| name | plan-with-fable-execute-with-subagents |
|---|---|
| description | Use when the user wants a task planned by the Fable model and built by Opus or Sonnet subagents. Triggers: "plan with fable", "fable then opus", "fable then sonnet", "fable plans and sonnet executes", "plan then dispatch subagents". |
One model plans. Other models build. Fable writes the plan. Opus or Sonnet subagents do the work in it.
- The task needs a plan before any code change.
- The user names Fable for the plan.
- The user names Opus, Sonnet, or both, for the build.
Skip this skill for a one-step task with no plan.
- Plan with Fable. Call the Agent tool with
subagent_type: "Plan"andmodel: "fable". State the task in full — the agent has no memory of this chat. Ask for a short numbered list. Each step gets one outcome and its own inputs, written out for a reader with no other context. The Plan agent has no Edit or Write tool, but it does have Bash, so tell it to plan only. - Read the plan. Every step needs a clear outcome and its inputs. To correct a vague step, use SendMessage with the planner's agent ID. A new Agent call starts fresh and loses the plan.
- Assign a model per step. A step with a hard trade-off, an unclear boundary, or a design call gets
model: "opus". A step that is direct and well-scoped getsmodel: "sonnet". Do not usesubagent_type: "fork"— a fork ignoresmodeland runs your own model. - Execute. Call the Agent tool once per step. State the step's outcome and inputs in full, because a fresh subagent never saw the plan. Send independent steps as separate tool calls in one message, so they run in parallel. Send a dependent step only after the step it needs finishes.
- Verify. Run the checks the task needs — tests, lint, build. Confirm each step's output matches its plan line before you call the task done.
| Role | subagent_type | model | Task |
|---|---|---|---|
| Planner | Plan | fable | Break the task into steps. Cannot edit a file, but has Bash. |
| Builder | general-purpose (or a fitting agent) | opus | A step with a judgment call. |
| Builder | general-purpose (or a fitting agent) | sonnet | A step that is clear and bounded. |
- One subagent gets the whole plan. Fix: one Agent call per step.
- Two independent steps run one after the other. Fix: read the plan for real dependencies, then send the independent steps in one message.
- A step runs with no context. Fix: write the step's outcome and inputs in full in the dispatch prompt.
- superpowers:writing-plans — for a plan that needs its own review checkpoint.
- superpowers:subagent-driven-development — for running the plan's steps in the current session.
- superpowers:dispatching-parallel-agents — for the rule on which steps can run together.