Approval Workflow
Phased execution with approval gates gives you control over complex multi-step tasks. Each phase being independently functional means you can stop at any point with a working codebase.
I want to {{overall_goal}}. Work through this incrementally:\n\nPhase 1: {{phase_1_description}}\n- Make the changes for phase 1\n- Show me what you changed (file-by-file summary)\n- STOP and wait for my approval before proceeding\n\nPhase 2: {{phase_2_description}}\n- Only start after I approve phase 1\n- Show changes and wait for approval\n\nPhase 3: {{phase_3_description}}\n- Only start after I approve phase 2\n- Show changes and wait for approval\n\nRules:\n- Never combine phases — one at a time\n- If you encounter an issue in any phase, stop and explain it instead of working around it\n- Each phase should be independently functional (the app shouldn't break between phases)\n- If I say "revert phase N", undo only that phase's changes
Variables to customize
Why this prompt works
Phased execution with approval gates gives you control over complex multi-step tasks. Each phase being independently functional means you can stop at any point with a working codebase.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
Tool Selection AgentThe 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.