← ClaudeAtlas

planr-operatelisted

Run one complete agent-native OpenPlanr operating cycle in Codex, from project research through CEO/CTO/CPO/CMO/COO/Chair synthesis and provisional drafts, stopping at review.
openplanr/planr-pipeline · ★ 2 · AI & Automation · score 73
Install: claude install-skill openplanr/planr-pipeline
# Planr Operate — Codex-native workflow This skill is the primary workflow. The user does not write an orchestration prompt or run machine lifecycle commands. Use only public `planr operate` commands for user actions and the CLI-returned `harness` actions internally. ## Default invocation A bare `$planr-operate` means: 1. Inspect with `planr operate inspect --json`. 2. Select Codex through normal runtime precedence and keep that binding for the entire cycle. Never invoke another vendor runtime or its commands, assets, or models. 3. If context is absent or stale, run the returned bootstrap harness. Follow [bootstrap](references/bootstrap.md): inspect the workspace first, produce cited context claims, then present one compact context review only when owner confirmation is genuinely needed. Use Codex's native question tool when it is available; otherwise ask naturally in chat. Never dump a questionnaire. 4. Preview, then start exactly one local cycle. The bare skill invocation is authority for reversible local cycle continuation through `reviewable`, `blocked`, or `failed`; it is not authority for connected research, draft approval, route application, PLAN, SHIP, or external effects. 5. Execute current `handoff.next[].argv` actions only. For each `harness.record`, dispatch the named Codex role with its mandate and [advisor procedure](references/advisor.md). Use native Codex subagents when exposed; otherwise run the same role sequentially in t