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 serejaris/kimi-skills --skill conventional-commit-gengit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/conventional-commit-gen)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/conventional-commit-gen"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/conventional-commit-gen/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/serejaris/kimi-skills/conventional-commit-gen"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/conventional-commit-gen.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 | $0.00067 | $0.00915 |
| Opus 5 | $0.00034 | $0.00458 |
| Sonnet 5 | $0.00013 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
conventional-commit-gen 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 8d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conventional Commit Gen
Analyzes the current git diff and automatically generates a commit message that follows the Conventional Commits specification, with smart scope detection.
Quick Start
# Analyze unstaged changes and generate a commit message
python3 scripts/analyze_diff.py
# Analyze staged changes only
python3 scripts/analyze_diff.py --staged
# Specify a repository path
python3 scripts/analyze_diff.py --repo /path/to/repo
# JSON output (useful for programmatic integration)
python3 scripts/analyze_diff.py --staged --format json
# Manually override type or scope
python3 scripts/analyze_diff.py --staged --type-override feat --scope-override auth
Usage Workflow (SOP)
1. Get the Diff Analysis
Run the script in the user's git repository to get the automated analysis:
python3 scripts/analyze_diff.py --staged --format json
2. Review and Adjust
The script outputs:
- type: The auto-detected commit type (feat / fix / docs / style / refactor / test / chore / perf / ci / build)
- scope: The scope detected from file paths (e.g., auth, api, ui)
- description: A brief description generated from the change summary
- commit_message: The fully assembled commit message
After reviewing the output, adjust as needed:
- If the type is inaccurate (e.g., the script detected
chorebut it's actually afeat), use--type-overrideto override - If the scope doesn't fit, use
--scope-overrideto override - The description should ideally be hand-written based on the actual changes; treat the script output as a starting point
Note: Type detection is based on file paths and change statistics. It works well for types like test/docs/ci/build, but for modifications to existing source code files (feat vs fix vs refactor), you should read the diff content and make the final call.
3. Conventional Commits Reference
<type>(<scope>): <description>
[optional body]
[optional footer(s)]
What ships with it
2 files 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.
- 8d ago First seen · 107 lines · 67 tokens per session scan A 1a31958e1fec
conventional-commit-gen is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 915 once invoked, about $0.0003 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
resolve-pr-comments
Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using reasoning recalled from past Claude Code transcripts). Use when the user asks to "resolve PR comments", "fix review comments", "address PR…
ship
Commit, push, and optionally create or update a PR for the current staged changes. Use when the user asks to "ship", "ship it", "ship changes", "commit push and PR", or "ship this".
stage
Stage implementation changes for commit with precise file selection. Use when the user asks to "stage changes", "stage files", "add files to staging", or "prepare changes for commit".
review-pr
Review a pull request by fetching PR comments, running a comprehensive code review, evaluating findings, and dispatching to implementation. Use when the user asks to "review PR", "review pull request", "review this PR", "check PR before merging", or "full PR review".
update-changelog
Update the Unreleased section of CHANGELOG.md based on current changes. No-op if CHANGELOG.md does not exist. Use when the user asks to "update changelog", "add to changelog", "update the changelog", "changelog entry", "add changelog entry", or "log this change".
mm
A dispatcher that provides short /mm commands for project setup, session recovery, project overviews, and workflow checks. It maps these aliases to longer system commands.