looptimal

name	looptimal
description	Looptimal — turns an objective into a delivered, VERIFIED OUTCOME by designing, war-gaming, and running the right loop or mission route. Use on 'looptimal', '/looptimal', 'run an outcome loop', 'orchestrate this objective to done', 'plan and ship this goal', or any non-trivial objective that needs a sealed acceptance suite, the right execution driver, and independent verification before you call it done. ALSO handles loop-design wizard requests ('design a loop', 'build a loop', 'new loop', 'loop wizard', or a vague recurring task to automate) via the 'design' fast-path (Stage 2 only, no outcome orchestration). For a single, non-recurring deliverable you still want proven — not trivial, just not a reusable loop — it routes to mission / goal-run when bounded iteration is useful, or degrades to 'single-pass' mode when one pass is enough: Frame → (Analyze if multi-domain) → light pre-mortem → Execute → Verify-outcome → Persist, skipping reusable-loop scaffolding. When the objective's shape is ambiguous, asks one upfront mode-fork question (single-pass / bounded mission or recurring system / just a blueprint) before any Frame work starts. Runs an 8-stage pipeline: 0 Frame (hash-pinned SEALED acceptance suite) → 1 Analyze (Capability Manifest + local capability readiness) → 2 Design-loop / Route (wizard: Task / Recurring / Supervised / Persistent-ratchet / Orchestration, mission / goal-run, single-pass, or REJECT) → 3 Plan → 4 Simulate (roll forward N steps, pre-mortem, harden) → [human GO] → 5 Execute (domain-expert sub-agents, maker ≠ checker) → 6 Verify-outcome (separate checker re-runs the SEALED suite vs live state) → 7 Persist. Fast-path hints: say 'design' or 'loop wizard' for Stage 2 blueprint only; 'single-pass' for one verified pass with no loop; 'skip wizard' to bypass the interview in Stage 2; 'skip simulate' to jump to Plan after Design-loop with explicit risk callout; 'fast path' for Frame + Design-loop + Plan then stop. If install looks broken — skill won't trigger, a script errors, profile won't resolve — run 'looptimal doctor' via scripts/looptimal-doctor.py.
license	MIT

Looptimal — outcome orchestrator

Turn an objective into a delivered, verified outcome: seal the acceptance criteria, pick or reject the right loop, war-game the plan, execute with domain experts, and gate completion on a separate verifier re-running the sealed suite against live state — never on self-reported GREEN.

The loop-design wizard (formerly the standalone LoopPrint) is embedded as Stage 2: Design-loop. It also runs as a design fast-path when you only want a loop blueprint without outcome orchestration.

When to use

• "looptimal", "/looptimal", "run an outcome loop", "orchestrate this objective to done", "plan and ship this goal".
• A non-trivial objective where "done" must be proved against live state, not asserted by the agent that did the work.
• Multi-domain work needing a Capability Manifest, consensus plan, and maker ≠ checker at the outcome altitude.
• Recurring, supervised, ratchet, or orchestration patterns — after Design-loop confirms this is actually a loop.
• You want Simulate to war-game the plan before any autonomous execution.
• A single, non-trivial objective you want delivered once and proven against live state. If it needs bounded iteration, route it as a mission / goal-run; if one careful pass is enough, use single-pass mode (see the mode fork below).

When to use the design fast-path

• "design a loop", "build a loop", "new loop", "loop wizard", or a vague recurring task to automate.
• You only want a loop blueprint (spec + artifacts) — no outcome orchestration.
• Jumps directly to Stage 2 (Decision Gate → wizard → artifact generation) and stops.

When NOT to use

• A trivial one-shot answer, quick edit, or conversational question → just do it well once, no tool needed. (A substantive one-shot objective you still want proven — not trivial, just not recurring — routes to mission / goal-run or single-pass below, not a reason to skip Looptimal entirely.)
• Analysis with no delivery obligation → answer directly or use esat.
• Irreversible, judgment-heavy actions with no human willing to hold the GO gate → recommend a human-gated process.
• Meta-loops ("run Looptimal to verify Looptimal", "auto-merge when Looptimal says GREEN") → Design-loop must REJECT.
• Symptom-only success metrics with no behavioral outcome oracle → re-Frame or REJECT.

Operating rules (read first)

• This is a skill, not a persona or mode. Open with one activation line, then do the work.
• Checkpoint-gated: Frame → Analyze → Design-loop / Route → Plan → Simulate each stop for brief status. Execute never starts without explicit human GO after Simulate — or, in single-pass mode, after the light pre-mortem that substitutes for the Analyze/Design-loop/Plan/Simulate checkpoints (see the mode fork below).