菜单
Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns. Use when creating Claude Code extensions or configuring Claude Code features.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/modu-ai/moai-adk --skill moai-foundation-cc命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | moai-foundation-cc |
| description | Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns. Use when creating Claude Code extensions or configuring Claude Code features. |
| when_to_use | Use for Claude Code authoring and extension: Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, orchestration, and delegation/agent-pattern authoring. |
| license | Apache-2.0 |
| compatibility | Designed for Claude Code |
| allowed-tools | Read, Write, Edit, Grep, Glob |
| user-invocable | false |
| metadata | {"version":"5.0.0","category":"foundation","status":"active","updated":"2026-01-11","modularized":"false","tags":"foundation, claude-code, skills, sub-agents, plugins, slash-commands, hooks, memory, settings, sandboxing, headless, agent-patterns","aliases":"moai-foundation-cc"} |
| progressive_disclosure | {"enabled":true,"level1_tokens":100,"level2_tokens":5000} |
Comprehensive reference for Claude Code Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns.
Core Features:
Configuration:
Advanced Features:
Skills: Model-invoked extensions in ~/.claude/skills/ (personal) or .claude/skills/ (project). Three-level progressive disclosure. Max 500 lines.
Sub-agents: Specialized assistants via Agent(subagent_type="..."). Context window follows the session model (Sonnet 5 = 1M native on the Anthropic API; Haiku / gateway / older models = 200K — CC 2.1.197). Nesting: a subagent can spawn nested subagents only when its tools list includes Agent (CC 2.1.172); MoAI retained agents omit Agent, so they do not nest. To create or manage subagents, ask Claude or edit .claude/agents/ directly — the /agents wizard was removed in CC 2.1.198 (the official sub-agents doc still documented a /agents tabbed interface as of 2026-07-03; doc lag — verify in a live 2.1.198 session).
Plugins: Reusable bundles in .claude-plugin/plugin.json. Include commands, agents, skills, hooks, MCP servers.
Commands: User-invoked via /command. Parameters: $ARGUMENTS, $1, $2. File refs: @file.
Hooks: Events in settings.json. PreToolUse, PostToolUse, SessionStart, SessionEnd, PreCompact, Notification.
Memory: CLAUDE.md files + .claude/rules/*.md. Enterprise to Project to User hierarchy. @import syntax.
Settings: 6-level hierarchy. Managed to file-managed to CLI to local to shared to user.
Sandboxing: OS-level isolation. Filesystem and network restrictions. Auto-allow safe operations.
Headless: -p flag for non-interactive. --allowedTools, --json-schema, --agents for automation.
Level 1 (Metadata): Name and description loaded at startup, approximately 100 tokens per Skill
Level 2 (Instructions): SKILL.md body loaded when triggered, under 5K tokens recommended
Level 3 (Resources): Additional files loaded on demand, effectively unlimited
Create a SKILL.md file with YAML frontmatter containing name in kebab-case and description explaining what it does and when to use it in third person. Maximum 1024 characters for description. After the frontmatter, include a heading with the skill name, a Quick Start section with brief instructions, and a Details section referencing REFERENCE.md for more information.
CC 2.1.198 CHANGELOG delta: The
/agentswizard was removed — per the CHANGELOG, "ask Claude to create or manage subagents, or edit.claude/agents/directly." The official sub-agents doc still documented a/agentstabbed interface as of 2026-07-03 (doc lag, or the removal covers only the creation wizard); verify in a live 2.1.198 session before relying on the flow below.
Type /agents, select Create New Agent, define purpose and tools, press e to edit prompt.
Create a markdown file with YAML frontmatter containing name, description explaining when to invoke (use PROACTIVELY for auto-delegation), tools as comma-separated list (Read, Write, Bash), and model specification (sonnet). After frontmatter, include the system prompt.
tools list includes Agent; MoAI retained agents omit Agent, so they do not nest)Create my-plugin directory with .claude-plugin/plugin.json, commands directory, agents directory, skills directory, hooks/hooks.json, and .mcp.json file.
Create a JSON object with name, description explaining plugin purpose, version as 1.0.0, and author object containing name field.
Use /plugin install owner/repo to install from GitHub. Use /plugin validate . to validate current directory. Use /plugin enable plugin-name to enable a plugin.
Initializer agent: Sets up environment, feature registry, progress docs
Executor agent: Works single features, updates registry, maintains progress
See reference/advanced-agent-patterns.md for details.
Lead agent: Decomposes tasks, spawns workers, synthesizes results
Worker agents: Execute focused tasks, return condensed summaries
When using Explore agent or direct exploration tools (Grep, Glob, Read), apply these optimizations to prevent performance bottlenecks with GLM models:
AST-Grep Priority
moai ast-grep to scan, moai ast-edit to rewrite matchessg -p 'class $X extends Service' --lang python is faster than grep -r "class.*extends.*Service"Search Scope Limitation
path parameter to limit search scopeGrep(pattern="func ", path="internal/core/") instead of Grep(pattern="async def")File Pattern Specificity
Glob(pattern="internal/core/*.go") instead of Glob(pattern="src/**/*.py")Parallel Processing
Phase 1 Explore: Read files, understand structure, map dependencies
Phase 2 Plan: Use think prompts, outline approach, define criteria
Phase 3 Code: Implement iteratively, verify each step, handle edges
Phase 4 Commit: Descriptive messages, logical groupings, clean history
For detailed patterns and working examples, see the reference directory.
Version History:
| Rationalization | Reality |
|---|---|
| "I will use Bash sed instead of Edit, it is faster" | Edit is the preferred tool for accuracy and review. Bash sed errors are silent and hard to trace. |
| "This hook does not need a timeout, it finishes quickly" | Hooks without timeouts can hang the entire session. Always set an explicit timeout. |
| "I can put all logic in CLAUDE.md, rules are overkill" | CLAUDE.md has a 40K character limit. Rules load conditionally and scale without bloating the prompt. |
| "Settings.json changes are low risk" | Incorrect settings.json breaks hooks, permissions, and model routing. Validate the JSON after every edit. |
| "I will skip progressive disclosure, all content is needed" | Loading 5K tokens for every skill wastes 67% of context. Level 1 metadata is sufficient for routing. |
| "This skill does not need allowed-tools, Claude will figure it out" | Missing allowed-tools means the skill silently inherits all tools. Explicit is safer than implicit. |
Provenance (frontmatter CSV-format drift): space-separated allowed-tools silently breaks tool permissions (CONST-V3R5-038) — observed recurrence, provenance pending in memory.
Fast defaults — always confirm against the cited body section for non-trivial decisions.
ToolSearch preload first (<- §Documentation Index / sub-agents).allowed-tools, default to a comma-separated string, never space-separated (<- §Red Flags).