cc-configs
CLAUDE.md0 starsChanged 6 months agoMITView on GitHub
所有 Claude Code 自定义配置(commands/skills/agents/rules)和配套 CLI 工具的单一 source of truth。
In this repository11 other files it gives its agents.
- debriefSkill
- dispatchSkill
- dwsSkill
- file-cleanupSkill
- html-figSkill
- pdf-decryptSkill
- retro-digestSkill
- sessionsSkill
- shipSkill
- spikeSkill
- verify-dataSkill
The file
Files
cc-configs — Claude Code 配置中心
所有 Claude Code 自定义配置(commands/skills/agents/rules)和配套 CLI 工具的单一 source of truth。
Quick Reference
| 项目 | 路径/值 |
| Commands | commands/ (30+ active,详见 ls commands/*.md) |
| Skills | skills/ (10+ auto-triggered,详见 ls skills/) |
| Agents | agents/ (2 agent definitions) |
| Rules | rules/ (command 规则文件) |
| 审计工具 | tools/harness/harness.py |
| Context 工具 | tools/context/context.py |
| 注册表 | harness.yaml |
常用命令
# 审计项目 CC 配置
python3 tools/harness/harness.py audit /path/to/project
# JSON 格式审计输出
python3 tools/harness/harness.py /path/to/project --json
# Context 监控
python3 tools/context/context.py monitor
# Context 健康检查
python3 tools/context/context.py health
# 运行测试
python3 -m pytest tools/harness/tests/ -v
python3 -m pytest tools/context/tests/ -v项目结构
commands/ # slash commands (symlink → ~/.claude/commands)
skills/ # auto-triggered skills (symlink → ~/.claude/skills)
agents/ # agent definitions (symlink → ~/.claude/agents)
rules/ # command 规则文件
tools/
harness/ # CC 配置审计工具
harness.py # CLI 入口
analyzers/ # 六维度分析 (D1-D6)
collectors/ # 数据采集
security/ # 安全扫描
reporters/ # 报告输出
tests/ # harness 测试
context/ # CC 上下文工程工具
context.py # CLI 入口
monitor/ # token 监控
snapshot/ # 上下文快照
health/ # 健康检查
hooks/ # CC hooks 安装
tests/ # context 测试
harness.yaml # skill 分发注册表 (symlink → ~/.claude/)
install.sh # symlink 安装脚本开发注意事项
- 纯 stdlib,不依赖任何第三方包
install.sh将 commands/skills/agents/harness.yaml symlink 到~/.claude/- tools/ 下的工具通过 commands 中的 slash command 调用,不直接 symlink
- 新增 command:在
commands/加.md文件即可 - 新增 skill:在
skills/加目录或.md文件
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

