yet-another-agent-harness: Skill for Claude Code

.claude/skills/commitlint/SKILL.md

commitlint is a skill for Claude Code from dirien/yet-another-agent-harness. It costs 50 tokens per session (967 once invoked), scanned B, original, MIT.

A tool for checking whether Git commit messages follow Conventional Commits, a shared format such as `fix:` or `feat:` that describes the kind of change.

In plain words
What is it for?
Use it to validate commits, prepare pull requests, detect project-specific rules, and receive specific corrections when a message has the wrong format.
Why use it?
Consistent commit messages make project history easier to read and support automatic changelogs and version decisions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dirien/yet-another-agent-harness's own configuration. It tells Claude Code how to work on yet-another-agent-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yet-another-agent-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dirien/yet-another-agent-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dirien/yet-another-agent-harness/main/.claude/skills/commitlint/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dirien/yet-another-agent-harness

Made for: Claude Code.

Wrote 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.

agentmods badge for commitlint

README.md
[![agentmods](https://agentmods.dev/badge/skills/dirien/yet-another-agent-harness/commitlint/github.svg)](https://agentmods.dev/skills/dirien/yet-another-agent-harness/commitlint)
Your own site
<a href="https://agentmods.dev/skills/dirien/yet-another-agent-harness/commitlint"><img src="https://agentmods.dev/badge/skills/dirien/yet-another-agent-harness/commitlint/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.

agentmods 80×15 button for commitlint

Your own site · 80×15
<a href="https://agentmods.dev/skills/dirien/yet-another-agent-harness/commitlint"><img src="https://agentmods.dev/badge/skills/dirien/yet-another-agent-harness/commitlint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.00967
Opus 5.5 $0.00020 $0.00387
Sonnet 5.5 $0.00010 $0.00193
Haiku 4.5 $0.00005 $0.00097

Measured 1mo ago against content hash 8dd6ab166456, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

commitlint scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Use `sudo npm install -g ...` or fix npm permissions
.claude/skills/commitlint/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commitlint

Validate commit messages follow the Conventional Commits specification. Enables automatic changelog generation, semantic versioning, and clean git history.

What this skill does

  1. Checks if @commitlint/cli and @commitlint/config-conventional are installed; installs them if missing.
  2. Detects project-specific commitlint configuration or falls back to a sensible default config.
  3. Validates commit messages for type, scope, subject, body, and footer format.
  4. Reports errors with specific fixes and examples.

Installation check

# Check if commitlint is available
npx commitlint --version 2>/dev/null

If not installed, install globally:

npm install -g @commitlint/cli @commitlint/config-conventional

If installation fails (permissions, no npm), stop validation and report the issue with remediation steps:

  • Use sudo npm install -g ... or fix npm permissions
  • Use a Node version manager (nvm, volta, fnm)
  • Install Node.js if not present

Do not silently skip validation.

Config detection priority

  1. commitlint.config.js in project root
  2. .commitlintrc.json in project root
  3. .commitlintrc.yaml in project root
  4. .commitlintrc in project root
  5. commitlint field in package.json
  6. Default config (see references/conventional-commits.md)

If no project config exists, create a temporary .commitlintrc.json using the default config from the reference document before running validation.

Validation workflow

1. Check commitlint installation
   ├─ Installed → continue
   └─ Missing → install, then continue (fail if install fails)

2. Detect project config
   ├─ Found → use it
   └─ Not found → use default config from references/

3. Run validation
   ├─ From a string:
   │    echo "<message>" | npx commitlint
   ├─ From a file:
   │    cat <file> | npx commitlint
   └─ From last git commit:
        git log -1 --format=%B | npx commitlint

4. Report results
   ├─ Valid → confirm and proceed
   └─ Invalid → show errors, suggest fixes, re-validate after correction

Read the full file on GitHub · 145 lines

Files

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.

Changes

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.

  1. 1mo ago First seen · 145 lines · 50 tokens per session scan B 8dd6ab166456

Subscribe to this mod's changes

commitlint is a skill published in the GitHub repository dirien/yet-another-agent-harness (20 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 967 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.