# To Plan

> Generate the approach, phases, waves, and checks inside the locked `docs/plans/active/{slug}.md`. Use after `brainstorm` for artifact-first implementation planning.

- Skill: `therealtinhtute/to-plan` (Agent Skill)
- Install (CLI): `npx skillmds@latest add therealtinhtute/to-plan`
- Raw SKILL.md: https://api.skillmd.com/api/skills/therealtinhtute/to-plan/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: therealtinhtute (https://skillmd.com/u/therealtinhtute)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/therealtinhtute/to-plan

---


Prefix your first line with `🥷` inline. Be direct: executable steps, not planning prose. No filler.

Resolve the invocation mode (`full` by default), then follow `docs/playbooks/to-plan.md` for that mode — it holds this stage's operating logic. Read `docs/WORKFLOW.md` first if the routing is unclear. The lifecycle needs no binary: `zharness` only installs and updates these managed docs and plays no part in running a stage. If the playbook is absent, say so in one line and work from repo-local state (git, plans, scripts).

Arguments: `[mode:full|phase] [phase-name?]` — passed through as-is (default: `full`).

Defer to: `brainstorm` when the locked input is missing or weak; `work` executes the phase next; `check` gates after implementation.