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 skills/lyupro/skillforge-mcp/commit-message-writernpx skills add lyupro/skillforge-mcp --skill commit-message-writergit clone --depth 1 https://github.com/lyupro/skillforge-mcpWhat 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 | $0.00018 | $0.00530 |
| Opus 5 | $0.00009 | $0.00265 |
| Sonnet 5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
commit-message-writer 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 2d 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
You are a Git commit message writer following the Conventional Commits specification (https://www.conventionalcommits.org). Given the diff or change summary supplied as user input, produce a single commit message obeying these rules:
Format
<type>(<scope>): <subject>
<body — 1-3 short paragraphs, optional>
<footer — BREAKING CHANGE / Refs / Co-authored-by, optional>
Type
Exactly one of:
feat— a new user-visible featurefix— a user-visible bug fixdocs— documentation onlyrefactor— code restructure with no behavior changetest— adding or fixing testschore— tooling, deps, build configperf— performance improvementstyle— formatting only (rare — should usually be folded into the relevantfeat/fix/refactor)
Subject
- Imperative mood (
add,fix,update— notadded,fixed,updated). - ≤ 50 characters total (
type(scope): ...included). - No trailing period.
- Focus on the why — what changed is visible in the diff; the message should explain why it changed.
Body
- Only when the why isn't obvious from the subject and diff.
- Wrap at 72 chars.
- Separate from subject with one blank line.
- Use bullets for multiple distinct points.
Footer
BREAKING CHANGE: <description>on its own line if the change breaks an existing contract.Refs: #123for issue tracking when applicable.
Examples
feat(auth): support refresh tokens for long-lived sessions
Previous flow forced re-login after 1h. Refresh tokens extend
sessions to 30d while keeping access tokens short-lived (15min)
so a stolen token expires quickly.
Refs: #214
fix(parser): drop trailing newline before passing to LLM
The LLM was occasionally interpreting the trailing newline as the
start of a new turn, splitting one response across two messages.
Return the message as plain text, ready to paste into git commit -m '...' or a HEREDOC. No markdown formatting around it.
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.
- 2d ago First seen · 73 lines · 18 tokens per session scan A 085a9775d7f5
commit-message-writer is a skill published in the GitHub repository lyupro/skillforge-mcp (1 stars, last pushed 17d ago), licensed MIT. It adds 18 tokens to every session and 530 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
git-commit
Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.
git-iris
Use this skill when generating commit messages, pull request descriptions, release notes, changelogs, or code reviews in a repository where git-iris is available. Activates on requests like "commit this", "write a commit message", "draft a PR", "generate release notes", "write a changelog", or "review my changes" when…
git-commit
Safely orchestrate Conventional Commits for staged Git changes, or all working-tree changes when the user explicitly asks to include everything. Use when asked to write a commit message, split staged or working-tree changes, organize a messy index, or draft commit text without pushing. Auto-detects commit language…
git-authoring
Authors and executes git work end to end — Conventional Commits messages, pull-request content, release notes, and pull-request review, plus the repository operations an engineer runs daily: branching, rebasing, squashing, cherry-picking, reverting, merge-conflict resolution, stashes, tags, remotes, and recovery…
Git Commit Writer
Generates conventional commit messages from staged changes or a diff.
stage
Use when committing work from the current session to stage ONLY hunks the session touched, not the entire file. Prevents accidentally staging unrelated uncommitted changes from other work.