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/heminwon/claude-code-marketplace/commitnpx skills add HeminWon/claude-code-marketplace --skill commitgit clone --depth 1 https://github.com/HeminWon/claude-code-marketplaceWhat 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 | $0.00062 | $0.01492 |
| Opus 5 | $0.00031 | $0.00746 |
| Sonnet 5 | $0.00012 | $0.00298 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Message
Bundled Resources
assets/commit-message-template.md：提交信息模板与示例commands/configure.md：配置 commit message 语言（写入git config --local claude.commit.lang）
Arguments
- 原始参数：
$ARGUMENTS - 约定格式：
[type] [scope] [subject] - 若未提供参数，则完全基于 staged diff 自动推断
- 若仅提供部分参数（如
type），其余字段自动推断并让用户确认
Workflow
-
获取改动信息（仅暂存区，先轻后重）：
- 必要命令：
git status --short、git diff --staged --stat、git diff --staged --name-only、git config user.name、git config user.email、git config --local claude.commit.lang - 若暂存区为空，提示用户先 stage 并停止。
- 条件命令：仅在类型/范围无法判断、存在 breaking 风险或用户要求精细对比时，展开
git diff --staged全量内容。
- 必要命令：
-
分析改动：
- 识别模块：基于路径/高频词确定模块或组件。
- 识别类型：
feat,fix,refactor,perf,docs,style,test,build,chore,ci。 - 判断范围：单模块使用
scope，多模块省略scope。 - 评估复杂度：简单/中等/复杂（按语义影响判断）。
- Commit message 语言优先使用
git config --local claude.commit.lang；若未配置，则基于项目变更内容与项目文档主语言联合推断。 - 若 staged diff 过大导致成本过高，可参考当前对话上下文压缩语义，但必须先以 staged 事实做锚定。
-
生成 Commit Message（按改动复杂度自适应生成候选版本数（1-3个））：
- 格式：
<gitmoji> <type>(<scope>): <subject>（多模块省略 scope）。 - Subject：祈使句、<= 50 字符、无句号；各版本一致。
- Body：简单 1-2 条，中等 2-4 条，复杂 4-6 条。
- 按改动复杂度自适应生成候选版本数（1-3个）并标注推荐项。
- 先生成并冻结 Footer（候选间保持一致），候选阶段直接展示完整 Footer；仅在
BREAKING CHANGE/Refs/Closes存在事实差异时允许不同。 - Footer 顺序如下：
- 可选：
BREAKING CHANGE: <desc>、Refs: #123、Closes: #456 - 空行
🤖 Generated with <tool> (<model>)- 空行
Co-Authored-By: <当前 AI tool> <该工具对应邮箱>（自识别当前工具并填写对应邮箱，禁止使用git config user.email；若无法确定邮箱则省略此行）Signed-off-by: <name> <email>（取自git config user.name/git config user.email；若缺失则省略）
- 可选：
- 格式：
-
输出与交互：
- 先输出摘要（files/modules/type/lines/complexity，是否展开 full diff）。
- 若启用了对话上下文辅助推断，在摘要中显式说明。
- 按改动复杂度自适应输出候选版本数（1-3个）并标注推荐版本（含完整 Footer）。
- 提示用户回复：版本号 /
y直接提交并 push 推荐版本 /e编辑 /n取消。 - 单次确认即执行：输入版本号后直接提交；输入
y后直接提交推荐版本并立即 push（不再二次确认）。
-
提交与推送：
- 选择版本号后使用已展示的完整 message 提交；输入
y时使用推荐版本提交。 - 使用 heredoc 或
git commit -F <file>写入完整多行 commit message（避免多行被-m压缩），展示 commit hash。 - 输入
y后在 commit 成功后直接执行git push；输入版本号后保持原流程：显示分支并询问是否 push。 - 选择
e进入交互式编辑 subject/body 后重新生成；Footer 按规则自动重算并保持结构不变。
- 选择版本号后使用已展示的完整 message 提交；输入
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.
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.
- yesterday First seen · 88 lines · 62 tokens per session scan A 1064faa6c760
commit is a skill published in the GitHub repository HeminWon/claude-code-marketplace (2 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 1,492 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…