Three-Agent Pipeline: Explorer, Implementer, Verifier Prompt
Design a three-stage agent pipeline where one agent plans, one builds, and one verifies — no agent does more than one job
Agent LoopsThree-Agent Pipeline: Explorer, Implementer, Verifier Prompt
Design a three-stage agent pipeline where one agent plans, one builds, and one verifies — no agent does more than one job
Design a three-agent pipeline for [YOUR_PROJECT] that handles [DESCRIBE THE TASK]. Agent 1 — Explorer: - Read-only access to the codebase - Reads the task spec from .agent/tasks.md - Produces a written implementation pl
Sub-agent orchestration prompt for a three-stage explorer/implementer/verifier pipeline — each agent has exactly one job.
Sub-agent orchestration prompt for a three-stage explorer/implementer/verifier pipeline — each agent has exactly one job.
How to use
- 1
Start by clearly defining [YOUR_PROJECT] and [DESCRIBE THE TASK] to ensure each agent has a focused objective and the pipeline operates smoothly.
- 2
After Agent 1 completes the implementation plan, review the details in .agent/plan-[task-id].md to confirm that all necessary modifications and risks are addressed before moving to Agent 2.
- 3
Follow up with Agent 3's verification by thoroughly checking the .agent/verdict-[task-id].md for a comprehensive assessment of the implementation against both the task spec and the plan.
Frequently asked questions
What is the Three-Agent Pipeline: Explorer, Implementer, Verifier Prompt prompt used for?
Sub-agent orchestration prompt for a three-stage explorer/implementer/verifier pipeline — each agent has exactly one job.
How do I get the best results from this sub-agent orchestration prompt?
Paste the prompt into Claude Code, Cursor, fill in every bracketed placeholder with your specific information, then submit. The more detail you add to each placeholder, the more targeted the output. You can continue in the same conversation to refine tone, length, or focus without restarting from scratch.
Does this prompt work with Claude Code?
Yes. This prompt is optimized for Claude Code and also works well with Cursor. The structured format with a defined role and numbered steps produces consistent results across all major instruction-following models, so you can use whichever tool you prefer.
How do I access this agent loops prompt?
This sub-agent orchestration prompt is available through TopFreePrompts with a Lucy+ licence. You can get access with a one-time Lucy+ purchase for $109, or a $15/month plan you can cancel anytime. Both options give access to the full library of 1,000,000+ prompts across all categories.
More Agent Loops Prompts
View allParallel Worktree Agent Workflow: Claude Code Prompt
Quality Gate Between Maker and Checker: Claude Code Prompt
Verification Agent After Every Pass: Claude Code Prompt
Loop State File Design: Claude Code, Replit Prompt
AGENTS.md Template for Loop Projects: Claude Code Prompt
Maker-Checker Sub-agent Pair: Claude Code, Cursor Prompt
Goal-Based Loop Until TypeScript Strict: Claude Code Prompt
Nightly Dependency Audit Loop: Claude Code, Replit Prompt
Replace Manual Workflow with Agent Loop: Claude Code Prompt
Minimum Viable Agent Loop: Claude Code, Cursor Prompt
Daily Triage Loop Architecture: Claude Code, Cursor Prompt
Dead Code Elimination Loop: Claude Code, Cursor Prompt
Related Prompts
View all
MCP Request and Response Logger and Inspector: Claude Code Prompt
MCP Tool Unit Test Framework: Claude Code, Cursor Prompt
MCP Mock Server for Local Testing: Claude Code, Cursor Prompt
Multi-Tenant MCP Server Design: Claude Code Prompt
MCP Error Handler with Retry Pattern: Claude Code Prompt
MCP Server Health Check Tool: Claude Code, Cursor Prompt
MCP Tool Response Caching Layer: Claude Code Prompt
MCP Rate Limiter Middleware: Claude Code, Cursor Prompt
MCP Server Authentication and Permission System: Claude Code Prompt
Resend Transactional Email MCP Tool: Claude Code Prompt
SMTP Email Sender MCP Tool: Claude Code, Cursor Prompt
Discord Message MCP Tool: Claude Code, Cursor Prompt