94/100 (Very Low)

OpenClaw： benign
VirusTotal： benign
StaticScan： unknown

OpenClaw： benign

This is an instruction-only routing policy for selecting z.ai (GLM) models (Flash → Standard → Plus/32B); it requests no credentials, installs nothing, and its instructions are consistent with its sta...

[内容已截断]

VirusTotal： benign VT 报告

静态扫描： unknown

README 未提供

{
    "latestVersion": {
        "_creationTime": 1770605733241,
        "_id": "k97a0pm6rf7ex51jxdyvq92x0d80tcbj",
        "changelog": "smart-model-routing-for-zai 1.0.0 introduces an auto-escalating model-routing strategy for cost-effective, accurate task processing on z.ai (GLM):\n\n- Implements three-tier task routing: Flash → Standard → Plus\/32B, starting with the cheapest model and escalating only when needed.\n- Clear rules and decision trees guide when to escalate tasks based on task complexity and required reasoning.\n- Provides detailed examples and quick-reference guides for selecting the correct model tier.\n- Aims to minimize API costs while ensuring correct and efficient responses for a wide range of user tasks.",
        "changelogSource": "auto",
        "createdAt": 1770605733241,
        "parsed": {
            "clawdis": {
                "emoji": "💰"
            }
        },
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "T",
        "handle": "princnl",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/93612321?v=4",
        "kind": "user",
        "linkedUserId": "kn7csjefpxk475pq302wdh5pn180tzj8"
    },
    "ownerHandle": "princnl",
    "skill": {
        "_creationTime": 1770605733241,
        "_id": "kd723qer1b1nqqh6r57ws48t5980vyes",
        "badges": [],
        "createdAt": 1770605733241,
        "displayName": "Smart Model Routing for Z.AI",
        "latestVersionId": "k97a0pm6rf7ex51jxdyvq92x0d80tcbj",
        "ownerUserId": "kn7csjefpxk475pq302wdh5pn180tzj8",
        "slug": "smart-model-routing-for-zai",
        "stats": {
            "comments": 2,
            "downloads": 1111,
            "installsAllTime": 3,
            "installsCurrent": 3,
            "stars": 1,
            "versions": 1
        },
        "summary": "Auto-route tasks to the cheapest z.ai (GLM) model that works correctly. Three-tier progression: Flash → Standard → Plus\/32B. Classify before responding.\nFLASH (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1–2 sentence tasks, cron jobs.\nESCALATE TO STANDARD: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations.\nESCALATE TO PLUS\/32B: architecture decisions, complex debugging, multi-file refactoring, strategic planning, nuanced judgment, deep research, critical production decisions.\nRule: If a human needs >30 seconds of focused thinking, escalate. If Standard struggles with complexity, go to Plus\/32B. Save major API costs by starting cheap and escalating only when needed.",
        "tags": {
            "latest": "k97a0pm6rf7ex51jxdyvq92x0d80tcbj"
        },
        "updatedAt": 1772064640938
    }
}