← ClaudeAtlas

planrunlisted

Use when executing a written implementation plan from the knowledge base in a fresh session. Reads the spec and plan, works the tasks in order, checks them off in place, and keeps the expensive gates off the hot path. Pair with /plan:snapshot to stop cleanly and /plan:resume to pick up an interrupted run.
franzos/claude-plugins · ★ 1 · Testing & QA · score 69
Install: claude install-skill franzos/claude-plugins
# Executing a plan > `$KB` is your knowledge-base root: a directory outside the working repo holding > `<project>/specs/`, `<project>/plans/` and `<project>/checkpoints/`. Point at it from > your CLAUDE.md. Keeping these out of the repo keeps process artifacts from leaking > into it, and the knowledge survives clones, branches and machines. Run this in a **fresh session**. Execution in the same session that wrote the plan starts at 100k+ of context and pays that on every turn for the rest of the run. ## Run it autonomously **Work the whole plan through without checking in.** The user already signed the plan off. Do not ask permission to start a task, to move to the next one, or to act on the commit answer they give you in section 1. Report at milestones, not per task - a short line when a group of related tasks lands, not a narration of each one. There are exactly four reasons to stop and ask: 1. The two run questions at the start (section 1), asked together, once. 2. A task contradicts the spec, or doing it would change scope (section 3). 3. Something is genuinely ambiguous and both readings lead to materially different work. 4. The context thresholds below. Anything else - a task that needs a small mechanical deviation, a pre-existing failure, a judgment call with an obvious default - decide it, note it, keep going. ## 1. Load Find the plan under `$KB/<project>/plans/`. If several match, take the newest by date and say which one you took. Check `$KB/<project>/che