创建自定义子代理

先从固定套路开始，最容易见效。

bug-hunter
reviewer
test-writer
docs-helper

到这里其实就剩一句话，把下面这句发出去就行。

/agents

"Quickstart: create your first subagent"这一段里最要紧的原始写法在下面，先看它怎么落地。

A code improvement agent that scans files and suggests improvements
for readability, performance, and best practices. It should explain
each issue, show the current code, and provide an improved version.

到这里其实就剩一句话，把下面这句发出去就行。

Use the code-improver agent to suggest improvements in this project

看到这里，别光点头，下面这条命令先跑起来再说。

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."
  }
}'

看到这里，别光点头，下面这条命令先跑起来再说。

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."
  }
}
'@

这一段说完，最后还得写到配置里才算真的生效。

---
name: code-reviewer
description: Reviews code for quality and best practices
tools: Read, Glob, Grep
model: sonnet
---

You are a code reviewer. When invoked, analyze the code and provide
specific, actionable feedback on quality, security, and best practices.

这会儿轮到改配置了，字段名和关键字别自己乱换。

---
name: safe-researcher
description: Research agent with restricted capabilities
tools: Read, Grep, Glob, Bash
---

这会儿轮到改配置了，字段名和关键字别自己乱换。

---
name: no-writes
description: Inherits every tool except file writes
disallowedTools: Write, Edit
---

这会儿轮到改配置了，字段名和关键字别自己乱换。

---
name: coordinator
description: Coordinates work across specialized agents
tools: Agent(worker, researcher), Read, Bash
---

这会儿轮到改配置了，字段名和关键字别自己乱换。

---
name: browser-tester
description: Tests features in a real browser using Playwright
mcpServers:
  # Inline definition: scoped to this subagent only
  - playwright:
      type: stdio
      command: npx
      args: ["-y", "@playwright/mcp@latest"]
  # Reference by name: reuses an already-configured server
  - github
---

Use the Playwright tools to navigate, screenshot, and interact with pages.

光知道意思还不够，这里得把规矩落进配置里，下面这块照着填。

---
name: code-reviewer
description: Review code changes with automatic linting
hooks:
  PreToolUse:
    - matcher: "Bash"
      hooks:
        - type: command
          command: "./scripts/validate-command.sh $TOOL_INPUT"
  PostToolUse:
    - matcher: "Edit|Write"
      hooks:
        - type: command
          command: "./scripts/run-linter.sh"
---

光知道意思还不够，这里得把规矩落进配置里，下面这块照着填。

{
  "hooks": {
    "SubagentStart": [
      {
        "matcher": "db-agent",
        "hooks": [
          { "type": "command", "command": "./scripts/setup-db-connection.sh" }
        ]
      }
    ],
    "SubagentStop": [
      {
        "hooks": [
          { "type": "command", "command": "./scripts/cleanup-db-connection.sh" }
        ]
      }
    ]
  }
}

先看下面这块原始片段，等会儿再回头看解释会顺得多。

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

先看下面这块原始片段，等会儿再回头看解释会顺得多。

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

这一段不是只让你理解意思，下面这条命令就是现在要跑的。

claude --agent code-reviewer

这一段说完，最后还得写到配置里才算真的生效。

{
  "agent": "code-reviewer"
}

这里不用敲命令，直接把下面这句话发给 Claude 就行，让它按"Common patterns"这一段的意思去办。

Use a subagent to run the test suite and report only the failing tests with their error messages

这里不用敲命令，直接把下面这句话发给 Claude 就行，让它按"Common patterns"这一段的意思去办。

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

这里不用敲命令，直接把下面这句话发给 Claude 就行，让它按"Common patterns"这一段的意思去办。

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

先看下面这块原始片段，等会儿再回头看解释会顺得多。

Use the code-reviewer subagent to review the authentication module
[Agent completes]

Continue that code review and now analyze the authorization logic
[Claude resumes the subagent with full context from previous conversation]

这一段说完，最后还得写到配置里才算真的生效。

{
  "type": "system",
  "subtype": "compact_boundary",
  "compactMetadata": {
    "trigger": "auto",
    "preTokens": 167189
  }
}

到这里其实就剩一句话，把下面这句发出去就行。

/fork draft unit tests for the parser changes so far

这会儿轮到改配置了，字段名和关键字别自己乱换。

---
name: code-reviewer
description: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
tools: Read, Grep, Glob, Bash
model: inherit
---

You are a senior code reviewer ensuring high standards of code quality and security.

