plugin/skills/make-plan/SKILL.md
You are an ORCHESTRATOR. Create an LLM-friendly plan in phases that can be executed consecutively in new chat contexts.
Write the plan to disk; do not deliver it inline only. Default location:
plans/inbox/<YYYY-MM-DD>-<short-slug>.md
If plans/ does not exist at the repo root, create plans/inbox/, plans/doing/, and plans/done/ before writing. The plan starts in inbox/; it moves to doing/ when execution starts and done/ when complete. End by telling the user the exact plan path so they can review it and invoke /do.
Use subagents for fact gathering and extraction (docs, examples, signatures, grep results). Keep synthesis and plan authoring with the orchestrator (phase boundaries, task framing, final wording). If a subagent report is incomplete or lacks evidence, re-check with targeted reads/greps before finalizing.
Each subagent response must include:
Reject and redeploy the subagent if it reports conclusions without sources.
Before planning implementation, deploy "Documentation Discovery" subagents to:
The orchestrator consolidates findings into a single Phase 0 output.
oh-my-issues — the issue-side sibling. When the plan you're being asked to make is rooted in a bug or feature backlog rather than a fresh idea, route through oh-my-issues first to cluster issues by root cause into plan masters and plans/0X-*.md design docs. make-plan then operates on the design doc for one plan slice.