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.
git clone --depth 1 https://github.com/tecnomanu/agent-rules-kitWrote 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/rules/tecnomanu/agent-rules-kit/commit-guidelines)<a href="https://agentmods.dev/rules/tecnomanu/agent-rules-kit/commit-guidelines"><img src="https://agentmods.dev/badge/rules/tecnomanu/agent-rules-kit/commit-guidelines/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.
<a href="https://agentmods.dev/rules/tecnomanu/agent-rules-kit/commit-guidelines"><img src="https://agentmods.dev/badge/rules/tecnomanu/agent-rules-kit/commit-guidelines.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00646 | $0.00646 |
| Opus 5.5 | $0.00258 | $0.00258 |
| Sonnet 5.5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
commit-guidelines 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Guidelines - CRITICAL VERSION CONTROL
⚠️ CRITICAL WARNING - BREAKING CHANGES
NEVER use BREAKING CHANGE: in commit messages unless it's a REAL breaking change that requires users to modify their code!
The project uses semantic-release which automatically:
fix:→ PATCH version (2.4.2 → 2.4.3)feat:→ MINOR version (2.4.2 → 2.5.0)BREAKING CHANGE:→ MAJOR version (2.4.2 → 3.0.0) ← AVOID THIS!
Commit Format
<type>: <emoji> <description>
[optional body]
[optional footer - NO BREAKING CHANGE unless absolutely necessary]
Allowed Types
For Version Bumps:
fix: 🐛- Bug fixes (PATCH)feat: ✨- New features (MINOR)
For No Version Bump:
docs: 📝- Documentation changesstyle: 🎨- Code formatting, stylingrefactor: ♻️- Code refactoringtest: ✅- Adding testschore: 🔧- Maintenance tasksci: 🚀- CI/CD changes
Examples
✅ CORRECT:
# Minor feature (will be 2.4.2 → 2.5.0)
git commit -m "feat: ✨ add IDE selector integration"
# Bug fix (will be 2.4.2 → 2.4.3)
git commit -m "fix: 🐛 correct backup logic for single files"
# No version bump
git commit -m "docs: 📝 update README with new examples"
❌ WRONG:
# This creates MAJOR version bump (3.0.0)!
git commit -m "feat: ✨ add IDE selector
BREAKING CHANGE: Removed install command"
When IS a Breaking Change?
Only use BREAKING CHANGE: when:
- API changes that break existing code
- Removing public functions/methods
- Changing function signatures
- Removing CLI flags that users rely on
- Changing default behavior that breaks existing workflows
Current Project Status
- Current version: 3.0.1 (due to incorrect BREAKING CHANGE usage)
- Going forward: Use only
fix:andfeat: - Avoid:
BREAKING CHANGE:unless absolutely necessary
AI Assistant Guidelines
When making commits as "Agent AI":
- Always use
--author="Agent AI <[email protected]>" - Prefer
fix:overfeat:when in doubt - Never use
BREAKING CHANGE:without explicit user confirmation - Keep commit messages concise and descriptive
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 First seen · 92 lines · 646 tokens per session scan A d4adcff1687c
commit-guidelines is a cursor rule published in the GitHub repository tecnomanu/agent-rules-kit (36 stars, last pushed 1y ago), licensed ISC. It adds 646 tokens to every session, about $0.0026 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.
Other cursor rules, from other repositories
github-workflow
GitHub invariants — standard flow on listed use cases; no issue spam; tick linked checklists before merge.
git
Git rules. Conventional commits, atomic staging, no force push.
release-ts-sdk
Release @aptos-labs/ts-sdk or @aptos-labs/confidential-asset — version bump, changelog stamp, release PR, then tag + GitHub Release that triggers NPM publish.
40-git-safety
Git safety rule for branches, commits, pushes, and destructive Git commands.
git-master
Git operations — clean commits, PR prep, conflict resolution, change summaries.
git-workflow
Git branching and PR workflow.