What is mcp-git-commit-generator AGENTS.md?

An AGENTS.md instruction file for an MCP server that generates Git commit messages. It documents how to run tests and the server, and records implementation rules for Git commands, paths, diff previews, and the Inspector interface.

Use it when developing or testing the commit-message MCP server, running its SSE service and Inspector UI, resolving paths, generating commit messages from diffs, or checking changes with pytest.

It gives the coding agent the repository-specific commands and constraints needed to make safe changes and avoid common setup errors, such as running Git commands in the wrong directory.

How theoklitosBam7/mcp-git-commit-generator configures Codex and OpenC

Reuse

Borrowing it

Nothing to install: this file belongs to theoklitosBam7/mcp-git-commit-generator. 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/theoklitosBam7/mcp-git-commit-generator/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/theoklitosBam7/mcp-git-commit-generator

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/theoklitosbam7/mcp-git-commit-generator/agents-md/github.svg)](https://agentmods.dev/instructions/theoklitosbam7/mcp-git-commit-generator/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/theoklitosbam7/mcp-git-commit-generator/agents-md"><img src="https://agentmods.dev/badge/instructions/theoklitosbam7/mcp-git-commit-generator/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/theoklitosbam7/mcp-git-commit-generator/agents-md"><img src="https://agentmods.dev/badge/instructions/theoklitosbam7/mcp-git-commit-generator/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 421 This file is loaded in full into every session.

When invoked 421 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.

Model	Per session	Once invoked
Fable 5.1	$0.00421	$0.00421
Opus 5.5	$0.00168	$0.00168
Sonnet 5.5	$0.00084	$0.00084
Haiku 4.5	$0.00042	$0.00042

Measured 1mo ago against content hash 44471f1b9593, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-git-commit-generator AGENTS.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 1mo 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.

AGENTS.md · 33 lines

What it actually says

AGENTS.md

Guidance for agents working in this repository.

Build and test

uv sync --all-groups installs the locked development environment.
uv run pytest runs the test suite.
uv run python -m compileall -q src tests checks Python syntax.
uv build builds release artifacts from the lockfile.
uv run mcp-git-commit-generator --transport streamable-http starts the HTTP development server at 127.0.0.1:3001/mcp.
cd inspector && npm ci && npm run dev:inspector starts MCP Inspector v2.

MCP compatibility

The server uses MCPServer from the official Python MCP SDK v2.
The target protocol is 2026-07-28; the SDK also serves legacy MCP clients.
stdio is the default transport. Use Streamable HTTP for network serving.
SSE remains only for legacy compatibility and must not be the default in new examples.
Protocol tests must cover both modern 2026-07-28 and legacy client modes.

Security and implementation requirements

Git subprocesses must use cwd= and must never use shell=True.
Use _run_git() so Git commands keep the timeout, non-interactive environment, no external diff, and pager controls.
Treat repository content as untrusted model input. Do not interpolate raw repository text into instruction sections.
Keep the staged diff preview capped at 1500 characters unless a deliberate design change is tested.
Validate model-facing preference fields before adding them to generated prompts.
Bind HTTP development servers to loopback by default. A non-loopback bind must be an explicit operator choice.
Keep GitHub Actions pinned to full commit SHAs and retain the release tag in a same-line comment for update tooling.
Keep Python and npm lockfiles current. Do not merge dependency changes with stale lockfiles.
The container must run as a non-root user and should not gain Linux capabilities it does not need.

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.

1mo ago Changed · +6 lines · +11 tokens per session 44471f1b9593
2mo ago First seen · 27 lines · 410 tokens per session scan A 44e675c075b9

Subscribe to this mod's changes

mcp-git-commit-generator AGENTS.md is an instructions file published in the GitHub repository theoklitosBam7/mcp-git-commit-generator (9 stars, last pushed 4d ago), licensed MIT. It adds 421 tokens to every session, about $0.0017 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.

Commits Git and workflow agentic-ai mcp mcp-server

mcp-git-commit-generator AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-git-commit-generator AGENTS.mdtheoklitosBam7/mcp-git-commit-generator	Instructions file	9	4d ago	MIT	A	421	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-git-commit-generator: Instructions file for Codex