antigravity-rotatorGoogle Antigravity 模型全自动运维方案。提供多账号自动轮换、优先级调度、会话热更新以及赛博朋克风仪表盘。使用场景包括：(1) 自动化管理多个 Antigravity 账号，(2) 监控配额并自动切换，(3) 在不重启会话的情况下更新模型。
Install via ClawdBot CLI:
clawdbot install chocomintx/antigravity-rotatorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:fetchAvailableModelUses known external API (expected, informational)
googleapis.comAI Analysis
The skill interacts with Google's Antigravity API (googleapis.com) for its stated purpose of quota monitoring and model management, which is consistent and expected. The use of shell commands (exec) for setup and cron job management is a legitimate implementation pattern for system automation but introduces a low security risk if the skill's code were maliciously modified. No evidence of credential harvesting, data exfiltration, hidden instructions, or obfuscation was found in the provided definition.
Generated Mar 21, 2026
Research teams managing multiple Google Antigravity accounts for model testing and experimentation can use this skill to automatically rotate accounts based on quota availability, ensuring continuous operation without manual intervention. It supports seamless model switching during long-running experiments, reducing downtime and maximizing resource utilization.
Companies deploying AI-powered applications that rely on Antigravity models can leverage this skill to maintain high availability by automatically switching to backup accounts when primary quotas are exhausted. The session hot update feature allows for uninterrupted service, critical for customer-facing applications requiring 24/7 uptime.
Content creation agencies or marketing teams using Antigravity for automated content generation can benefit from automated account rotation to avoid quota limits, ensuring consistent output. The dashboard provides real-time monitoring of account statuses, helping teams manage usage and plan for scaling needs.
Online learning platforms integrating Antigravity for AI-driven tutoring or content generation can use this skill to manage multiple accounts efficiently, automatically switching to available models during peak usage times. This ensures reliable access for students and reduces administrative overhead in monitoring quotas.
Offer this skill as part of a premium subscription for AI developers and enterprises, providing enhanced support, priority updates, and custom configurations. Revenue is generated through monthly or annual fees, with tiers based on the number of managed accounts or advanced features like custom dashboards.
Provide consulting services to help businesses integrate and customize the Antigravity Rotator into their existing AI workflows, including setup, cron job configuration, and dashboard customization. Revenue comes from one-time project fees or ongoing maintenance contracts, targeting organizations with complex deployment needs.
Release the core skill as open-source or freeware to build a user base, then monetize through premium add-ons such as advanced analytics, extended dashboard features, or enterprise-grade security options. Revenue is driven by upselling these add-ons to users requiring more robust functionality.
💬 Integration Tip
Ensure the openclaw binary path is correctly set in config.json and test cron jobs in a staging environment before full deployment to avoid disruptions.
Scored Jun 17, 2026
Audited Apr 17, 2026 · audit v1.0
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 min...
Generate and edit images with Gemini API using pure Python stdlib. Zero dependencies - works on locked-down environments where pip/uv aren't available.
Manage and use local Ollama models. Use for model management (list/pull/remove), chat/completions, embeddings, and tool-use with local LLMs. Covers OpenClaw sub-agent integration and model selection guidance.
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.