opus

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: architecture decisions, complex debugging, multi-file refactoring, strategic planning, nuanced judgment, deep research, critical production decisions. Rule: If a human needs >30 seconds of focused thinking, escalate. If Sonnet struggles with complexity, go to Opus. Save 50-90% on API costs by starting cheap and escalating only when needed.

This skill appears to be a straightforward model-routing policy and contains no code or secret requests, but there are packaging/provenance inconsistencies (different skill name in SKILL.md vs registry slug and differing ownerId between registry and _meta.json). Before installing: 1) verify the publisher/owner and that the slug/name mismatch is intentional (ask the publisher or check an authoritative registry page); 2) confirm your platform supports the sessions_spawn pattern and the model names used (haiku/sonnet/opus) so the instructions actually map to real models; 3) test in a sandbox account or with billing limits — the policy intentionally escalates to costly models and could increase your API spend if thresholds are tuned incorrectly; 4) consider putting cost/budget guards or rate limits on autonomous model spawning; 5) if provenance isn’t verifiable, treat it as untrusted documentation rather than install/enable. If you can confirm publisher identity and intended mapping of model names, the skill is coherent and likely safe to use.

Type: OpenClaw Skill Name: opus Version: 1.0.0 The skill bundle provides instructions for an AI agent on how to intelligently select the appropriate Claude model (Haiku, Sonnet, Opus) based on task complexity to optimize API costs. The `SKILL.md` file contains clear guidelines, decision trees, and illustrative code snippets for model selection, all aligned with the stated purpose. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection attempts designed to subvert the agent for harmful actions. The content is purely instructional for internal operational efficiency.