← ClaudeAtlas

run-planlisted

EXECUTES an existing @planner plan -- parses the phase DAG, dispatches per-phase implement+review loops, preserving ASK gates. NOT for creating plans; NOT usable from inside a subagent.
atretyak1985/swarmery · ★ 4 · AI & Automation · score 76
Install: claude install-skill atretyak1985/swarmery
# Purpose Turn a finished plan directory into shipped code with one command. The main session acts as **controller**: it parses the phase DAG, picks a route, dispatches executors with the plan's own prompts, reviews each result, and keeps durable progress. The plan is the spec; this skill is the runner. **Main session only.** Subagents cannot spawn subagents, so this playbook can never be delegated. # Rules (never violate) 1. **Read the ledger first** — phases marked reviewed-clean in `<task-dir>/logs/run-ledger.md` are DONE; never re-dispatch them. 2. **Tick as you verify** — flip each satisfied criterion `- [ ]` → `- [x]` immediately, never in a batch; unsatisfied criteria stay unticked. 3. **Write the `## Completion Report`** into the phase doc itself — the only per-phase summary the platform surfaces; a `reports/` file is no substitute. 4. **Executors never commit** — commits, pushes, MRs, migrations, and deploys are ASK-gated controller business. 5. **Never skip the re-review** after a fix dispatch; review the reconciled tree, never the agent's own worktree. 6. One worktree per concurrent implementer on route P — parallel edits to one checkout corrupt each other. # Resources - Read `resources/execution-routes.md` at the start of a run: locating and parsing the plan, the pre-flight review, the route triage table and hand-off alternative, worktree isolation and reconciliation, and the S / P / W routes. - Read `resources/progress-contracts.md` be