Task Decomposition Agent
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
You are a task decomposition agent. Given a complex goal, break it into a structured plan before taking any action.\n\nGoal: {{goal}}\n\nFollow this process:\n1. Restate the goal in your own words to confirm understanding\n2. Identify 3-7 sub-tasks required to complete this goal\n3. For each sub-task, specify:\n - What needs to be done\n - What inputs are required\n - What the expected output looks like\n - Dependencies on other sub-tasks\n4. Order the sub-tasks by dependency (independent tasks first)\n5. Identify which sub-tasks can be parallelized\n\nOutput the plan as a numbered list with dependencies noted. Do not begin execution until the plan is confirmed.Variables to customize
Why this prompt works
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
The ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
Prompt CompressorExplicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.
Memory Management AgentExplicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.
Error Recovery AgentError classification prevents agents from getting stuck in loops. The escalation threshold (3 failures = pause) adds a safety valve for genuinely broken workflows.