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/07-commit-conventions)<a href="https://agentmods.dev/rules/tecnomanu/agent-rules-kit/07-commit-conventions"><img src="https://agentmods.dev/badge/rules/tecnomanu/agent-rules-kit/07-commit-conventions/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/07-commit-conventions"><img src="https://agentmods.dev/badge/rules/tecnomanu/agent-rules-kit/07-commit-conventions.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 | $0.01088 | $0.01088 |
| Opus 5.5 | $0.00435 | $0.00435 |
| Sonnet 5.5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
07-commit-conventions 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Conventions
Follow Conventional Commits with emojis and semantic-release automation.
Basic Format
<type>: <emoji> <description>
[optional body]
[optional footer]
Common Types
| Type | Emoji | Impact | Example |
|---|---|---|---|
| feat | ✨ | MINOR | feat: ✨ add user authentication |
| fix | 🐛 | PATCH | fix: 🐛 handle timeout error |
| docs | 📝 | None | docs: 📝 update README |
| chore | 🔧 | None | chore: 🔧 bump dependencies |
Breaking Changes (MAJOR version)
For major version bumps, use BREAKING CHANGE footer:
✅ Correct:
feat: 🎉 redesign authentication system
BREAKING CHANGE: Token format changed, requires client updates
❌ Wrong:
# Don't use exclamation mark
feat!: ✨ breaking change
# Don't make super long single-line messages
feat: 🎉 very long message with breaking change info all in one line BREAKING CHANGE: xyz
Author Identity (MANDATORY)
ALWAYS use --author for AI commits:
AI Assistant Commits:
# For Claude/Sonnet
git commit --author="Agent AI <[email protected]>" -m "feat: ✨ add feature"
# For Cursor AI
git commit --author="Agent AI <[email protected]>" -m "fix: 🐛 resolve issue"
Human Developer Commits:
# Use normal identity (no --author needed)
git commit -m "feat: ✨ implement feature"
Key Rules
- Keep commits short: Title under 72 characters
- Use blank lines: Separate title from body/footer
- Always use --author: For AI-generated commits
- BREAKING CHANGE footer: For major version bumps
- English only: All commit messages in English
Language
All commits must be written in English, regardless of your native language. This ensures consistency throughout the project, as all code, documentation, and rules are maintained in English.
Commit Format
We follow the Conventional Commits specification with emojis:
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 · 157 lines · 1,088 tokens per session scan A 6e81dd668d34
07-commit-conventions is a cursor rule published in the GitHub repository tecnomanu/agent-rules-kit (36 stars, last pushed 1y ago), licensed ISC. It adds 1,088 tokens to every session, about $0.0044 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.