← ClaudeAtlas

planning-replanlisted

Deciding what a plan becomes once reality diverges: classifying the divergence, measuring it, the stop test, and a dated changelog of what changed and why.
simota/planning-skills · ★ 2 · AI & Automation · score 66
Install: claude install-skill simota/planning-skills
<!-- planning:contract --> ## Owns Post-start divergence, classified and corrected at its owning phase. Pre-start edits return there directly. **Stopping stays on the table and is priced like any other option.** Phases: `MEASURE → CLASSIFY → PRICE → CORRECT → RECORD`. ## Before starting - **Measure before diagnosing**: planned versus actual per task and milestone, with the numbers stated. **No narrative before the table** — the story you tell about a slip determines which correction you reach for - **Name the sunk cost once, to set it aside.** Then decide on remaining cost and remaining value alone - **Establish whether the problem changed or only the path.** A changed problem is a re-framing, not a replan, and treating it as one patches a plan that is solving the wrong thing <!-- deliver:sizing --> - **Declare the tier before anything else**, read off the work and stated at the top of the deliverable. `S` — under a day, reversible: one brief in the response, **no files, no handoff**. `M` — multi-day, single owner: the brief and the plan. `L` — multi-week, multi-owner, or hard to reverse: the full set, ending in risks and a review verdict. **Over-planning an `S` is a failure of the same weight as under-planning an `L`** - **The planning gate stops the run at the phase that owns the condition** — the goal cannot be stated in one sentence without "and", no success criterion is measurable, a load-bearing assumption is cheap to verify and unverified,