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
/plugin marketplace add WorldFlowAI/everything-claude-code
/plugin install everything-claude-code@everything-claude-codeWhat 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-code2Manually: put the files in place
.claude/rules/agents.mdThe paths frontmatter field limits the files
AGENTS.md
Codex reads AGENTS.md: paste the rule text there
Manually: put the files in place
.cursor/rules/agents.mdcFrontmatter: description, globs, alwaysApply
Manually: put the files in place
.github/instructions/agents.instructions.mdThe applyTo field sets which files it applies to
Manually: put the files in place
.devin/rules/agents.mdManually: put the files in place
.clinerules/agents.mdStep 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.