problems in code that consumes the Python/C API.

Part of a family of review toolkits:

Key architectural difference: uses Tree-sitter for C parsing (not regex), enabling analysis that regex cannot do (borrowed-ref lifetime tracking, type slot cross-referencing, accurate scope analysis).

Prerequisites

  • Python 3.10+
  • tree-sitter and tree-sitter-c: pip install tree-sitter tree-sitter-c
  • tree-sitter-cpp (optional): pip install tree-sitter-cpp — enables C++ file parsing
  • clang-tidy and cppcheck (optional): system packages — enables external tool cross-referencing
  • No other dependencies — all scripts use only the standard library plus tree-sitter

Dev commands

# Activate the project venv (Python 3.14 from ~/projects/3.14/python)
source ~/venvs/cext-review-toolkit/bin/activate

# Run all tests
python -m unittest discover tests -v

# Run a specific test file
python -m unittest tests.test_scan_refcounts -v

# Run a single script standalone (all output JSON to stdout)
python plugins/cext-review-toolkit/scripts/scan_refcounts.py /path/to/extension.c
python plugins/cext-review-toolkit/scripts/discover_extension.py /path/to/project

# Lint and format (install ruff/mypy into venv if not present)
ruff format <changed-files>
ruff check <changed-files>
mypy

Code style

  • Python 3.10+ (uses X | Y union syntax)
  • Double quotes for strings
  • Type hints on all function signatures
  • Docstrings on classes and public functions
  • Tests use unittest — never pytest
  • Linted and formatted with ruff, type checked with mypy

Read the full file on GitHub · 180 lines

Changes

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.

  1. 8d ago First seen · 180 lines · 2,660 tokens per session scan A a2b6fcce00f1

Subscribe to this mod's changes

cext-review-toolkit CLAUDE.md is an instructions file published in the GitHub repository ReviewToolkits/cext-review-toolkit (28 stars, last pushed 1mo ago), licensed MIT. It adds 2,660 tokens to every session, about $0.0133 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens