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/golid-ai/golid/git-commitsgit clone --depth 1 https://github.com/golid-ai/golidWrote 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/golid-ai/golid/git-commits)<a href="https://agentmods.dev/rules/golid-ai/golid/git-commits"><img src="https://agentmods.dev/badge/rules/golid-ai/golid/git-commits.svg" alt="Measured on agentmods" 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 | $0.01050 | $0.01050 |
| Opus 5 | $0.00525 | $0.00525 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
git-commits 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 3d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commits
Thesis: Atomic commits with consistent prefixes make history scannable, bisectable, and reviewable. One logical change per commit, imperative mood, body explains "why" not "what".
Commit Message Format
type: short description (imperative, lowercase after type)
Optional body explaining the "why" — not the "what".
Keep to 1-3 sentences. Reference specific files or functions
only when it adds clarity.
Types
| Type | When |
|---|---|
feat |
New feature or capability |
fix |
Bug fix |
refactor |
Code restructure with no behavior change |
perf |
Performance improvement |
docs |
Documentation only |
test |
Adding or updating tests |
chore |
Deps, config, CI, dead code removal |
style |
Formatting, whitespace, CSS-only changes |
Rules
- First line under 72 characters
- Imperative mood: "add", "fix", "remove" — not "added", "fixes", "removing"
- No period at end of first line
- Body separated from title by blank line
- One logical change per commit — don't bundle unrelated changes
- Before committing code that touches module-owned files, run
scripts/check_spec_drift.sh <base-ref>and fix any drift in the same commit. If the change legitimately does not affect module behavior, add the required[skip-spec(<module>): <reason>]marker to the commit message. - Use HEREDOC for multi-line:
git commit -m "$(cat <<'EOF' ... EOF)" - Do NOT commit
.env, credentials, or secret files - Do NOT amend commits that have been pushed
Parallel Shared-File Exception
The "one logical change" rule has one narrow exception: cross-cutting touches
produced by parallel subagents working on shared files. See parallel-subagents
before using this exception.
If you're writing one, name it explicitly:
chore: sweep-up shared-file edits from <batch-name>. Full checklist and
examples live in docs/git-reference.md.
Change Sizing
Aim for ~100 lines of diff per logical commit. Reviewable in one sitting, bisects to a single intent. The line count is a guideline, not a hard cap — but if you're past 300 lines the commit is almost certainly bundling.
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.
- 3d ago First seen · 96 lines · 1,050 tokens per session scan A 108e0903bd37
git-commits is a cursor rule published in the GitHub repository golid-ai/golid (40 stars, last pushed 2mo ago), licensed MIT. It adds 1,050 tokens to every session, about $0.0052 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.
Other cursor rules, from other repositories
git-commits
Git commit safety — commits are human-only; AI suggests, never executes.
git-flow
Branching, commits and PR hygiene. Always applies.
documentation
CRITICAL: Update documentation automatically after every code change.
version-management
Automatically commit and push changes after completing any feature, bug fix, or significant addition.
git-commits
Git commit safety — commits are human-only; AI suggests, never executes.
git-commits
Git commit safety — commits are human-only; AI suggests, never executes.