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/strelov1/freehireWrote 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/strelov1/freehire/commit-checks)<a href="https://agentmods.dev/rules/strelov1/freehire/commit-checks"><img src="https://agentmods.dev/badge/rules/strelov1/freehire/commit-checks/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/strelov1/freehire/commit-checks"><img src="https://agentmods.dev/badge/rules/strelov1/freehire/commit-checks.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 | $0.00175 | $0.00175 |
| Opus 5.5 | $0.00070 | $0.00070 |
| Sonnet 5.5 | $0.00035 | $0.00035 |
| Haiku 4.5 | $0.00017 | $0.00017 |
Grade A, and why
commit-checks 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.
What it actually says
Before committing Go
When creating a git commit that includes any *.go file:
gofmt -wthose paths.gofmt -l .must print nothing.go vet ./...go test ./...(unit tests only — no-tags=integration).
Do not commit if vet or tests fail; fix first.
Skip this suite when the commit has no Go files (docs, OpenSpec, web-only).
Do not run go test -tags=integration ./... at commit time. That stays push-time: go vet -tags=integration ./... before every push; the full tagged suite when behaviour changed.
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 · 19 lines · 175 tokens per session scan A 1f449adea427
commit-checks is a cursor rule published in the GitHub repository strelov1/freehire (842 stars, last pushed today), licensed MIT. It adds 175 tokens to every session, about $0.0007 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
A Git workflow rule set covering branch names, commit messages, and pull-request titles, with issue IDs linking changes to tracked work.
pre-commit-lint-format
Enforce Prettier format, ESLint lint, and unit tests before every commit in lfx-self-serve.
hook-commits
Set up pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
cmd-build
Implement the next task incrementally — build, test, verify, commit.
issue-workflow
GitHub issue workflow and mandatory manual-test handoff for UI/behavior changes.
swarm-forge-handoff
Handoff YAML estricto — un script lo valida, y desde 0.28 comprueba el protocolo de dos pasadas.