---
name: writing-plans
description: Use before starting any non-trivial or multi-step piece of work — produce a clear plan BEFORE diving in. Triggers when the user asks you to plan, design an approach, scope an effort, or tackle work big enough to need ordered steps. The plan lives in a Scribe milestone (via start_planning), not a local file.
---

# Writing plans

A plan is **how** you'll execute a chunk of work — the design plus an ordered
set of steps — written *before* you start, so the approach is reviewable and the
work stays trackable.

## Start the plan in Scribe, not a file

For non-trivial work, call **`start_planning(project_id, title)` FIRST** —
before any design or implementation. It creates a **milestone** (the plan
container) seeded with a design template and returns the milestone id plus the
project's applicable rules. The plan lives in that milestone:

- The **design/intent** goes in the milestone `body` — edit it with
  `update_milestone(milestone_id, body=...)`.
- Each **step** is its own task under the milestone — create it with
  `create_task(milestone_id=<that milestone>)` and track it with status +
  `add_task_log`. Steps are first-class tasks, **not** checkboxes in the body.
- Read the whole plan back with `get_milestone` (body + its step-tasks).

**Do not** write plans or specs to local `.md` files — the milestone is the
record, not a file on disk. (The old `kind=plan` task is retired; `start_planning`
no longer creates one.)

Before designing from scratch, **recall**: `search` Scribe for a related prior
plan or decision. Often the thinking (or half of it) already exists.

## What a good plan contains

- **Goal** — what "done" looks like, and why, in a sentence or two (milestone body).
- **Approach** — the key design decisions and the trade-offs you chose, briefly
  (milestone body).
- **Steps** — an ordered set of step-tasks under the milestone, each small enough
  to verify on its own; note which files/areas each touches.
- **Verification** — how you'll know it actually works (a test, CI, an
  observable behavior), not just "it's written."

## While executing

- Keep the plan **honest**: drive each step-task's status (todo →
  in_progress → done) as it lands; record decisions, findings, and pivots with
  `add_task_log` on the relevant step rather than silently rewriting the body.
- If reality diverges from the plan, **update the milestone body** — a design
  that no longer matches what you're doing is worse than none. Add or re-scope
  step-tasks as the work changes.
- Mark the milestone `done` when its steps are complete.

## Match depth to the work

A two-step change deserves a two-line plan; a multi-day effort deserves a
fleshed-out milestone body and several step-tasks. Don't over-plan the trivial,
and don't under-plan something that will sprawl. The point is a shared,
reviewable intent — not ceremony.