ccc Semantic Code Search
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
项目代码库上下文管理。通读项目生成参考文档(scan),或加载文档辅助开发(dev). An agent skill from kingxiaozhe/cm-workflow.
$ npx skills add kingxiaozhe/cm-workflow --skill codebase-context -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kingxiaozhe/cm-workflow codebase-context --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codebase-context .claude/skills/codebase-context && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "codebase-context" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/codebase-context into .claude/skills/codebase-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-context", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/codebase-contextType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kingxiaozhe/cm-workflow --skill codebase-context -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kingxiaozhe/cm-workflow codebase-context --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/codebase-context .agents/skills/codebase-context && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "codebase-context" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/codebase-context into .agents/skills/codebase-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-context", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kingxiaozhe/cm-workflow --skill codebase-context -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kingxiaozhe/cm-workflow codebase-context --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/codebase-context .cursor/skills/codebase-context && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "codebase-context" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/codebase-context into .cursor/skills/codebase-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-context", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kingxiaozhe/cm-workflow.git --path skills/codebase-context--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kingxiaozhe/cm-workflow --skill codebase-context -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kingxiaozhe/cm-workflow codebase-context --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/codebase-context .gemini/skills/codebase-context && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "codebase-context" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/codebase-context into .gemini/skills/codebase-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-context", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kingxiaozhe/cm-workflow codebase-contextInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kingxiaozhe/cm-workflow --skill codebase-context -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/codebase-context .github/skills/codebase-context && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "codebase-context" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/codebase-context