Skip to main content
rule CX Codex

Agents · worldflowai — Claude Code rule: nine specialized agents

A rule that defines nine agents in ~/.claude/agents/ for different development tasks: planning, design, testing, code review, and more. Run them in parallel for independent work.

MIT ★ 6,739 updated 2026-01-23

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add WorldFlowAI/everything-claude-code
/plugin install everything-claude-code@everything-claude-code
Open on GitHub

What agents does

This rule sets up nine agents stored in ~/.claude/agents/, each for a specific role. The planner handles implementation plans for complex features and refactoring. The architect makes system design decisions. The tdd-guide walks through test-driven development for new features and bug fixes. The code-reviewer examines written code, while security-reviewer analyzes security before commits. The build-error-resolver fixes build failures. The e2e-runner executes end-to-end tests on critical user flows. The refactor-cleaner removes dead code, and doc-updater maintains documentation.

Apply agents immediately without extra prompts: for complex feature requests, use planner; after writing code, use code-reviewer; for bugs or new features, use tdd-guide; for architectural questions, use architect. For independent tasks, launch multiple agents in parallel rather than sequentially. For complex problems, employ multi-perspective analysis using different roles: a factual reviewer, senior engineer, security specialist, consistency reviewer, and redundancy checker.

What it helps with

  • pick the right agent for each development task
  • run independent operations in parallel
  • analyze code from multiple professional perspectives
  • automate code review and testing workflows

Example prompts for the agent

  • Use planner to design a new authentication module
  • Run security-reviewer before committing to main
  • Have code-reviewer examine your component after you finish writing

How to install agents

1Plugin marketplace

/plugin marketplace add WorldFlowAI/everything-claude-code
/plugin install everything-claude-code@everything-claude-code

2Manually: put the files in place

.claude/rules/agents.md

The paths frontmatter field limits the files

Step by step, with commands for each platform: AGENTS.md vs CLAUDE.md: what they are and which one to use

Questions about agents

How do I install agents in Claude Code?

Run /plugin marketplace add WorldFlowAI/everything-claude-code, then /plugin install everything-claude-code@everything-claude-code. The rule file will be placed in .claude/rules/agents.md.

What does the agents rule do?

It defines nine agents for different development phases—planning, architecture, code review, testing, and documentation. It tells you which agent to use for each situation and how to run them in parallel.

Can I run multiple agents at the same time?

Yes, that's recommended for independent work. For instance, security-reviewer and e2e-runner can work simultaneously if they analyze different parts of your codebase.

Source text

agents.md · MIT
# Agent Orchestration

## Available Agents

Located in `~/.claude/agents/`:

| Agent | Purpose | When to Use |
|-------|---------|-------------|
| planner | Implementation planning | Complex features, refactoring |
| architect | System design | Architectural decisions |
| tdd-guide | Test-driven development | New features, bug fixes |
| code-reviewer | Code review | After writing code |
| security-reviewer | Security analysis | Before commits |
| build-error-resolver | Fix build errors | When build fails |
| e2e-runner | E2E testing | Critical user flows |
| refactor-cleaner | Dead code cleanup | Code maintenance |
| doc-updater | Documentation | Updating docs |

## Immediate Agent Usage

No user prompt needed:
1. Complex feature requests - Use **planner** agent
2. Code just written/modified - Use **code-reviewer** agent
3. Bug fix or new feature - Use **tdd-guide** agent
4. Architectural decision - Use **architect** agent

## Parallel Task Execution

ALWAYS use parallel Task execution for independent operations:

```markdown
# GOOD: Parallel execution
Launch 3 agents in parallel:
1. Agent 1: Security analysis of auth.ts
2. Agent 2: Performance review of cache system
3. Agent 3: Type checking of utils.ts

# BAD: Sequential when unnecessary
First agent 1, then agent 2, then agent 3
```

## Multi-Perspective Analysis

For complex problems, use split role sub-agents:
- Factual reviewer
- Senior engineer
- Security expert
- Consistency reviewer
- Redundancy checker

© Affaan Mustafa · MIT · WorldFlowAI/everything-claude-code

Similar IDE rules

All IDE rules for Agent setup: memory, context, orchestration →

agents by other authors comes first.

From the same set29

The whole set →
verify The verify command checks the build, types, lint, tests, logs, and Git state. Use it before a commit or pull request. CX Codex +1 ★ 6,739repo stars performance performance — a Claude Code rule that matches model to task and keeps heavy refactors away from the tail of the context window. CX Codex +1 ★ 6,739repo stars coding-style coding-style is a Claude Code rule for code structure and quality checks. It applies while an agent writes or changes code. CX Codex +1 ★ 6,739repo stars hooks The hooks rule defines actions before and after tool calls, plus a final session check. It helps run code checks and review Git-related changes. CX Codex +1 ★ 6,739repo stars checkpoint Saves named Git checkpoints during a Claude Code workflow and compares changed files, test results, and test coverage against earlier marks. CX Codex +1 ★ 6,739repo stars learn The learn slash command turns reusable lessons from the current session into skills. Run it after a difficult fix, debugging session, or project-specific discovery. CX Codex +1 ★ 6,739repo stars setup-pm setup-pm — a command to configure which package manager (npm, pnpm, yarn, or bun) Claude Code uses in your project or globally. Use it when you want to enforce a specific manager across your workflow. CX Codex +1 ★ 6,739repo stars code-reviewer The code-reviewer subagent reviews code changes for security vulnerabilities, bugs, performance problems, and style violations. Run it immediately after writing or modifying code to catch issues before they reach production. CX Codex ★ 6,739repo stars

Project sponsors

Companies that keep this analytics open