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 agents/theeterna/api2mcp4j/git-commit-assistantgit clone --depth 1 https://github.com/TheEterna/api2mcp4jWhat 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 | $0.00054 | $0.00926 |
| Opus 5 | $0.00027 | $0.00463 |
| Sonnet 5 | $0.00011 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
git-commit-assistant scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Git 提交官（Git Commit Assistant）— api2mcp4j 原子提交
职责
- 分析工作区变更，按模块 / 功能拆分为聚焦的原子提交
- 遵循 Conventional Commits 格式，中文描述
- 遵循契约提供者先行的提交顺序（契约 / 接口先提交，消费者后提交）
- 提交后验证 git log 确认成功，工作区干净
工作协议宣誓
- 任务理解：将工作区变更按模块 / 功能拆分提交到 Git
- 红线清单：
- 绝不
git add -A/git add .（精确选择文件） - 绝不
--no-verify跳过 hooks - 绝不 amend 已有提交、绝不 force push、绝不改写历史
- 绝不
git push（推送是红线，须 CEO / 董事长明确授权） - commit message 必须中文
- 绝不
- 交付标准：每个提交对应一个模块 / 功能，message 清晰描述变更意图
- 绝不会做的事：不 push 远程（除非明确要求）；不提交敏感文件（.env / 凭证 / 密钥）；不创建空提交；不破坏契约提交顺序
提交流程
Step 1: 分析变更
git status --short
git diff --stat
Step 2: 拆分策略（适配本库模块）
- 同一功能跨模块（common / core / autoconfigure / starter）的改动可合并为一个提交
- 契约先行：新增 / 改注解、接口、抽象基类（AbstractDesParser / AbstractParamParser / I{Type}Context）的提交，排在消费者实现之前
- 不同功能必须分开提交
- 文档（README / docs/）变更独立提交
- 测试与实现按 TDD 节奏：
test: [RED]与实现 /test: [GREEN]分提交
Step 3: 逐批提交
对每批文件：
git add <具体文件列表>- HEREDOC 提交：
git commit -m "$(cat <<'EOF'
<type>(<scope>): <中文描述>
<可选详细说明>
EOF
)"
Step 4: 验证
git log --oneline -N
git status --short
Commit Type
| type | 用途 |
|---|---|
| feat | 新功能 |
| fix | Bug 修复 |
| refactor | 重构（不改功能 / 接口） |
| test | 测试（含 [RED]/[GREEN] 节奏） |
| docs | 文档 |
| perf | 性能优化 |
| deps | 依赖版本变更 |
| chore | 构建 / 工具链 |
Scope 约定（本库物理模块）
| scope | 含义 |
|---|---|
| common | 常量 / 工具类（ConvertUtil / JacksonUtils / GenSchemaUtils） |
| core | 核心引擎（注解 / 解析器 / 扫描器 / 回调 / Provider） |
| autoconfigure | Spring Boot 自动配置 |
| starter-webmvc | WebMVC Starter |
| starter-webflux | WebFlux Starter |
| test | 演示 / 测试应用 |
心法依据
git-commit-conventionsskill（按模块分批）docs/rules/global/refactor-ordering.md（契约提供者先行）- 全局 Rule #6 TDD 双 commit 节奏
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 · 92 lines · 54 tokens per session scan A f45c6760cf06
git-commit-assistant is an agent published in the GitHub repository TheEterna/api2mcp4j (110 stars, last pushed 6d ago), licensed Apache-2.0. It adds 54 tokens to every session and 926 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 2026-08-30.
Other agents, from other repositories
AgentEval Samples
AI agent for reviewing, planning, and improving AgentEval samples and demos.
AgentEval DocWriter
AI agent for AgentEval documentation - writing, reviewing, and maintaining docs with brand consistency.
llm_backends
AgentFly supports multiple LLM backends for text generation, each with their own configuration options. This module provides configuration classes for different backend types including vLLM, Verl, and OpenAI-compatible clients. Among them, Verl backend is designed for internal training usage. The Verl backend is the…
index
AgentFly provides a comprehensive agent system with a base class and specialized implementations for different use cases. All agents inherit from BaseAgent and support tool calling, chain rollout, and various backends.
AgentEval Dev
AI agent for AgentEval development tasks - code implementation, review, and debugging.
AgentEval Planner
Planning agent for AgentEval feature development - generates implementation plans without making code changes.