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.
npx agentmods add instructions/unilorn/generative-commit-message-for-ai-tool/claude-mdgit clone --depth 1 https://github.com/UNILORN/generative-commit-message-for-ai-toolWrote 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/unilorn/generative-commit-message-for-ai-tool/claude-md)<a href="https://agentmods.dev/instructions/unilorn/generative-commit-message-for-ai-tool/claude-md"><img src="https://agentmods.dev/badge/instructions/unilorn/generative-commit-message-for-ai-tool/claude-md.svg" alt="Measured on agentmods" 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 | $0.00607 | $0.00607 |
| Opus 5 | $0.00303 | $0.00303 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
generative-commit-message-for-ai-tool 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 5d 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 — 63 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
This is a Go CLI tool that generates commit messages using AI providers. The tool analyzes Git staged changes and generates appropriate commit messages through AWS Bedrock, Claude API directly, or local Gemini CLI.
Build and Development Commands
Use the Makefile for all build operations:
make build- Build the binarymake test- Run all tests with verbose outputmake install- Build and install to $GOPATH/binmake clean- Remove build artifactsmake release- Cross-compile for multiple platforms (Linux, macOS, Windows)make help- Show all available targets
For development, use standard Go commands:
go run .- Run the application directlygo test ./...- Run tests for all packages
Architecture
The codebase follows a clean modular architecture with three main packages:
Core Packages
client/- Abstract interface for AI providersbedrock/- AWS Bedrock client implementationclaude/- Claude API direct client implementationgeminicli/- Local Gemini CLI client implementation (executesgeminicommand)git/- Git operations (staged diffs, branch detection, file status)message/- Commit message generation logic that orchestrates AI clients and git packagesmain.go- CLI entry point with flag parsing and orchestration
Data Flow
- CLI parses flags (provider, model ID, region, verbose mode)
- Auto-detects provider based on environment variables and available tools if not specified
gitpackage extracts staged changes and current branch- Appropriate AI client (
bedrock,claude, orgeminicli) is initialized messagepackage combines git context and calls AI client through interface- Generated message is printed to stdout
Usage Requirements
For Gemini CLI (Simplest)
- Requires
geminicommand available in PATH - Default model:
gemini-2.5-pro
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.
- 5d ago First seen · 63 lines · 607 tokens per session scan A 0e81086d1b1e
generative-commit-message-for-ai-tool CLAUDE.md is an instructions file published in the GitHub repository UNILORN/generative-commit-message-for-ai-tool (2 stars, last pushed 5mo ago), licensed MIT. It adds 607 tokens to every session, about $0.0030 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 2026-08-31.
Other instructions, from other repositories
Project-AMBER AGENTS.md
AGENTS.md instructions for JJHbrams/Project-AMBER, covering agent orchestration, roles and non-negotiable rules.
omni-cli AGENTS.md
Instructions for mabelisle/omni-cli, covering agents.md - omni-cli repository guidelines, 📦 project structure, core files, configuration directories (mounted volumes) and installed cli tools (in container).
Project-AMBER project-guides.instructions.md
Project coding guidelines, todo monitoring rules, and context for AI agents working on Project Engram.
omni-cli GEMINI.md
Instructions for mabelisle/omni-cli, covering omni-cli context, project overview, architecture & core components, docker structure and key scripts.
all-agents-mcp CLAUDE.md
Instructions for Dokkabei97/all-agents-mcp, covering claude.md, project overview, build & development commands, architecture and entry flow.
all-agents-mcp AGENTS.md
Instructions for Dokkabei97/all-agents-mcp, a project described as: MCP server that orchestrates Claude Code, Codex, Gemini CLI, and Copilot CLI through a unified stdio interface — ask, compare, verify, and collaborate across multiple AI agents.