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.
What you get when you save this prompt
Your workspace unlocks powerful tools to iterate and improve.
AI Optimization
One-click improvement with structure analysis and pattern suggestions.
Version History
Track every edit. Compare versions side-by-side with word-level diffs.
Folders & Tags
Organize your library with nested folders, tags, and drag-and-drop.
$ npm i -g @promptingbox/mcpUse Everywhere
Access prompts from Claude, Cursor, ChatGPT & more via MCP integration.
Your prompts, organized
Save, version, and access your best prompts across ChatGPT, Claude, Cursor, and more.