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/xrensiu/claude-code-forge/commitnpx skills add XRenSiu/claude-code-forge --skill commitgit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/commit)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/commit"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/commit.svg" alt="Measured on agentmods" 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 | $0.00216 | $0.02043 |
| Opus 5 | $0.00108 | $0.01022 |
| Sonnet 5 | $0.00043 | $0.00409 |
| Haiku 4.5 | $0.00022 | $0.00204 |
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commit — 一个关注点，一条能审的记录，三道落地前的闸
产物是一个 git commit：消息按 Conventional Commits 的形状（产物序），暂存集只含这个关注点的 文件。本文件写：commit 在这条流水线里是什么、什么算对、原语与出口、不可豁免的边界。分几次 提、先提哪个是你的份额。
缺口（Judgment + Capability）
deletion 测试：撤掉本 skill，引擎 git add -A && git commit -m "fix stuff"——把三张卡的改动、
一个误留的 .env、一处 console.log 和一条改了 done_when.yaml 的行一起提进去。review 无法
按关注点读，锁形同虚设，白名单从未在落地前被检查。缺的是判据（原子 / 消息 / 不该进的东西）
和把机械半边编译掉的原语。
世界（Σ：git 的性质，不是流程规定）
- 暂存是按 hunk 的：
git add -p可以只提一个文件里属于本关注点的块。一个 diff 含两个 关注点 → 两次提交，不是一条长消息。 - 本地 commit 可逆、push 不可逆、amend 改写历史：未推送的 commit 可
--amend/reset --soft； 已推送的永不 amend / rebase（毁 review 锚点、毁协作者基线）。 - 消息是给六个月后的人读的：subject 说做了什么（祈使、≤ 72 字符、不加句号），body 说
为什么与取舍，footer 说关联（
Refs #N/Closes #N）与 breaking change。 - 卡与锁（在 /sdlc 里跑时）：卡的
allowed_files是白名单执行器的输入；.done_when.lock列出的文件是 G2 冻结物，同一 diff 改它们必须带change-proposal-*.md。 - 红-绿证据（TDD 模式下）：新增测试的 commit 先于实现的 commit，且前者在基线上必须失败——
这是堵"driver 写成空断言"的主防线。本 skill 不做红-绿脚本；
references/conventions.md写了手工做法与记录格式（登记为空白）。 - 关于用户的 Σ："提一下""存个档"= 用户要的是安全点，不是发布；WIP 允许但消息也要能读
（
wip(scope): …），且不进 main。
判据（φ）
- 原子：暂存文件属于一个关注点；跨 > 3 个顶层目录且无 scope → 可疑（flag，非拒）。
- 消息：
type(scope)?: subject，type ∈ feat/fix/docs/style/refactor/perf/test/chore/ci/build/revert（+wip仅限非 main）； subject ≤ 72、无句号；body 行 ≤ 100（flag）；有 issue 时 footer 含Refs #N或Closes #N（flag）；!或BREAKING CHANGE:时 body 必须解释。 - 不该进的东西（拒）：secret 形态的字符串（AWS / GitHub / Slack / OpenAI token、私钥块）；
debugger;/pdb.set_trace()/binding.pry；.env、*.pem、id_rsa；node_modules/、 构建产物（除非仓库约定提交）。console.log/print(新增行 → flag。 - 白名单（
--card）：每个暂存文件匹配allowed_files且不匹配forbidden_files；溢出即拒。 - 锁（
--lock）：锁内文件被改 → 无变更提案同 diff → 拒；有 → 放行并提示登记 task 回流。 - 不在 main / master / develop 上提交（拒，除
--allow-main）。 - 体量：新增 > 800 行 → flag "考虑拆"。
- 残差（人 / judge）：消息说的"为什么"是不是真的；两个文件到底算不算一个关注点。
原语（Π）
scripts/verify_commit.py [--msg-file F | --msg S] [--card C] [--lock L] [--issue N] [--allow-main]—— 读暂存区（git diff --cached），exit 0 过 / 1 拒 / 2 IO。commit 前必须跑；它检的是 产物（暂存集 + 消息），对你怎么组织改动免疫。assets/commit_template.txt—— 消息形状。references/conventions.md—— type/scope 语义、breaking change、红-绿证据记录、分支命名。- 前置自检（存在则跑）：
package.json的test/lint/typecheck、Makefile的test、pyproject的pytest——推断不出 → 照常提交，消息 body 注明untested — 未找到测试入口。
What ships with it
5 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.
- yesterday First seen · 98 lines · 216 tokens per session scan A 706ff33c4868
commit is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed yesterday), licensed MIT. It adds 216 tokens to every session and 2,043 once invoked, about $0.0011 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 2026-09-05.
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-next. 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.
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…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
git-commit
Creates git commits following Conventional Commits format with type/scope/subject and detailed markdown body. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md. Each change type gets its own markdown heading (# emoji + type), with…