{"id":"c796560c-c849-4a43-801b-d903ac2cb9f5","slug":"zscole-model-hierarchy-skill","name":"model-hierarchy","description":"Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity. Use this skill when: (1) deciding which model to use for a task, (2) spawning sub-agents, (3) considering cost efficiency, (4) the current model feels like overkill for the task. Triggers: \"model routing\", \"cost optimization\", \"which model\", \"too expensive\", \"spawn agent\".","canonicalUrl":"https://xpersona.co/skill/zscole-model-hierarchy-skill","sourceUrl":"https://github.com/zscole/model-hierarchy-skill","homepage":null,"source":"GITHUB_OPENCLEW","vendor":{"slug":"zscole","label":"Zscole","url":"https://github.com/zscole/model-hierarchy-skill"},"protocols":["OPENCLEW"],"capabilities":["handle","figure"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-02-25T02:06:31.176Z","freshnessLabel":"Feb 25, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Feb 25, 2026"},{"label":"Vendor","value":"Zscole"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official domain","href":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceUrl":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceType":"search_document","confidence":"medium","observedAt":"2026-04-15T05:03:46.393Z","isPublic":true},{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Zscole","href":"https://github.com/zscole/model-hierarchy-skill","sourceUrl":"https://github.com/zscole/model-hierarchy-skill","sourceType":"profile","confidence":"medium","observedAt":"2026-02-25T02:06:32.391Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://xpersona.co/api/v1/agents/zscole-model-hierarchy-skill/contract","sourceUrl":"https://xpersona.co/api/v1/agents/zscole-model-hierarchy-skill/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-02-25T02:06:32.391Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"321 GitHub stars","href":"https://github.com/zscole/model-hierarchy-skill","sourceUrl":"https://github.com/zscole/model-hierarchy-skill","sourceType":"profile","confidence":"medium","observedAt":"2026-02-25T02:06:32.391Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://xpersona.co/api/v1/agents/zscole-model-hierarchy-skill/trust","sourceUrl":"https://xpersona.co/api/v1/agents/zscole-model-hierarchy-skill/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["321 GitHub stars","Trust evidence available"],"agentCard":{"name":"model-hierarchy","description":"Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity. Use this skill when: (1) deciding which model to use for a task, (2) spawning sub-agents, (3) considering cost efficiency, (4) the current model feels like overkill for the task. Triggers: \"model routing\", \"cost optimization\", \"which model\", \"too expensive\", \"spawn agent\".","source":"GITHUB_OPENCLEW","sourceId":"github:1155817029","repository":"https://github.com/zscole/model-hierarchy-skill","documentation":"https://xpersona.co/skill/zscole-model-hierarchy-skill/agent/zscole-model-hierarchy-skill","protocols":["OPENCLEW"],"capabilities":["handle","figure"],"languages":["typescript"],"install":{"command":"git clone https://github.com/zscole/model-hierarchy-skill.git","ecosystem":"git"},"examples":[{"kind":"example","language":"text","snippet":"function selectModel(task):\n    # Rule 1: Vision override (Tier 1/2 includes text-only models)\n    if task.requiresImageInput or task.requiresVision:\n        return VISION_CAPABLE_MODEL  # e.g. Kimi K2.5, GPT-4o, Gemini, Claude; do not use GLM 5 or other text-only\n    \n    # Rule 2: Escalation override\n    if task.previousAttemptFailed:\n        return nextTierUp(task.previousModel)\n    \n    # Rule 3: Explicit complexity signals\n    if task.hasSignal(\"debug\", \"architect\", \"design\", \"security\"):\n        return TIER_3\n    \n    if task.hasSignal(\"write\", \"code\", \"summarize\", \"analyze\"):\n        return TIER_2\n    \n    # Rule 4: Default classification\n    complexity = classifyTask(task)\n    \n    if complexity == ROUTINE:\n        return TIER_1\n    elif complexity == MODERATE:\n        return TIER_2\n    else:\n        return TIER_3"},{"kind":"example","language":"yaml","snippet":"# config.yml - set default model\nmodel: anthropic/claude-sonnet-4\n\n# In session, switch models\n/model opus  # upgrade for complex task\n/model deepseek  # downgrade for routine\n\n# Spawn sub-agent on cheap model\nsessions_spawn:\n  task: \"Fetch and parse these 50 URLs\"\n  model: deepseek"}]}}