Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
中文简介正在准备中。当前显示原文说明。
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Generate a custom agent file based on requirements.
Usage: /agent-template [agent-name] [purpose]
| Purpose | Template | Tools | Color | Model |
|---|---|---|---|---|
| Review/Audit | Reviewer | Read, Grep, Glob, Bash | yellow | inherit |
| Generate/Create | Generator | Read, Write, Grep, Glob | cyan | inherit |
| Fix/Modify | Fixer | Read, Write, Edit, Bash, Grep | red | inherit |
| Test/Validate | Tester | Read, Bash, Grep, Glob | green | inherit |
| Document | Documenter | Read, Write, Grep, Glob | cyan | inherit |
| Orchestrate | Orchestrator | Read, Write, Bash, Grep, Glob, Agent | cyan | haiku |
Gather Requirements
Select Template based on purpose
Generate File at .claude/agents/[name].md
Validate with /agent-check
---
name: agent-name # Required: lowercase, hyphenated, 3-50 chars
description: > # Required: 200-1000 chars recommended, include <example> blocks.
Use this agent PROACTIVELY when [triggering conditions]. Examples:
<example>
Context: [situation]
user: "[request]"
assistant: "[response]"
<commentary>[why this agent]</commentary>
</example>
color: cyan # Required by Director Mode convention (CI-enforced); optional per spec
model: inherit # Required by Director Mode convention (CI-enforced); optional per spec.
# Valid: fable, opus, sonnet, haiku, inherit, default, best, sonnet[1m],
# opus[1m] (or a full model ID). inherit recommended. NOT opusplan.
effort: medium # Optional: low, medium, high, xhigh, max
tools: # Optional: YAML list (omit = all tools)
- Read
- Write
- Edit
- Bash
- Grep
- Glob
- Agent
- WebFetch
- WebSearch
- TodoWrite
- NotebookEdit
disallowedTools: # Optional: explicit tool blocking
- NotebookEdit
maxTurns: 20 # Optional: max agentic turns before stopping (positive integer)
skills: # Optional: preloaded skill names (list)
- linked-skill
memory: project # Optional: one of user, project, local
background: false # Optional: run the agent in the background (boolean)
isolation: worktree # Optional: run the agent in an isolated git worktree
---
Not supported in filesystem/plugin agent frontmatter — do not emit these:
hooks, mcpServers, permissionMode (security restriction), and forkContext
(not an official field). Agents fork automatically when dispatched.
---
name: [name]
description: >
Use this agent PROACTIVELY when [triggering conditions]. Examples:
<example>
Context: [situation]
user: "[request]"
assistant: "[response]"
</example>
color: yellow
tools:
- Read
- Grep
- Glob
- Bash
model: inherit
skills:
- linked-skill
# maxTurns: 20
# memory: project
---
# [Name] Agent
## Activation
When to trigger
## Review Checklist
- [ ] Check items
## Output Format
Report structure
/agent-template security-scanner "scan code for vulnerabilities"
Output: Created .claude/agents/security-scanner.md
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
中文简介正在准备中。当前显示原文说明。
List all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.
中文简介正在准备中。当前显示原文说明。
TDD-based autonomous development loop with checkpoint recovery and observability changelog
中文简介正在准备中。当前显示原文说明。
View and manage the runtime changelog for observability
中文简介正在准备中。当前显示原文说明。
Track development session events in a daily markdown changelog, including file changes, test results, and key decisions.
中文简介正在准备中。当前显示原文说明。
Verify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks only when selected. Use after installation or when a native surface misbehaves.
中文简介正在准备中。当前显示原文说明。