Menu
Use when you have a written implementation plan to execute - direct execution by default, subagents for complex tasks
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Explore ideas and create designs before implementation
Use when about to claim work is complete or before committing - enforces verification and proposes a commit
Fetch current library and framework documentation from Context7 instead of relying on training data
Use when encountering any bug, test failure, or unexpected behavior — find root cause before proposing any fix
Use when implementing any feature or bugfix, before writing implementation code
Use when starting substantive work to choose the right workflow skill without adding unnecessary ceremony to trivial interactions
| name | executing-plans |
| description | Use when you have a written implementation plan to execute - direct execution by default, subagents for complex tasks |
| license | MIT |
| compatibility | opencode |
Read the plan. Execute tasks one by one. Verify after each. Report progress.
Core principle: Direct execution by default. Use subagents only when task complexity warrants isolation.
Use when you have a written implementation plan (from writing-plans or provided by the user) and are ready to implement it.
For each task:
in_progresscompleting-work skill before marking donecompletedUse @implementer only when a task is:
For simple or sequential tasks, execute directly. Most tasks should be direct.
Invoke @code-reviewer when the diff becomes risky enough to benefit from a fresh review, especially after:
After all tasks are done:
completing-work to verify status and optionally suggest commit messaging if the user asked for itStop immediately when:
Ask for clarification rather than guessing.
systematic-debugging