pr-genius: Instructions file for Claude Code

CLAUDE.md

pr-genius CLAUDE.md is an instructions file for Claude Code from zsxh1990/pr-genius. It costs 669 tokens per session, scanned A, original, MIT.

Repository-specific instructions for PR Genius, a Python command-line tool and GitHub Action that reviews commits and pull requests.

In plain words
What is it for?
It helps handle feature changes, bug reports, pull-request reviews, and TDD, which means writing tests before the code they check.
Why use it?
It tells coding agents which project skills and coding rules to apply for implementation, bug diagnosis, reviews, and test-first work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is zsxh1990/pr-genius's own configuration. It tells Claude Code how to work on pr-genius 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 pr-genius configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zsxh1990/pr-genius. 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/zsxh1990/pr-genius/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zsxh1990/pr-genius

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 pr-genius CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zsxh1990/pr-genius/claude-md/github.svg)](https://agentmods.dev/instructions/zsxh1990/pr-genius/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zsxh1990/pr-genius/claude-md"><img src="https://agentmods.dev/badge/instructions/zsxh1990/pr-genius/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 pr-genius CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zsxh1990/pr-genius/claude-md"><img src="https://agentmods.dev/badge/instructions/zsxh1990/pr-genius/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 669 This file is loaded in full into every session.
When invoked 669 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 $0.00669 $0.00669
Opus 5 $0.00334 $0.00334
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured 4d ago against content hash e38747437a10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pr-genius 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 4d 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Genius — Agent Guidelines

Project Overview

PR Genius is a Python CLI + GitHub Action that provides commit-level improvement coaching and cross-repo PR pattern intelligence. Published as prgenius-core on PyPI and ghcr.io/zsxh1990/pr-genius on GHCR.

Engineering Skills (auto-invoke)

When the user's task matches one of these patterns, invoke the corresponding skill before writing code. Do not wait for the user to ask.

Task pattern Skill to invoke
User asks to implement a feature, fix a bug, or describes a change /implement
User reports something broken, failing, slow, or says "diagnose" /diagnosing-bugs
User asks to review changes, a branch, or a PR /review
User wants to build test-first or mentions "red-green-refactor" /tdd
User wants to clarify requirements before coding /grill-with-docs

Code Standards

  • Python 3.9+; no type hints required but recommended for public APIs
  • All YAML parsing must strip inline comments before yaml.safe_load (lesson: yaml_inline_comment_coercion.md)
  • Anti-pattern / success-pattern YAML: use block scalar | for multiline content
  • anti_patterns_hit must return object arrays ({key, description, severity, fix_action}), never string arrays
  • Shell scripts: set -euo pipefail; escape user input via temp files, never inline interpolation
  • Docker: no shell redirection syntax in COPY/RUN (2>/dev/null doesn't work in Dockerfile)

Testing

# Quick validation
python3 validate.py

# Full test suite
python3 -m pytest tests/ -v

Release Process

  1. Bump version in pyproject.toml and prgenius/__init__.py
  2. Update CHANGELOG.md
  3. git tag v1.x.x && git push origin v1.x.x
  4. PyPI publish workflow triggers automatically
  5. GHCR publish workflow triggers automatically
  6. Major tag v1 is auto-updated to point to latest release

Key Files

  • prgenius/src/prgenius/evaluator.py — core analysis engine
  • prgenius/src/prgenius/cli.py — CLI entry point
  • github_action/entrypoint.sh — GitHub Action entry point
  • anti-patterns/ — anti-pattern YAML definitions
  • success-patterns/ — success-pattern YAML definitions
  • docs/ — knowledge bundle shipped with Docker image

Read the full file on GitHub · 70 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. 4d ago First seen · 70 lines · 669 tokens per session scan A e38747437a10

Subscribe to this mod's changes

pr-genius CLAUDE.md is an instructions file published in the GitHub repository zsxh1990/pr-genius (3 stars, last pushed 2d ago), licensed MIT. It adds 669 tokens to every session, about $0.0033 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 2026-09-05.

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens