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/shenjingnan/xiaozhi-client/commitnpx skills add shenjingnan/xiaozhi-client --skill commitgit clone --depth 1 https://github.com/shenjingnan/xiaozhi-clientWhat 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 | $0.00010 | $0.02823 |
| Opus 5 | $0.00005 | $0.01411 |
| Sonnet 5 | $0.00002 | $0.00565 |
| Haiku 4.5 | $0.00001 | $0.00282 |
Grade A, and why
commit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
我是 Git Commit 生成技能，专门为 xiaozhi-client 项目生成符合规范的、代码评审友好的 commit 信息，同时遵循务实开发理念。
技能使用原则
- 真实准确，但避免过度详细：基于实际代码改动生成信息，不虚构不存在的细节
- 评审友好优先，格式完美次之：让评审人快速理解改动比完美格式更重要
- 简单明确优于复杂说明：优先选择清晰直接的描述方式
- 务实开发指导：突出"为什么改"和"改了什么"两个核心问题
技能能力
1. 代码改动分析
核心能力：分析实际的代码改动，提取关键信息用于生成 commit 信息。
分析流程
# 1. 更新远程分支信息
git fetch origin
# 2. 获取主分支名称
MAIN_BRANCH=$(git symbolic-ref refs/remotes/origin/HEAD | sed 's@^refs/remotes/origin/@@')
# 3. 获取改动内容（优先检查未 add 的改动）
git diff --no-pager
git diff --cached --no-pager
# 4. 获取相对于主分支的改动
git diff --no-pager origin/$MAIN_BRANCH...HEAD
分析要点
- 改动范围：哪些文件、模块被修改
- 改动类型：新增功能、修复 bug、重构、文档更新等
- 影响分析：改动对现有功能的影响
- 验证方式：如何验证改动的正确性
2. Commit 类型判断
根据改动内容自动判断合适的 commit 类型。
Type 类型定义
feat：新增 featurefix：修复 bugdocs：仅仅修改了文档，比如 README、CHANGELOG、CONTRIBUTE 等等style：仅仅修改了空格、格式缩进、逗号等等，不改变代码逻辑refactor：代码重构，没有加新功能或者修复 bugperf：优化相关，比如提升性能、体验test：测试用例，包括单元测试、集成测试等chore：改变构建流程、或者增加依赖库、工具等revert：回滚到上一个版本
类型判断示例
// feat 判断标准
// - 新增文件
// - 新增公共方法
// - 新增配置选项
// - 新增 API 端点
// fix 判断标准
// - 修复 bug
// - 修复内存泄漏
// - 修复崩溃问题
// - 修复类型错误
// refactor 判断标准
// - 代码结构调整
// - 变量重命名
// - 代码提取/合并
// - 类型定义优化
// test 判断标准
// - 新增测试用例
// - 修复测试用例
// - 提高测试覆盖率
3. 分支名称生成
根据改动内容生成符合规范的分支名称。
分支命名规范
- 前缀类型：
feature/、bugfix/、docs/、test/、refactor/、chore/ - 格式要求：kebab-case 格式，简洁反映改动内容
- 长度限制：不超过 50 字符
分支命名示例
# 功能开发
feature/add-user-auth-api
feature/implement-websocket-adapter
feature/support-modelscope-integration
# Bug 修复
bugfix/fix-memory-leak
bugfix/fix-type-error-in-mcp-service
bugfix/fix-connection-timeout-issue
# 文档更新
docs/update-readme-installation
docs/add-mcp-protocol-guide
# 测试相关
test/add-unit-tests-for-connection-manager
test-improve-test-coverage
# 重构
refactor-simplify-mcp-manager
refactor-optimize-path-alias-system
4. Commit 信息生成
生成符合代码评审友好的 commit 信息。
Commit 信息结构
<type>(<scope>): <subject>
## 改动说明
- 为什么改：<改动动机和问题背景>
- 改了什么：<具体的改动内容>
- 影响范围：<受影响的模块和兼容性>
- 验证方式：<测试方法或验证点>
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.
- 2d ago First seen · 326 lines · 10 tokens per session scan A 5c423b6c7110
commit is a skill published in the GitHub repository shenjingnan/xiaozhi-client (337 stars, last pushed 7d ago), licensed MIT. It adds 10 tokens to every session and 2,823 once invoked, about $0.0001 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 skills, from other repositories
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
commits
Use this skill whenever the user asks to commit changes, write or fix a commit message, amend or rename a commit, or do a workflow that includes committing in the IntelliJ repository. This is a thin repo-specific overlay: use IntelliJ commit format, write full commit messages by default, and keep requested suffixes…
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…