/opus-pilot

name: opus-pilot
description: |
  Opus-first ceiling-elevation playbook: through reverse-advisor loops, parallel
  harness hypotheses, CAR-explicit declarations, externalized decision logs,
  and meta-harness diagnostics, push Opus 4.7 BEYOND vanilla Opus 4.7 quality.
  Triggers: "opus", "Opus", "Opus mode", "opus-pilot".
  Sub-mode modifiers: "Opus 1M" (1M context), "Opus xhigh" (extended thinking).

  Do NOT use for: cost optimization (use haiku-pilot / sonnet-pilot for that),
  default execution (Opus is the ceiling — only fire when the task warrants it),
  routine extraction / lookup (Opus on easy tasks underperforms Sonnet+pilot
  due to over-elaboration). This SKILL elevates Opus on hard tasks; it does
  not make Opus the default.
allowed-tools: Read, Grep, Glob, Bash, TodoWrite

Opus Pilot — Ceiling-Elevation Execution Playbook

Thesis

**Vanilla Opus is a strong solo solver. Opus + harness engineering is a stronger orchestrator that surpasses vanilla Opus on architecture / synthesis / counter-factual tasks.**

> **AgentOpt** (P10 / arxiv 2604.06296): On HotpotQA, Opus solo = **31.71%**; Ministral planner + Opus solver = **74.27%** (+42.56pp). **Individual model capability does NOT predict ensemble performance.** The reverse insight: Opus orchestrating Opus (via reverse-advisor) likewise outperforms solo Opus. > **Meta-Harness** (P03 / arxiv 2603.28052): Harness optimization with full execution-history access yields 5–10pp uplift on cross-domain transfer; the diagnostic loop (read-traces → form-causal-hypothesis → propose-fix) requires depth-of-reasoning that only Opus reliably executes on dense diagnostics. > **Confucius** (P02 / arxiv 2512.10398) §3: Scalable scaffolding (per-codebase memory + meta-agent dual critique) beats raw capability on real-world repos. > **CAR** (P07 / preprints 202603.1756): Treating harness as **Control / Agency / Runtime** layers makes harness mismatches diagnosable; Opus can introspect on labeled CAR declarations where Sonnet/Haiku miss the implication.

**What this SKILL actually does** (analytical estimate; empirical A/B vs vanilla Opus 4.7 to be verified per § Verification):

• On hard analytical tasks (architecture, counter-factual, synthesis) → **+8–15% quality** uplift over vanilla Opus via Reverse-Advisor + Parallel Hypotheses + CAR explicitness.
• On easy/recall tasks → **flat or slight loss** vs vanilla Opus (overhead > value); **fast-path** (skip mandatory pre-flights) addresses this.
• On medium/agentic tasks → **−20–40% cost** via down-delegation to Sonnet/Haiku sub-agents (Opus as planner only).

→ **Opus + this SKILL ≠ "always more thinking"**. It's **structured thinking + explicit delegation**. Opus's failure mode is *internal exhaustive exploration*; this SKILL externalizes the exploration into auditable artifacts and parallel sub-agents.

> Cost ratio: Opus ($15 / $75) is 5× Sonnet, 15× Haiku. Opus mode should fire only when the task *requires* Opus reasoning depth. Use sonnet-pilot or haiku-pilot for the other 80% of tasks.

---

The Five Mechanisms (Beyond-Vanilla Levers)

Mechanism #1 — Reverse-Advisor Loop

**Trigger**: any global-architecture / cross-module / synthesis / counter-factual / security-design decision.

**Procedure**: 1. Opus drafts the decision (Choice + Rationale + Rejected options). 2. Call `advisor()` (which is itself Opus with fresh context). 3. The advisor sees the full transcript; it acts as **peer reviewer**, not as fallback. 4. If advisor disagrees → reconcile via one more advisor call ("I found X, you suggest Y; which constraint breaks the tie?"). 5. Only declare done after advisor concurs OR explicitly notes "remaining disagreement is judgment-bound".

**Why Opus-specific**: Sonnet/Haiku call advisor() to *upgrade*; Opus calls advisor() for *peer review*. The cost is 1× (Opus → Opus), justified on architecture-grade decisions. AgentOpt principle inverted: orchestrated > solo, even at the ceiling tier. **(P10 AgentOpt 31.71% → 74.27%; P02 Confucius §4 dual-critique meta-agent)**

**Anti-pattern**: skipping advisor() because "Opus already thought about it carefully". The advisor sees blind spots Opus's depth-first reasoning misses.

---

Mechanism #2 — Parallel Hypotheses + Synthesis (Multi-Sample)

**Trigger**: harness-design / system-architecture / "what's the right approach" tasks.

**Procedure**: 1. Generate **N=3 candidate approaches** in parallel (single message, multiple Agent calls). Each sub-agent produces a complete proposal. 2. Read all N. Rank on agreed criteria (e.g., simplicity, correctness, ablation-friendliness). 3. **Synthesize the best features into a final design** — not "pick the best one", but "compose the strongest from N". 4. Document which features came from which candidate (citation traceability).

**Why Opus-specific**: Sonnet/Haiku parallel sampling produces lower variance (≈ same answer 3×); Opus produces meaningfully different proposals that benefit from synthesis. AgentFlow §3.2 structured DSL constraint hints at this — multi-agent variants outperform single-agent runs. **(P01 AgentFlow §3; P03 Meta-Harness ablation: 2–3 components drive 80% of gains, so synthesis must remain selective)**

**Anti-pattern**: generating 7 candidates + writing a 1500-word tradeoff matrix. The cost exceeds the value past N=3.

---

Mechanism #3 — CAR Explicitness (Three-Layer Harness Verbalization)

**Trigger**: any harness-design / agent-architecture / runbook / tool-config task.

**Procedure**: structure the answer (and any artifacts produced) using **Control / Agency / Runtime** labels:

• **Control**: policies (when does X fire? what's the decision rule?)
• **Agency**: tool access (which tools, with what permissions, fan-out vs serial)
• **Runtime**: memory / compaction / state-store / observability

**Why Opus-specific**: Opus excels at introspecting on labeled structures; CAR labels enable *self-diagnosis* of harness mismatches mid-task ("The bug is in Runtime — obser