Borrowing it
Nothing to install: this file belongs to GabsFranke/claude-code-github-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GabsFranke/claude-code-github-agent/main/CLAUDE.mdgit clone --depth 1 https://github.com/GabsFranke/claude-code-github-agentWrote 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/instructions/gabsfranke/claude-code-github-agent/claude-md)<a href="https://agentmods.dev/instructions/gabsfranke/claude-code-github-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/gabsfranke/claude-code-github-agent/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.
<a href="https://agentmods.dev/instructions/gabsfranke/claude-code-github-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/gabsfranke/claude-code-github-agent/claude-md.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 | $0.01278 | $0.01278 |
| Opus 5.5 | $0.00511 | $0.00511 |
| Sonnet 5.5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
claude-code-github-agent 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 26d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for Claude Code GitHub Agent
Where You Are
You are working in a git worktree - an isolated workspace created from a cached bare repository. This is NOT the main repository clone.
Important Context:
- Your working directory is a temporary worktree (e.g.,
/tmp/job_abc12345_123456/) - The worktree is created from a cached bare repository at
/var/cache/repos/{owner}/{repo}.git - You have a unique branch name like
job-abc12345-123456 - Git credentials are pre-configured for pushing changes
- The worktree will be automatically cleaned up after job completion
- All your file operations (Read, Write, Edit, List, Search, Bash) work on local files in this worktree
- GitHub API operations (creating PRs, posting comments, reading PR metadata) use GitHub MCP tools
Architecture Overview
This is a self-hosted GitHub bot that uses Claude Agent SDK to autonomously review PRs and respond to commands. The system has several key components.
Technology Stack
- Python 3.11+ with async/await patterns
- FastAPI for webhook service
- Redis for message queues and job coordination
- CodeGraph for code intelligence (local SQLite code graph via tree-sitter)
- Claude Agent SDK for autonomous operations
- GitHub MCP for GitHub API interactions
- Git worktrees for isolated workspaces
Code Quality Standards
When making changes to this codebase:
Formatting & Style
- Use black for code formatting (line length: 88)
- Use isort for import organization (black profile)
- Follow PEP 8 conventions
- Use type hints throughout (Python 3.11+ syntax)
- Use Pydantic for configuration and validation
Code Quality
- Write async functions for all I/O operations
- Use proper error handling with custom exceptions from
shared/exceptions.py - Add logging at appropriate levels (DEBUG, INFO, WARNING, ERROR)
- Use context managers for resource cleanup
- Implement graceful shutdown handlers for services
Testing
- Write tests using pytest
- Use markers:
@pytest.mark.unit,@pytest.mark.integration - Aim for high coverage on critical paths
- Mock external dependencies (GitHub API, Redis, etc.)
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.
- 26d ago Changed · -1 tokens per session dcdd58cf7720
- 1mo ago First seen · 152 lines · 1,279 tokens per session scan A 93f7b1c524d7
claude-code-github-agent CLAUDE.md is an instructions file published in the GitHub repository GabsFranke/claude-code-github-agent (5 stars, last pushed 26d ago), licensed MIT. It adds 1,278 tokens to every session, about $0.0051 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 instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.