into .github/skills/codebase-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-context", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kingxiaozhe/cm-workflow --skill codebase-context -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kingxiaozhe/cm-workflow codebase-context --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/codebase-context .opencode/skills/codebase-context && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "codebase-context" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/codebase-context into .opencode/skills/codebase-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-context", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
codebase-context项目代码库上下文管理。通读项目生成参考文档(scan),或加载文档辅助开发(dev). An agent skill from kingxiaozhe/cm-workflow.
Codebase Context is an agent skill from kingxiaozhe/cm-workflow. 项目代码库上下文管理。通读项目生成参考文档(scan),或加载文档辅助开发(dev)。
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/writeback.md`).
It sits in Agent Workflows, covering Codebase knowledge for agents. The repository describes itself as: Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 971c231. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
ENV_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Codebase Context loads about 2.8k tokens when it runs, and up to ~4.8k if it reads all its reference files. Until then it costs about 15 tokens; SKILL.md has 545 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from kingxiaozhe/cm-workflow at commit 971c231, republished under its MIT licence (© kingxiaozhe). 545 words, ~2,826 tokens.
.claude/skills/codebase-context/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.这是一份写给 AI 执行的 SOP。目的:把"每次开发前重读整个代码库"这个昂贵动作一次性固化成结构化文档缓存,后续开发直接加载文档当上下文。
调用格式:/codebase-context <mode> [project-name] [--full]
mode:scan → 进入 scan 模式dev → 进入 dev 模式用法: /codebase-context <scan|dev> [project-name] [--full] 并终止-- 开头参数为 project-name:basename "$PWD",取当前工作目录最后一段路径名作为 project-name--full 参数:DOC_DIR = {PROJECT_ROOT}/docs/codebase-context/(存于项目工程内,随 git 提交、团队共享、换机不丢)PROJECT_ROOT = 当前工作目录全部存于 DOC_DIR 下,文件名固定,不得增删改名:
| 文件 | 内容 |
|---|---|
| 00-index.md | 索引与快速导航 |
| 01-overview.md | 项目概述与技术栈 |
| 02-directory.md | 目录结构 |
| 03-architecture.md | 架构设计与模块关系 |
| 04-api-routes.md | API 接口汇总 |
| 05-data-models.md | 数据模型与类型 |
| 06-core-modules.md | 核心模块(组件/Hooks/Store) |
| 07-business-logic.md | 关键业务逻辑 |
| 08-conventions.md | 编码规范与约定 |
| 09-changelog.md | 文档变更记录 |
| .scan-meta.json | `{"lastScanTime":"UTC时间","scanType":"full |
