# 启动指定 agent 会话
claude --agent code-reviewer

# 配合非交互模式
claude --agent code-reviewer -p "Review the auth module"

# 后台模式运行 agent
claude --bg --agent code-reviewer "investigate the flaky test"

# 插件 agent（多插件同名时用作用域前缀消歧义）
claude --agent my-plugin:security-reviewer

---
name: code-reviewer
description: Reviews code for quality and best practices. Use proactively after code changes.
tools: Read, Glob, Grep, Bash
model: sonnet
maxTurns: 50
permissionMode: acceptEdits
---

You are a senior code reviewer. When invoked:
1. Run git diff to see recent changes
2. Focus on modified files
3. Begin review immediately

Review checklist:
- Code clarity and readability
- No exposed secrets or API keys
- Proper error handling
- Performance considerations

Provide feedback organized by priority:
- Critical issues (must fix)
- Warnings (should fix)
- Suggestions (consider improving)

Use the test-runner subagent to fix failing tests
Have the code-reviewer subagent look at my recent changes

@"code-reviewer (agent)" look at the auth changes

claude --agent code-reviewer

{
  "agent": "code-reviewer"
}

claude --agents '{
  "code-reviewer": {
    "description": "Expert code reviewer. Use proactively after code changes.",
    "prompt": "You are a senior code reviewer. Focus on code quality, security, and best practices.",
    "tools": ["Read", "Grep", "Glob", "Bash"],
    "model": "sonnet"
  },
  "debugger": {
    "description": "Debugging specialist for errors and test failures.",
    "prompt": "You are an expert debugger. Analyze errors, identify root causes, and provide fixes."
  }
}'

Use a subagent to run the test suite and report only the failing tests

Research the authentication, database, and API modules in parallel using separate subagents

Use the code-reviewer to find performance issues, then use the optimizer to fix them

---
name: daily-report
description: Generates a daily code activity report
initialPrompt: /review HEAD~5..HEAD and generate a summary
---

You are a report generator...

claude --agent daily-report
# 启动后自动执行 initialPrompt

---
name: browser-tester
description: Tests features in a real browser using Playwright
mcpServers:
  - playwright:
      type: stdio
      command: npx
      args: ["-y", "@playwright/mcp@latest"]
  - github  # 引用已配置的服务器
---

---
name: code-reviewer
description: Reviews code for quality
memory: project
---

{
  "permissions": {
    "deny": ["Agent(Explore)", "Agent(my-custom-agent)"]
  }
}

claude --disallowedTools "Agent(Explore)"

/fork draft unit tests for the parser changes so far