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 skills add andrewsrigom/agent-skills --skill setup-conventional-commitsgit clone --depth 1 https://github.com/andrewsrigom/agent-skillsWrote 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/skills/andrewsrigom/agent-skills/setup-conventional-commits)<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/setup-conventional-commits"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/setup-conventional-commits/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/skills/andrewsrigom/agent-skills/setup-conventional-commits"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/setup-conventional-commits.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 | $0.00056 | $0.00794 |
| Opus 5.5 | $0.00022 | $0.00318 |
| Sonnet 5.5 | $0.00011 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
setup-conventional-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 2mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Conventional Commits
Use this skill when the task is to enforce Conventional Commits in a repo with minimal friction.
Scope
commitlintsetup- Husky
commit-msghook setup - local
commit-msgenforcement - choosing a minimal config
- keeping commit flow lightweight
Routing cues
- enforce semantic commits, add commitlint, set up conventional commits, validate commit messages, or add a
commit-msghook -> use this skill - if the task is about naming one specific commit well -> use
write-intentional-commit-message - if the task is mainly about broader pre-commit automation -> use
setup-pre-commit
Default path
- Use Conventional Commits as the history format.
- Use
@commitlint/cliwith@commitlint/config-conventional. - Prefer one small config file such as
commitlint.config.cjs. - Add a
commit-msghook through Husky when the repo accepts local hook tooling. - Keep enforcement syntax-focused in tooling and intent-focused in docs or agent guidance.
When to deviate
- Extend the default type rules only when the repo has a real semantic need, not just personal preference.
- Skip Husky if the repo deliberately avoids local Git hook tooling.
- Add prompts or commit generators only when the team explicitly wants them; do not make them the default.
Guardrails
- keep the config minimal
- syntax enforcement should not pretend to solve poor commit intent by itself
- do not add
commitizenor other interactive tooling unless the repo actually wants that ceremony commit-msgvalidation is the right hook for commit format; do not overloadpre-commit
Avoid
- introducing a large commit workflow stack for a small repo
- forcing interactive commit tooling when plain Git is enough
- adding extra enforcement layers when the local hook already solves the problem
- treating enforcement as complete when contributors still have no guidance on type selection
Verification checklist
- the repo has one clear Conventional Commit policy
- commitlint config is minimal and readable
commit-msgis used for message validation if local hooks are enabled- contributors still have guidance on choosing the right type, not only passing syntax
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 84 lines · 56 tokens per session scan A f1aee12ad909
setup-conventional-commits is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 56 tokens to every session and 794 once invoked, about $0.0002 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 2026-08-31.
setup-conventional-commits compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setup-conventional-commitsandrewsrigom/agent-skills | Skill | 2 | 7mo ago | MIT | A | 56 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| git-commitThinkInAIXYZ/deepchat | Skill | 6.4k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| repo-syncdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 25 | Claude Code, Codex |
| engineer-bot-opsmakecindy/cindy | Skill | 9.4k | today | Apache-2.0 | A | 57 | Claude Code, Codex |
| mcore-split-prNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 25 | Claude Code |
| git-commit-writermergisi/awesome-openclaw-agents | Skill | 4.1k | 3d ago | MIT | A | 53 | Claude Code, Codex |