When invoked:
1. Run git diff to see recent changes
2. Focus on modified files
3. Begin review immediately

Review checklist:
- Code is clear and readable
- Functions and variables are well-named
- No duplicated code
- Proper error handling
- No exposed secrets or API keys
- Input validation implemented
- Good test coverage
- Performance considerations addressed

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

Include specific examples of how to fix issues.

想把这条规矩固定住，就把下面这块老老实实写进去。

---
name: debugger
description: Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
tools: Read, Edit, Bash, Grep, Glob
---

You are an expert debugger specializing in root cause analysis.

When invoked:
1. Capture error message and stack trace
2. Identify reproduction steps
3. Isolate the failure location
4. Implement minimal fix
5. Verify solution works

Debugging process:
- Analyze error messages and logs
- Check recent code changes
- Form and test hypotheses
- Add strategic debug logging
- Inspect variable states

For each issue, provide:
- Root cause explanation
- Evidence supporting the diagnosis
- Specific code fix
- Testing approach
- Prevention recommendations

Focus on fixing the underlying issue, not the symptoms.

这会儿轮到改配置了，字段名和关键字别自己乱换。

---
name: data-scientist
description: Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.
tools: Bash, Read, Write
model: sonnet
---

You are a data scientist specializing in SQL and BigQuery analysis.

When invoked:
1. Understand the data analysis requirement
2. Write efficient SQL queries
3. Use BigQuery command line tools (bq) when appropriate
4. Analyze and summarize results
5. Present findings clearly

Key practices:
- Write optimized SQL queries with proper filters
- Use appropriate aggregations and joins
- Include comments explaining complex logic
- Format results for readability
- Provide data-driven recommendations

For each analysis:
- Explain the query approach
- Document any assumptions
- Highlight key findings
- Suggest next steps based on data

Always ensure queries are efficient and cost-effective.

想把这条规矩固定住，就把下面这块老老实实写进去。

---
name: db-reader
description: Execute read-only database queries. Use when analyzing data or generating reports.
tools: Bash
hooks:
  PreToolUse:
    - matcher: "Bash"
      hooks:
        - type: command
          command: "./scripts/validate-readonly-query.sh"
---

You are a database analyst with read-only access. Execute SELECT queries to answer questions about the data.

When asked to analyze data:
1. Identify which tables contain the relevant data
2. Write efficient SELECT queries with appropriate filters
3. Present results clearly with context

You cannot modify data. If asked to INSERT, UPDATE, DELETE, or modify schema, explain that you only have read access.

看到这里，别光点头，下面这条命令先跑起来再说。

#!/bin/bash
# Blocks SQL write operations, allows SELECT queries

# Read JSON input from stdin
INPUT=$(cat)

# Extract the command field from tool_input using jq
COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command // empty')

if [ -z "$COMMAND" ]; then
  exit 0
fi

# Block write operations (case-insensitive)
if echo "$COMMAND" | grep -iE '\b(INSERT|UPDATE|DELETE|DROP|CREATE|ALTER|TRUNCATE|REPLACE|MERGE)\b' > /dev/null; then
  echo "Blocked: Write operations not allowed. Use SELECT queries only." >&2
  exit 2
fi

exit 0

"Database query validator"这一段里最要紧的原始写法在下面，先看它怎么落地。

chmod +x ./scripts/validate-readonly-query.sh

先从固定套路开始，最容易见效。

bug-hunter
reviewer
test-writer
docs-helper