cursorrules

A set of commit rules that requires using `git-ai-commit`, a command-line tool that creates commit messages from staged changes.

In plain words
What is it for?
Use it when committing changes to get suggested messages, conventional commit formatting, change summaries, or help with the commit tool.
Why use it?
It removes the need to write every commit message from scratch and encourages a consistent description of code changes.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/the-cafe/git-ai-commit/cursorrules
Clone the repo
git clone --depth 1 https://github.com/the-cafe/git-ai-commit

Made for: Cursor.

Per session 262 This file is loaded in full into every session.
When invoked 262 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00262 $0.00262
Opus 5 $0.00131 $0.00131
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured yesterday against content hash 36c98d2f50d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 23 lines

What it actually says

Git AI Commit Integration

Commit Workflow

When making commits, always use the git-ai-commit CLI tool instead of regular git commit. This tool automatically generates AI-powered commit messages based on your staged changes.

Recommended Commands:

  • Use git-ai-commit instead of git commit for AI-generated commit messages
  • Use git-ai-commit conventional for conventional commit format
  • Use git-ai-commit summarize to get a quick overview of changes before committing
  • Use git-ai-commit help-ai [question] if you need assistance with the tool

Setup Instructions:

  1. Ensure git-ai-commit is installed: pip install git-ai-commit
  2. Configure your API keys: git-ai-commit config --setup
  3. Set up git hooks: git-ai-commit hook --setup

Workflow Integration:

  • Before committing, stage your changes with git add
  • Instead of git commit -m "message", simply run git-ai-commit
  • The tool will analyze your changes and suggest an appropriate commit message
  • Review and accept the AI-generated message or customize as needed

This ensures consistent, descriptive commit messages that follow best practices and provide clear context about the changes made.

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. yesterday First seen · 23 lines · 262 tokens per session scan A 36c98d2f50d0

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository the-cafe/git-ai-commit (86 stars, last pushed 1y ago), licensed MIT. It adds 262 tokens to every session, about $0.0013 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 2026-08-30.