*/package.json、*/*/package.json(及 Cargo.toml/go.mod 等)——若当前目录自身不是单一项目根(无 src/),而多个子目录各含项目描述文件 → 列出候选子项目并让用户选定(或用 project-name 参数匹配子目录名);选定后 PROJECT_ROOT/DOC_DIR 重设为该子项目根。把多个不相干项目扫进一张地图,查重与波及面全部失真——脏地图比没地图更危险(实跑教训:4 项目混装仓库靠人肉 cd 才扫对)--full 参数 → 全量扫描.scan-meta.json 且 无 --full → 增量扫描.scan-meta.json → 全量扫描(元数据缺失视同首扫)mkdir -p {DOC_DIR} 创建目录规模档位(先数源码文件再动手):≤200 个源文件 → 按下述七轮正常执行;>200 个 → 第 4/5/6 轮不逐个 Read,改用 Grep 收 export 签名清单入表(函数名/类型名/位置),精读仍限抽样 3–5 个最复杂文件;>500 个 → 同上,并提示用户"项目较大,建议按模块分次 scan(cd 到子模块根分别执行)"。防止扫到一半上下文耗尽——成本花了、地图没产出是最差结果。
第 1 轮 项目元信息:用 Read 读取 package.json、README.md;用 Glob 匹配构建配置 vite.config.*、webpack.config.*、tsconfig.json、next.config.*、.env.example,逐个 Read。提取:项目名/版本/依赖清单/脚本命令/构建工具/环境变量键名。
第 2 轮 目录结构:用 Bash 执行 ls -R(或用 Glob src/*/* 展开 src 两层)。识别 pages/、components/、api/、store/、hooks/、utils/、types/ 等目录及其职责。
第 3 轮 入口与路由:用 Glob 定位 main.*、index.*、App.*、router/、routes/,逐个 Read;用 Grep 搜索全局 store 初始化与全局 service 入口。提取:启动链路、路由表、全局状态挂载点。
第 4 轮 API 接口层:用 Glob 匹配 **/api/** 与 **/services/**,逐个 Read。提取每个接口函数的:函数名 / HTTP 方法 / URL / 参数 / 返回类型 / 定义位置(文件:函数)。
第 5 轮 数据模型与类型:用 Glob 匹配 **/types/**、**/models/**、**/interfaces/**、**/enums/**,逐个 Read。提取:实体 / 枚举 / DTO 及各自定义位置。
第 6 轮 核心模块:用 Glob 展开 components/(区分公共组件 vs 业务组件)、hooks/、store/,逐个 Read 提取签名与职责;再用 Grep 按 import 次数与文件行数抽样精读 3–5 个最复杂的页面/组件(Read 全文),提取其状态、关键流程。
第 7 轮 规范与工具:用 Glob 匹配 **/constants/**、**/config/**、**/utils/** 及 .eslintrc*、.prettierrc*,逐个 Read。提取:常量清单 / 工具函数清单 / 可推断的代码规范。
依据下方【文档模板】,按 00 → 09 顺序逐份用 Write 生成 10 份文档,照模板填空。
date -u +"%Y-%m-%dT%H:%M:%SZ" 取 UTC 时间.scan-meta.json:{"lastScanTime":"{UTC}","scanType":"full","projectRoot":"{PROJECT_ROOT}"}✅ codebase-context 全量扫描完成 — {project-name}
📁 文档目录: {DOC_DIR}
📄 生成文档: 10 份(00-index ~ 09-changelog)
📊 扫描统计: 接口 {N} 个 | 类型 {N} 个 | 组件 {N} 个 | Hooks {N} 个 | 精读页面 {N} 个
▶ 开发时执行: /codebase-context dev {project-name}.scan-meta.json,取 lastScanTime 与 projectRootfind {projectRoot}/src -type f \( -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.jsx" -o -name "*.vue" -o -name "*.json" \) -newer {DOC_DIR}/.scan-meta.json02-directory.md 记录的文件清单对比,推断新增文件(结果里有、文档里无)与删除文件(文档里有、磁盘上无——用 Bash test -f 验证)按下表将每个变更文件路径映射到扫描轮次,只重跑受影响的轮次:
| 文件路径模式 | 扫描轮次 | 需更新文档 |
|---|---|---|
| package.json / README / vite・webpack・tsconfig・next 配置 / .env.example | 第 1 轮 | 01-overview |
| 目录新增/删除(任何路径层级变化) | 第 2 轮 | 02-directory |
| main.* / index.* / App.* / router/ / routes/ / 全局 store・service 入口 | 第 3 轮 | 03-architecture |
| **/api/** 、 **/services/** | 第 4 轮 | 04-api-routes |
| **/types/** 、 **/models/** 、 **/interfaces/** 、 **/enums/** | 第 5 轮 | 05-data-models |
| components/ 、 hooks/ 、 store/ | 第 6 轮 | 06-core-modules |
| pages/ 下的页面文件 | 第 6 轮 | 06-core-modules、07-business-logic |
| **/constants/** 、 **/config/** 、 **/utils/** 、 eslint/prettier 配置 | 第 7 轮 | 08-conventions |
| (任何变更,无条件) | — | 09-changelog、00-index(日期) |
00-index.md 的"最后更新"日期09-changelog.md 追加本次条目(日期/类型 incremental/变更摘要/涉及文档).scan-meta.json(scanType: "incremental");否则保留原元数据,在索引/日志标明本次局部核实范围,不用新时间掩盖未知区域✅ codebase-context 增量扫描完成 — {project-name}
🔍 变更检测: 新增 {N} 个 | 修改 {N} 个 | 删除 {N} 个
