// Breaks the next task from a plan into an implementable task file. Use when decomposing a multi-step plan into ordered work units.
Multi-model supervisor that discovers skills, picks models, and composes runs. Use when executing multi-step plans across multiple models.
Agent execution engine that composes prompts, routes models, and writes run artifacts. Use when launching subagent runs.
Multi-model supervisor that discovers skills, picks models, and composes runs. Use when executing multi-step plans across multiple models.
Agent execution engine that composes prompts, routes models, and writes run artifacts. Use when launching subagent runs.
Verifies implementation aligns with stated requirements and acceptance criteria. Use before implementation (to clarify scope) and before final sign-off (to detect gaps).
Explores codebases and evaluates approaches before planning. Use when investigating a problem space, comparing alternatives, or gathering context for a plan.
| name | plan-task |
| description | Breaks the next task from a plan into an implementable task file. Use when decomposing a multi-step plan into ordered work units. |
Create the next implementable task from a plan.
Use these prompt variables:
{{PLAN_FILE}} — source plan to readResolve output directory:
<dir-of-PLAN_FILE>/tasks.Gather context on what is already completed:
{{PLAN_FILE}} and inspect status/phase tracking sections.<resolved-tasks-dir>/progress.md exists, read it for prior completed tasks.<resolved-tasks-dir>/task.md exists, use it as context for continuity.If all phases/steps in the plan are complete:
ALL_DONE to <resolved-tasks-dir>/task.md.Determine the next logical task from the plan.
Write <resolved-tasks-dir>/task.md. Include whatever structure makes sense, but the task file should give an implementing agent everything it needs:
A good task is self-contained: the codebase must be in a working state when done. Size is secondary — focus on logical completeness, not line count.