Save Money

Auto-detect task complexity for Claude models (Haiku + Sonnet). Route simple tasks to Haiku, escalate complex ones to Sonnet. Save 50%+ on API costs. | 適用 Claude 模型（Haiku + Sonnet），自動偵測任務難度，簡單用 Haiku，複雜升級 Sonnet，輕鬆省下 50% 以上的費用。— RULES: Before responding, classify the task. If it matches an escalation trigger, call sessions_spawn with the full task and model anthropic/claude-sonnet-4-20250514 IMMEDIATELY. Do NOT answer complex tasks yourself. ESCALATE: analysis, comparisons, planning, strategy, code >10 lines, reports, proposals, multi-step reasoning, tables, outlines, charts, long writing >3 paragraphs, summarization, long translation. NEVER on Haiku: comparison tables, code >10 lines, multi-step analysis, reports, complex reasoning. STAY on Haiku: factual Q&A, definitions, greetings, reminders, short lookups, casual chat, 1-2 sentence tasks. When in doubt, escalate. Keep Haiku replies concise.

Install this only if you want automatic model handoff for many complex or uncertain requests. Avoid using it on sensitive prompts unless you are comfortable with the full task being sent to a spawned Sonnet session, and monitor costs because escalation does not require a separate confirmation step.

Type: OpenClaw Skill Name: save-money Version: 4.2.0 The skill is designed to optimize API costs by instructing the AI agent to classify task complexity and route requests to either a cheaper (Haiku) or more powerful (Sonnet) Claude model using `sessions_spawn()`. The instructions in SKILL.md, including the `description` field which is injected into the system prompt, are prescriptive but solely focused on this model routing logic. There is no evidence of malicious intent, such as data exfiltration, unauthorized command execution, persistence mechanisms, or prompt injection aimed at subverting the agent for harmful purposes. The instructions are transparent about their goal of cost saving and model selection.