📄 已更新文档: {文档列表,如 04-api-routes、05-data-models、09-changelog、00-index}references/writeback.md 先查项目指定地图,否则从代码定向建立本次链路;任务目标缺失时先补问目标,不盲扫全仓references/writeback.md 核实地图与当前代码;过期、错误或缺少相关链路时定向补查,确认本次影响范围后才能改业务代码。授权范围内审前回写,不强制全量 scan📚 已加载 {project-name} 参考文档({实际数量} 份,覆盖 {相关模块},最后更新 {日期})
📌 项目概要: {已核实的一句话或待核实}开发过程中强制遵循:
08-conventions.md 的规范与约定04-api-routes.md——已有接口直接复用,不重复造05-data-models.md——已有类型直接引用,不重复定义06-core-modules.md——已有组件/Hook 直接复用03-architecture.md 的分层与模块归属开发结束、独立审查前必须按 业务地图增量回写 评估并更新受影响章节; 无需更新时说明依据。需求开发和缺陷修复复用同一判据,不重复扫描或在批准后回写。
生成时照模板填空;某章节在本项目无对应内容时保留标题并填"本项目未发现此类文件"。
# {project-name} — 代码库参考文档索引
- 最后更新: {YYYY-MM-DD HH:MM UTC}
- 扫描类型: {full | incremental}
- 项目根: {projectRoot}
## 文档导航
| 文档 | 内容 | 什么时候看 |
| ---- | ---- | ---- |
| 01-overview | 项目概述与技术栈 | 初次接触项目 |
| 02-directory | 目录结构 | 找文件放哪/在哪 |
| 03-architecture | 架构与模块关系 | 新代码归属、理解依赖方向 |
| 04-api-routes | API 接口汇总 | 调接口前查重 |
| 05-data-models | 数据模型与类型 | 定义类型前查重 |
| 06-core-modules | 组件/Hooks/Store | 写组件前查复用 |
| 07-business-logic | 关键业务逻辑 | 改业务流程前看线路 |
| 08-conventions | 编码规范与约定 | 动手写代码前 |
| 09-changelog | 文档变更记录 | 追溯文档演进 |
## 快速定位
| 我想找… | 去 |
| ---- | ---- |
| 某个接口怎么调 | 04-api-routes |
| 某个字段的类型定义 | 05-data-models |
| 有没有现成组件/Hook | 06-core-modules |
| 某业务流程的完整线路 | 07-business-logic |
| 命名/风格规矩 | 08-conventions |# 项目概述与技术栈
## 项目定位
{一句话说明这个项目是什么、给谁用、解决什么问题}
## 技术栈
| 层 | 技术 | 版本 |
| ---- | ---- | ---- |
| 语言 | {TypeScript/…} | {x.y} |
| 框架 | {React/Vue/…} | {x.y} |
| 构建 | {Vite/Webpack/…} | {x.y} |
| 状态管理 | {…} | {x.y} |
| 其他关键依赖 | {…} | {x.y} |
## 脚本命令
| 命令 | 作用 |
| ---- | ---- |
| `npm run dev` | {…} |
| `npm run build` | {…} |
| `npm run test` | {…} |
## 环境变量(仅键名与用途,不含值)
| 键 | 用途 | 来源 |
| ---- | ---- | ---- |
| {ENV_KEY} | {…} | .env.example |# 目录结构
## 目录树(src 两层)
```text
src/
├── pages/ # {职责}
├── components/ # {职责}
├── api/ # {职责}
├── store/ # {职责}
├── hooks/ # {职责}
├── utils/ # {职责}
└── types/ # {职责}
```
## 目录职责
| 目录 | 职责 | 典型文件 |
| ---- | ---- | ---- |
| {src/pages} | {…} | {…} |
## 文件清单(供增量扫描对比新增/删除)
| 文件 | 所属轮次 |
| ---- | ---- |
| {src/api/user.ts} | 4 |# 架构设计与模块关系
## 分层结构
```text
{页面层 pages}
↓ 调用
{逻辑层 hooks / store}
↓ 调用
{服务层 api / services}
↓ 请求
{后端 / 云函数}
```
## 启动链路
{main.* → App.* → 路由挂载 → 全局 store 初始化,逐步说明,每步带 文件:位置}
## 路由表
| 路径 | 页面 | 定义位置 |
| ---- | ---- | ---- |
| {/home} | {pages/home} | {router/index.ts} |
## 模块依赖关系
| 模块 | 依赖谁 | 被谁依赖 |
| ---- | ---- | ---- |
| {store/user} | {api/user} | {pages/*, hooks/useAuth} |# API 接口汇总
## {模块名,如 user}
| 函数名 | 方法 | URL | 参数 | 返回类型 | 定义位置 |
| ---- | ---- | ---- | ---- | ---- | ---- |
| {getUser} | GET | {/api/user/:id} | {id: string} | {User} | {src/api/user.ts} |
(按模块分节重复上表;无 api/ 与 services/ 目录时填"本项目未发现此类文件")# 数据模型与类型
## 实体
| 名称 | 字段摘要 | 定义位置 | 主要使用方 |
| ---- | ---- | ---- | ---- |
| {User} | {id, name, role…} | {src/types/user.ts} | {api/user, store/user} |
## 枚举
| 名称 | 取值 | 定义位置 |
| ---- | ---- | ---- |
