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/weiyi88/cc-code/initnpx skills add weiyi88/cc-code --skill initgit clone --depth 1 https://github.com/weiyi88/cc-codeWhat 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 | $0.00087 | $0.06537 |
| Opus 5 | $0.00044 | $0.03268 |
| Sonnet 5 | $0.00017 | $0.01307 |
| Haiku 4.5 | $0.00009 | $0.00654 |
Grade A, and why
init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cc-code:init — 项目场域初始化 / 版本升级
执行 cc-code 工作流的入场协议。同时负责把旧版场域升级到当前插件规范。
第 1 步：三轨判定
扫描当前工作区，由 .cc_code/.cc_code_version 版本戳分流：
| 探测条件 | 轨道 | 行为 |
|---|---|---|
无 active/Agent.md，且存在 src/ / package.json / go.mod 等旧代码或根目录已有 CLAUDE.md |
Track A 旧项目接管 | 扫描技术栈+断层，与用户多轮补 PRD，预填 project.md；执行第 2A 步分拆旧 CLAUDE.md |
无 active/Agent.md，全空目录 |
Track B 新项目 | 直接搭场域 + 盖版本戳，切 PM 角色等待需求 |
有 active/Agent.md，且版本戳 == 插件版本 |
Track C 已最新 | 跳过脚手架，搬散落物 + ⭐跑 D4 骨架格式体检（0.9.0 起），再进第 3 步 |
有 active/Agent.md，但版本戳缺失或更旧 |
Track D ⭐升级迁移 | 脚本做 D1 归档 + D2 清点，AI 按第 2C 步做 D3~D7 |
⭐ 版本戳是升级的唯一判据。戳未盖 = 迁移未完成，下次
init仍判 Track D，不会把半成品误认为已完成。
⚠️ Track C 也必须体检（0.9.0 修正）：0.8.0 及以前 Track C「仅搬散落物」，零格式体检。一旦某文件盖戳时格式没归位，之后每次
init都判 Track C 跳过检查 → 旧格式永久留存，永无自愈机会。 Track C 体检为轻量版：只检 D4 骨架清单，发现缺失即报主人并给归位建议，不自动改写（已最新的项目不该被 init 悄悄动内容）。
第 2 步：执行脚手架
bash "$CLAUDE_PLUGIN_ROOT/scripts/init.sh" "$(pwd)"
脚本按三轨自动分流。Track B/A 生成 active/ backup/ docs/{plans,qa}/ images/ scripts/ references/ + 8 个 active 模板骨架（按 L0~L4 分层：Agent status / prd / ux / project data api / gates）+ references/INDEX.md 索引 + 根目录 CLAUDE.md 入口引导 + .cc_code/README.md 使用手册（每次 init 无条件刷新到最新版）+ 版本戳。Track C 搬散落物 + 刷新手册 + AI 跑 D4 轻量骨架体检。Track D 见第 2C 步（脚本 D2 阶段自动补建缺失的 references/）。
子命令（供 AI 在升级阶段调用）：
| 命令 | 用途 |
|---|---|
bash init.sh --relocate <相对路径...> |
冗余归位：mv 进 backup/YYYY-MM/superseded/。零删除，且拒绝归位规范 8 文件 |
bash init.sh --stamp |
盖版本戳。仅在 D5 校验门全过后才允许调用 |
散落物迁移采用**「默认不动」判定链**（任一命中即跳过）：① 保护白名单 → ② git 已追踪（最强判据：人 commit 过 = 不是垃圾）→ ③ 被 package.json/CI/Dockerfile/源码引用 → 三关全过才做正向识别（名字像临时物/过程报告才搬）→ ④ 都不匹配则原地保留并记入 backup/YYYY-MM/needs_review.md 交人工判断。搬走的记入 migration_manifest.md。同时把 .cc_code/backup/ 追加进根 .gitignore。
⚠️ 判定链宁可漏搬也绝不误杀 ——
setup.py/manage.py/conftest.py/AGENTS.md/build.sh/logo.png这类项目基建必须原地不动。
CLAUDE.md 处理（init.sh 自动完成，机械活）：
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 · 290 lines · 87 tokens per session scan A 86946e6d2b30
init is a skill published in the GitHub repository weiyi88/cc-code (5 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session and 6,537 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
state-machine
Task lifecycle state transitions with validation gates. Defines states, triggers, and required proofs.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
mutation-testing
Mutation testing patterns for verifying test effectiveness. Use when analyzing branch code to find weak or missing tests.
planning
Planning work in small, known-good increments. Use when starting significant work or breaking down complex tasks.
fastapi-scaffold
Scaffold a new FastAPI project with standard structure, Pydantic models, dependency injection, and optional MCP/OAuth integration. Use when starting a new FastAPI service or adding a new API module to an existing project.
testing
Testing patterns for behavior-driven tests. Use when writing tests or test factories.