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 FeiZhuLulu/kimi-code-skills --skill commit-craftgit clone --depth 1 https://github.com/FeiZhuLulu/kimi-code-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/feizhululu/kimi-code-skills/commit-craft)<a href="https://agentmods.dev/skills/feizhululu/kimi-code-skills/commit-craft"><img src="https://agentmods.dev/badge/skills/feizhululu/kimi-code-skills/commit-craft/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/feizhululu/kimi-code-skills/commit-craft"><img src="https://agentmods.dev/badge/skills/feizhululu/kimi-code-skills/commit-craft.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 | $0.00022 | $0.02120 |
| Opus 5.5 | $0.00009 | $0.00848 |
| Sonnet 5.5 | $0.00004 | $0.00424 |
| Haiku 4.5 | $0.00002 | $0.00212 |
Grade A, and why
commit-craft 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.
How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Craft — Conventional Commit Message Generator
Purpose
Analyze git changes and generate well-structured Conventional Commit messages. This skill generates messages only — it does not execute git commit unless the user explicitly asks you to commit.
Kimi Code Usage
Manual invocation:
/skill:commit-craft
/skill:commit-craft staged only
/skill:commit-craft unstaged diff
/skill:commit-craft split
Requested mode: $mode
Supported modes:
staged only— only analyze staged changesunstaged diff— analyze unstaged changessplit— suggest splitting into multiple commits- (empty) — default behavior: prefer staged, fall back to unstaged
This skill may be automatically invoked when the user asks for a commit message, but it must not run git commit unless the user explicitly asks to create the commit now.
Workflow
1. Check Repository State
git status --short
git rev-parse --is-inside-work-tree 2>/dev/null
If not inside a git repo, stop and tell the user.
2. Get the Diff
Preferred: staged changes (what will be committed):
git diff --cached --stat
git diff --cached
If staging area is empty, check unstaged changes:
git diff --stat
git diff
If both are empty, check for untracked files:
git ls-files --others --exclude-standard
If nothing at all, tell the user there's nothing to commit.
If there are unstaged changes but nothing staged:
- Show the user what changed
- Tell them: "These changes are not staged yet. Run
git addfirst, or tell me to proceed with the unstaged diff." - Do not assume they want to stage everything
2.1 Secret Safety Check
Before generating any commit message, scan the diff for secrets:
.envfiles,*.pem,*.keyfiles being added or modified- Strings matching known token prefixes:
sk-,ghp_,hf_,AKIA,AIza,xoxb-,Bearer eyJ... - Strings matching
*_KEY=,*_TOKEN=,*_SECRET=,*_PASSWORD=with non-empty values - Private key blocks (
-----BEGIN PRIVATE KEY-----)
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 · 271 lines · 22 tokens per session scan A adf44a1d8a31
commit-craft is a skill published in the GitHub repository FeiZhuLulu/kimi-code-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 2,120 once invoked, about $0.0001 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.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.