| {OrderStatus} | {pending/paid/closed} | {src/types/order.ts} |
## DTO / 请求响应类型
| 名称 | 用于接口 | 定义位置 |
| ---- | ---- | ---- |
| {CreateOrderReq} | {POST /api/order} | {src/types/dto.ts} |# 核心模块
## 公共组件
| 组件 | Props 摘要 | 定义位置 | 复用场景 |
| ---- | ---- | ---- | ---- |
| {Button} | {type, onClick…} | {src/components/common/} | {全局} |
## 业务组件
| 组件 | 职责 | 定义位置 | 所属业务 |
| ---- | ---- | ---- | ---- |
## Hooks
| 名称 | 输入 | 输出 | 定义位置 |
| ---- | ---- | ---- | ---- |
| {useAuth} | {—} | {user, login, logout} | {src/hooks/useAuth.ts} |
## Store
| 模块 | state 摘要 | 主要 actions | 定义位置 |
| ---- | ---- | ---- | ---- |
## 复杂页面精读(3–5 个)
### {页面名}({文件路径})
- 职责: {…}
- 关键状态: {…}
- 关键流程: {步骤 1 → 步骤 2 → …,每步带函数名}# 关键业务逻辑
## {业务线名,如:下单}
**线路**:{页面 pages/order} → {hook useOrder} → {api createOrder} → {POST /api/order} → {模型 Order}
(每个环节标注 文件:函数)
**关键规则**:
- {规则 1,如:金额用分存储,展示层才转元 —— src/utils/money.ts}
- {规则 2}
**边界与注意**:
- {已知坑/特殊分支/兼容逻辑,带位置}
(按业务线重复本节)# 编码规范与约定
## 命名
| 对象 | 规则 | 示例 |
| ---- | ---- | ---- |
| 组件文件 | {PascalCase} | {UserCard.tsx} |
| hooks | {use 前缀} | {useAuth} |
## 代码风格(自 ESLint/Prettier 推断)
- {缩进/引号/分号/import 排序 等要点}
## 常量
| 常量 | 值/含义 | 定义位置 |
| ---- | ---- | ---- |
## 工具函数
| 函数 | 用途 | 定义位置 |
| ---- | ---- | ---- |
## 其他约定
- {错误处理方式/请求封装规则/目录放置约定}# 文档变更记录
| 日期(UTC) | 类型 | 变更摘要 | 涉及文档 |
| ---- | ---- | ---- | ---- |
| {2026-07-14T08:00Z} | full | 首次全量扫描 | 全部 10 份 |
| {…} | incremental | {新增 2 接口/修改 1 类型} | {04、05} |
| {…} | dev回写 | {开发 xx 功能后回写} | {04、06、07} |⚠ 当前目录未发现 package.json,请确认 {PROJECT_ROOT} 是正确的项目目录(回复继续则按非 npm 项目扫描),等用户确认后再继续。api/):跳过该轮,在对应文档的相应章节标注"本项目未发现此类文件",不报错不中断。(大文件,仅提取签名)。references/writeback.md 定向核实/补齐;证据不足暂停相关修改,不猜测,不强制全量 scan。© kingxiaozhe, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in skills/codebase-context of kingxiaozhe/cm-workflow.
Open the folder on GitHubat commit 971c231
Codebase Context next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Codebase Context this skillkingxiaozhe/cm-workflow | 104 | — | ~2.8k | Automated safety check: Pass | MIT | |
| ccc Semantic Code Searchcocoindex-io/cocoindex-code | 2.7k | — | ~938 | Automated safety check: Pass | Apache-2.0 | |
| Context Engineeringabashev/vfs-s3 | 106 | 9 repos | ~2.6k | Automated safety check: Notes | Apache-2.0 | |
| Repomix Codebase Packeryamadashy/repomix | 29k | — | ~1.3k | Automated safety check: Notes | MIT | |
| Codebase Handbook BuilderRuhan-Wang/Harness_Handbook | 331 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| CodemapJordanCoin/codemap | 704 | — | ~1.8k | Automated safety check: Pass | MIT |
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
abashev/vfs-s3
Optimizes agent context setup. An agent skill from abashev/vfs-s3.
yamadashy/repomix
Packs a local directory or remote GitHub repository into one AI-friendly file with Repomix, then searches it to explore structure, find patterns and count tokens.
