CodeGPT: Instructions file for Claude Code

CLAUDE.md

CodeGPT CLAUDE.md is an instructions file for Claude Code from appleboy/CodeGPT. It costs 1,261 tokens per session, scanned A, original, MIT.

Repository instructions for CodeGPT, a Go command-line tool that creates Git commit messages and code reviews with AI services.

In plain words
What is it for?
Use them when changing CodeGPT, running its tests or linters, building the binary, or installing it globally.
Why use it?
They document how to build, install, test, format, and lint the project, helping contributors follow its required development checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is appleboy/CodeGPT's own configuration. It tells Claude Code how to work on CodeGPT 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 CodeGPT configures →

About the project

CodeGPT is a Go command-line tool that uses AI services to generate Git commit messages and summarize code reviews, while also managing a Git commit-message hook. Developers use it with several supported AI backends to assist with routine Git workflows.

appleboy/CodeGPT · 1,504 stars · on GitHub

Reuse

Borrowing it

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

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 CodeGPT CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/appleboy/codegpt/claude-md"><img src="https://agentmods.dev/badge/instructions/appleboy/codegpt/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,261 This file is loaded in full into every session.
When invoked 1,261 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 $0.01261 $0.01261
Opus 5.5 $0.00504 $0.00504
Sonnet 5.5 $0.00252 $0.00252
Haiku 4.5 $0.00126 $0.00126

Measured 2mo ago against content hash fab53c4405b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

CodeGPT 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 2mo 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 · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

CodeGPT is a CLI tool written in Go that generates git commit messages and code reviews using AI. It supports multiple AI providers (OpenAI, Azure OpenAI, Gemini, Anthropic, Ollama, Groq, OpenRouter) and integrates with git prepare-commit-msg hooks.

Build and Development Commands

# Build the binary
make build              # outputs to bin/codegpt

# Install globally
make install

# Run all tests with coverage
make test               # or: go test -v -cover -coverprofile coverage.txt ./...

# Run a single test
go test -v -run TestName ./path/to/package

# Format go files (auto-installs golangci-lint if missing)
make fmt

# Lint (auto-installs golangci-lint v2 if missing)
make lint

Development Guidelines

IMPORTANT: When making changes to this codebase, you MUST:

  1. Write Tests - Always write corresponding tests for any new functionality or bug fixes
  2. Pass Linting - All code must pass make lint validation before submission
  3. Format Code - Always run make fmt to ensure consistent coding style

Architecture

Core Design Pattern

CodeGPT uses a provider pattern where all AI services implement the core.Generative interface:

type Generative interface {
    Completion(ctx context.Context, content string) (*Response, error)
    GetSummaryPrefix(ctx context.Context, content string) (*Response, error)
}

This allows adding new AI providers without changing core logic.

Package Structure

  • cmd/ - CLI commands using Cobra

    • cmd.go - Root command setup with Viper config initialization (supports env vars with CI platform prefixes like GITHUB_ and DRONE_)
    • commit.go - Generate commit messages (codegpt commit)
    • review.go - Generate code reviews (codegpt review)
    • hook.go - Git hook management (codegpt hook install/uninstall)
    • provider.go - Factory functions for instantiating AI providers (NewOpenAI, NewGemini, NewAnthropic)
    • config.go, config_set.go, config_list.go - Configuration management

Read the full file on GitHub · 130 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. 2mo ago First seen · 130 lines · 1,261 tokens per session scan A fab53c4405b9

Subscribe to this mod's changes

CodeGPT CLAUDE.md is an instructions file published in the GitHub repository appleboy/CodeGPT (1,504 stars, last pushed 1mo ago), licensed MIT. It adds 1,261 tokens to every session, about $0.0050 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.

Related

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).

microsoft/vscode · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

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).

microsoft/vscode · 2,731 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 · 4,261 tokens