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/pampaWrote 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/pampa/git-commit-guidelines)<a href="https://agentmods.dev/rules/tecnomanu/pampa/git-commit-guidelines"><img src="https://agentmods.dev/badge/rules/tecnomanu/pampa/git-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/pampa/git-commit-guidelines"><img src="https://agentmods.dev/badge/rules/tecnomanu/pampa/git-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 | $0.00691 | $0.00691 |
| Opus 5.5 | $0.00276 | $0.00276 |
| Sonnet 5.5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
git-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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Guidelines
Adopt Conventional Commits with emojis for quick context:
| Type | Emoji | Example |
|---|---|---|
| feat | ✨ | feat(api): ✨ add user authentication |
| fix | 🐛 | fix(payment): 🐛 handle timeout error |
| docs | 📝 | docs(readme): 📝 clarify setup |
| refactor | ♻️ | refactor(core): ♻️ extract helper |
| test | ✅ | test(utils): ✅ edge cases for parser |
| chore | 🔧 | chore(ci): 🔧 bump node version |
Versioning
- MAJOR: breaking changes (v2.0.0)
- MINOR: new features, backward‑compatible (v1.1.0)
- PATCH: bug fixes, backward‑compatible (v1.0.1)
Author Identity Rules
To clearly differentiate the origin of each commit, ALWAYS use --author according to context:
Human Developer Commits
Commits made directly by human developers:
# Use developer's normal identity (without --author)
git commit -m "feat(auth): ✨ implement OAuth login"
AI Assistant Commits
Commits made by AI assistants (Cursor, Claude, ChatGPT, etc.):
# MANDATORY use --author with AI identification
git commit --author="Cursor AI <[email protected]>" -m "feat(api): ✨ add user validation"
git commit --author="Cursor AI <[email protected]>" -m "fix(auth): 🐛 handle token expiry"
Automated System Commits
Automatic commits (semantic-release, bots, CI/CD):
# These systems already configure their own author automatically
# No manual action required
Important Notes
- Avatar Display: Avatar is determined by email. Emails not associated with GitHub accounts will show default avatar
- Consistency: Maintain consistency in AI email format:
<ai-name>[email protected] - Transparency: This practice improves transparency and traceability of collaborative development
Release Guidelines
When NOT to Create Releases
- Default Behavior: Do NOT create releases unless explicitly requested
- Check Existing Automation: Before attempting any release, verify if automation already exists:
- GitHub Actions workflows (
.github/workflows/) - GitLab CI/CD pipelines (
.gitlab-ci.yml) semantic-releaseinpackage.jsondependencies- Other automated release tools
- GitHub Actions workflows (
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 · 79 lines · 691 tokens per session scan A 3e5d7f94e4f5
git-commit-guidelines is a cursor rule published in the GitHub repository tecnomanu/pampa (30 stars, last pushed 1y ago), licensed ISC. It adds 691 tokens to every session, about $0.0028 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
git
Git workflow — commit format, push policy, and PR process.
commit-sponsors
Every git commit message must acknowledge BetterDesk supporters.
no-ai-contributors
Never add AI tools as git authors or project contributors.
git-discipline
Commit, push, and branching rules. Owns ALL git behavior; other files state only their deviations.
git-commit-standards
Enforce structured Git commit messages.
conventional-commits
Use the Conventional Commit Messages specification to generate commit messages.