Ruhan-Wang/Harness_Handbook
Generates, refreshes, validates and uses a compact handbook that maps where a change touches in a repository, using the active Codex session and no external LLM API.
JordanCoin/codemap
Gives an agent a quick map of a codebase's structure, dependencies, changes and handoffs, and tunes per-project config so the output stays code-first.
sopaco/deepwiki-rs
A skill your agent uses when an agent needs source code from the local repomix index under .terrain/agent/repomix.md (not committed; regenerate via Terrain scan).
kingxiaozhe/cm-workflow
用户明确说“规格已确认,开始实现”或要求按已审批 CM specs 开发时使用。新任务默认由 JS workflow 驱动 N1-N8,完成开发、独立审查、QA 与文档同步;模糊点子、未审规格和单独一句“继续”不能触发编码批准。
kingxiaozhe/cm-workflow
用户说“检查工作流是否安装正确”“为什么找不到 cm 命令”时使用。默认查询 npm 稳定版,有新版自动升级已管理的 CM 安装,再检查插件、核心 Skills、兼容包装与模板引用;不测试或修改业务代码。
kingxiaozhe/cm-workflow
用户说“修复这个可复现 bug”或要求根据失败报告修代码时使用。执行红灯测试、根因定位、最小修复、独立审查和回归;尚未确认的问题先用 cm-test,新功能和架构重设计转交 cm-prd。
kingxiaozhe/cm-workflow
用户说“我有个点子”“帮我梳理产品”或需要先聊清目标时使用。通过逐题访谈整理为可交给 cm-prd 的 PRD;已有明确需求文档时改用 cm-prd,不写代码、不拆开发任务。
kingxiaozhe/cm-workflow
用户说“第一次接管这个项目”“分析仓库并生成项目规则”时使用。分析已有代码并生成 Codex AGENTS.md 与 CM/Claude 兼容规则;仅适用于非空存量项目,不创建脚手架、不承接普通代码修改。
kingxiaozhe/cm-workflow
微信小程序开发工程师 Skill,执行小程序开发任务,自动适配项目技术栈(原生小程序/Taro/uni-app 等),支持 Figma/Stitch 设计稿还原与云开发
Categories
项目代码库上下文管理。通读项目生成参考文档(scan),或加载文档辅助开发(dev). An agent skill from kingxiaozhe/cm-workflow. Codebase Context is an agent skill from kingxiaozhe/cm-workflow.
Codebase Context fits situations like: tasks that involve Codebase knowledge for agents.
Run `npx skills add kingxiaozhe/cm-workflow --skill codebase-context -a claude-code`. Or copy the skill folder (skills/codebase-context in kingxiaozhe/cm-workflow) into .claude/skills/codebase-context in your project. Claude Code loads it when a task matches its description.
Run `npx skills add kingxiaozhe/cm-workflow --skill codebase-context -a codex`. Or copy the skill folder (skills/codebase-context in kingxiaozhe/cm-workflow) into .agents/skills/codebase-context in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kingxiaozhe/cm-workflow --skill codebase-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codebase-context, .gemini/skills/codebase-context, .github/skills/codebase-context and .opencode/skills/codebase-context in your project.
Going by SKILL.md and its folder, Codebase Context needs credentials named ENV_KEY.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Codebase Context is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Codebase Context: ccc Semantic Code Search (cocoindex-io/cocoindex-code, 2.7k stars), Context Engineering (abashev/vfs-s3, 106 stars), Repomix Codebase Packer (yamadashy/repomix, 29k stars) and Codebase Handbook Builder (Ruhan-Wang/Harness_Handbook, 331 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
kingxiaozhe (a GitHub user) maintains it in kingxiaozhe/cm-workflow, which has 104 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 6, 2026.
Source: kingxiaozhe/cm-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.