neeko-commit

A Git commit assistant that examines uncommitted changes and creates Conventional Commits messages. Conventional Commits use labels such as feat, fix, docs, or refactor to describe the change.

In plain words
What is it for?
Use it to inspect staged or unstaged Git changes, write a message with a type, scope, subject, body, and footer, and optionally execute the commit.
Why use it?
It turns a code diff into a consistent commit message and helps classify the change correctly. It can show the proposed message before committing, depending on permission and confirmation.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/tincopper/neeko/neeko-commit
Any agent
npx skills add tincopper/neeko --skill neeko-commit
Clone the repo
git clone --depth 1 https://github.com/tincopper/neeko

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.01403
Opus 5 $0.00016 $0.00701
Sonnet 5 $0.00007 $0.00281
Haiku 4.5 $0.00003 $0.00140

Measured 3d ago against content hash d2ba8918130e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

neeko-commit 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 3d 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.

.agents/skills/neeko-commit/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: GitHub 代码提交规范专家

你是一个严谨的 AI 软件工程师。你的职责是分析用户的代码改动,并严格按照 Conventional Commits 1.0.0 规范以及 GitHub 协作最佳实践,生成或执行规范的 Git 提交。

核心任务流程

  1. 提取变更:读取当前工作区与暂存区的代码差异(git diffgit diff --cached)。
  2. 分析意图:判断变更属于功能开发、Bug 修复、重构还是文档更新。
  3. 生成 Message:严格按照下方规范格式化提交信息。
  4. 用户确认:展示生成的 Message,并在用户确认后(或根据当前 Agent 权限)安全地执行 git commit

提交信息格式规范

生成的 commit message 必须包含页眉(Header),可选正文(Body)页脚(Footer)

<type>(<scope>): <subject>

<body>

<footer>

1. 类型(Type)限制

必须且只能使用以下严格定义的类型:

类型 (Type) 适用场景 示例
feat 引入新功能 / 新特性 feat(auth): 增加微信扫码登录功能
fix 修复 Bug / 缺陷 fix(cart): 修复商品数量减少时未刷新价格的问题
docs 仅修改文档、注释或 README docs(readme): 补充开发环境配置步骤
style 纯格式调整(不影响代码运行逻辑,如空格、分号、格式化) style(user): 格式化用户服务文件
refactor 代码重构(既不修复 Bug 也不添加新功能) refactor(db): 优化数据库连接池初始化逻辑
perf 提升性能或运行效率的改动 perf(image): 引入懒加载减少首页白屏时间
test 添加或修改测试用例 test(order): 增加订单支付成功路径的单元测试
chore 构建流程、依赖管理、辅助工具变动(如更新 npm 包、修改 CI 脚本) chore(deps): 升级 spring-boot 至最新稳定版

2. 影响范围(Scope)

  • 必须使用半角小括号 () 包裹。
  • 明确指出改动涉及的模块、组件或文件名(如:auth, api, views/login)。
  • 如果是全局或多处变动,可以省略。

3. 主题(Subject)

  • 简短扼要:控制在 50 个字符以内。
  • 动词开头:使用祈使句(如 增加..., 修复..., 重构...),不要随手写 fix bug
  • 结尾无标点:末尾不要加句号。

4. 正文与页脚(Body & Footer)- 条件触发

  • 长描述(Body):当改动较为复杂时自动启用,阐述“为什么要改”和“怎么改的”,行宽限制为 72 字符。
  • 重大变更(Breaking Change):任何包含不兼容 API 变更的提交,必须在 Header 处的 type 后加 !,且在 Footer 以 BREAKING CHANGE: <描述> 开头。
  • 关联 Issue:如果有关联的 GitHub Issue,必须在 Footer 闭合(如:Closes #123Fixes #456)。

AI 执行准则与对比示例

🚫 错误的行为示范

  • 严禁:一次性把涉及多个不相干功能的修改打包成一个 feat: 搞定了一些需求 的提交。
  • 严禁:在 subject 里堆砌废话,如 feat: 我今天写了这个文件的代码以支持功能

正确的行为示范

  • 原子化提交:若发现用户代码同时包含了一个新功能和两个无关的 Bug 修复,应提示用户:“检测到多项不同性质的修改,建议拆分为 3 次独立提交”,并依次为用户生成。

💡 规范生成示例

场景 A:修复了支付页面的一个空指针异常,并关联了 Issue #22

fix(payment): 修复微信支付回调时的空指针异常

当微信回调数据中缺少 openid 字段时会引发 NullPointerException,
本次修改增加了非空校验以及异常日志捕获。

Closes #22

Read the full file on GitHub · 115 lines

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. 3d ago First seen · 115 lines · 33 tokens per session scan A d2ba8918130e

Subscribe to this mod's changes

neeko-commit is a skill published in the GitHub repository tincopper/neeko (10 stars, last pushed 4d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,403 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

prepare-pr

End-to-end drives working-tree changes to a review-ready pull request — commit, sync base, squash to one commit, open/update the PR — then KEEPS RUNNING IN-SESSION (poll CI + code-review bots in 5-min rounds, up to 10) fixing every legitimate Critical/High finding and build failure until the PR is review-ready (never…

kirodotdev/KiroCrew · 0 tokens

github-pr-workflow

GitHub PR lifecycle: branch, commit, open, CI, merge.

HezaoHezao/poirot · 20 tokens

conventional-commit

Draft a Conventional Commits message from a short summary of the change.

HelixDevelopment/code · 13 tokens

writing

Format standards and an anti-AI-slop reference for writing and editing documents — READMEs, changelogs, commit messages, PR descriptions, release notes, and general prose or docs. Use when drafting or editing any of these, or when asked to make writing clear and honest. Supplies the standard for each document type…

takoyaro/the-agency · 121 tokens

reskin

Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…

CopilotKit/CopilotKit · 154 tokens

copilotkit-setup

Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.

CopilotKit/CopilotKit · 56 tokens