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 Jxin-Cai/jxin-skills --skill git-auto-commit-reviewgit clone --depth 1 https://github.com/Jxin-Cai/jxin-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/jxin-cai/jxin-skills/git-auto-commit-review)<a href="https://agentmods.dev/skills/jxin-cai/jxin-skills/git-auto-commit-review"><img src="https://agentmods.dev/badge/skills/jxin-cai/jxin-skills/git-auto-commit-review/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/jxin-cai/jxin-skills/git-auto-commit-review"><img src="https://agentmods.dev/badge/skills/jxin-cai/jxin-skills/git-auto-commit-review.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 | $0.00087 | $0.01148 |
| Opus 5 | $0.00044 | $0.00574 |
| Sonnet 5 | $0.00017 | $0.00230 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
git-auto-commit-review 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 9d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git 提交助手
支持快速提交和深度 CR 提交两种模式。简单改动走快速流程，关键变更走 CR 流程。
流程
第 0 步：获取变更
git diff && git diff --staged && git status --porcelain
如果无任何变更，告知用户并停止。
第 1 步：暂存检查
检查是否有未暂存的改动：
- 如果所有改动已暂存（staged），直接进入第 2 步
- 如果有未暂存的改动，向用户确认：暂存全部（
git add -A）还是只暂存部分文件
第 2 步：询问提交模式
向用户展示变更概要（改了哪些文件、大致改了什么），然后询问：
- 快速提交：仅生成规范 commit message 并提交，适合小改动
- CR 提交：深度代码审查 + 生成审查报告 + 提交，适合重要变更
快速提交流程
生成 commit message
格式：<type>(<scope>): <subject>（scope 可选）
允许的 type：feat | fix | to | docs | style | refactor | perf | test | chore | revert | merge | sync
fix= 本次提交包含实际修复to= 团队扩展类型，标记待修复的 bug，后续用fix提交（非 Conventional Commits 标准）
subject 要求：中文优先，<=50 字，不加结尾标点。
示例：fix(DAO):用户查询缺少username属性 · feat(Controller):用户查询接口开发
确认并提交
- 向用户展示 commit message，等待确认
- 确认暂存区内容（
git diff --staged） - 提交。绝不修改 git config，绝不 push 除非用户明确要求
CR 提交流程
第 1 步：生成审查快照
运行本技能 scripts/ 目录下的脚本捕获当前状态：
python3 "<本技能目录>/scripts/create_review_bundle.py"
注：
<本技能目录>指本技能的实际安装路径，即包含此 SKILL.md 的目录。
在 code_review_reports/ 下生成带时间戳的文件集（.md 报告模板、.diff.patch、.status.txt 等）。
第 2 步：审查 diff
以资深工程师视角审查，关注：可维护性、健壮性、性能、并发安全、API 设计、可测试性、边界情况。
- 读取
.diff.patch和.diff_staged.patch - 根据项目技术栈选择审查规则（通用规则必读，语言规则按需加载）：
- 通用规则（所有项目必读）：
references/review-rules.md - Java 后端（Spring/Dubbo/MyBatis）：
references/review-rules-java.md - 前端（Vue/React/TypeScript）：
references/review-rules-frontend.md - Python（Django/Flask/FastAPI）：
references/review-rules-python.md - Go：
references/review-rules-go.md - 只读取与变更相关的章节，不必逐条检查
- 通用规则（所有项目必读）：
- 编辑
.md报告文件（用文件编辑工具写入），填写：- 变更概览：改了什么、影响范围、风险等级
- 必须修复：阻塞提交的问题
- 建议改进：不阻塞提交但值得优化
- 建议明细：每条建议附文件路径和理由
第 3 步：等待用户决策
展示审查结论，等待用户明确回复。审查阶段只输出建议，不主动修改代码。
用户回复后，编辑报告的"开发者决策"章节，记录采纳情况。
第 4 步：执行采纳的建议
用户明确采纳后，进入修改阶段：
- 实施用户同意的修改
- 更新快照：
python3 "<本技能目录>/scripts/create_review_bundle.py" --update-latest - 更新报告中的"已执行变更"章节
What ships with it
6 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.
- 9d ago First seen · 110 lines · 87 tokens per session scan A 1d49285965c6
git-auto-commit-review is a skill published in the GitHub repository Jxin-Cai/jxin-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,148 once invoked, about $0.0004 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
pr-pending-feedback
Evaluate pending (unsubmitted) review comments on the current branch's PR and, after user confirmation, address each in a separate sub-agent and separate commit.