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 rules/lukaszzychal/mcp-doc-generator/commit-messagesgit clone --depth 1 https://github.com/lukaszzychal/mcp-doc-generatorWhat 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 | $0.00521 | $0.00521 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
commit-messages 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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Message Rules
Format: Conventional Commits
ALWAYS use this format for commit messages:
<type>(<scope>): <subject>
<body>
<footer>
Types
feat: A new featurefix: A bug fixdocs: Documentation only changesstyle: Code style changes (formatting, etc.)refactor: Code refactoringperf: Performance improvementstest: Adding or updating testschore: Build process or auxiliary toolsci: CI configuration changes
Scope (optional)
server: MCP server codeclient: MCP client codetools: Diagram generation toolsdocs: Documentationexamples: Example filesscripts: Utility scripts
Subject Rules
- Language: English only - No Polish characters allowed
- Imperative present tense: "change" not "changed" nor "changes"
- Lowercase first letter: "add" not "Add"
- No dot at end: "add feature" not "add feature."
- Max 72 characters
Examples
✅ Good:
feat(server): add C4 context diagram generationfix(tools): correct PlantUML container parsingdocs(readme): update installation instructionschore(git): add commit message rules and validation hook
❌ Bad:
Naprawiono błąd(Polish, no format)Add feature(no type prefix)Added C4 diagram(past tense, no type)feat(server): Add comprehensive C4 context diagram generation with full support(too long, capitalized)
When Creating Commits
- Always generate commit message in English
- Always use Conventional Commits format
- Always keep subject under 72 characters
- Always use imperative present tense
- Never use Polish in commit messages
The git hook (.githooks/commit-msg) will validate these rules automatically.
Integration with Git Hooks
This Cursor rule works together with the git hook (.githooks/commit-msg):
- Cursor Rules: Help AI generate correct commit messages
- Git Hooks: Validate and block incorrect commit messages
Both are required for complete commit message enforcement.
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.
- 2d ago First seen · 78 lines · 521 tokens per session scan A 47e6bcf1ebff
commit-messages is a cursor rule published in the GitHub repository lukaszzychal/mcp-doc-generator (2 stars, last pushed 9mo ago), licensed MIT. It adds 521 tokens to every session, about $0.0026 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 cursor rules, from other repositories
archgate-governance
Archgate ADR governance — enforces architecture decision records.
pull-request-templates
Pull request templates, commit conventions, code review standards, and quality gates. Applied when creating PRs, writing commits, or reviewing code.
ai_software_architect_reviews
Comprehensive evaluation from all team perspectives.
ai_software_architect_structure
Main framework directory containing all architecture documentation.
ai_software_architect_usage
Command: "Create ADR for [decision topic]".
ai_software_architect_overview
This project uses the AI Software Architect framework for structured architecture management. The framework provides a systematic approach to documenting decisions, conducting reviews, and managing architectural evolution.