model-usageUse 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.
Install via ClawdBot CLI:
clawdbot install steipete/model-usageInstall CodexBar (brew cask):
Install CodexBar (brew cask)Requires:
Grade Excellent — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Feb 15, 2026
Development teams using multiple AI models (Codex/Claude) track per-model spending to optimize their budget. The skill helps identify which models are driving costs during daily development cycles, enabling teams to adjust usage patterns or switch to more cost-effective models for specific tasks.
Freelancers using AI tools for client work need to attribute costs to specific projects. This skill allows them to generate per-model usage reports that can be included in client invoices, providing transparency about which AI services were utilized and their associated costs for each project.
Early-stage startups with limited budgets need to monitor AI spending closely. The skill helps founders track which models (Codex vs Claude) are being used most and at what cost, enabling data-driven decisions about which AI services to prioritize as they scale their operations.
Academic or corporate research labs testing multiple AI models need to compare not just performance but also costs. This skill provides structured cost breakdowns that researchers can use alongside performance metrics to determine the most cost-effective models for their specific research tasks.
Marketing or content agencies using AI for client deliverables need to allocate costs across departments. The skill helps managers understand which teams are using which models, enabling better resource planning and ensuring high-cost models are reserved for premium client work where they provide the most value.
Offer AI cost monitoring as a service to businesses using multiple AI models. Provide detailed breakdowns showing which models drive expenses, helping clients optimize their AI spending. Charge monthly subscription fees based on the number of models monitored and reporting frequency.
Consult with companies to analyze their AI usage patterns and recommend cost-saving strategies. Use the skill's data to identify expensive model usage and suggest alternatives or usage patterns that maintain quality while reducing costs. Charge project-based or retainer fees.
Build the skill into larger AI management platforms that handle multiple providers. Offer automated cost tracking alongside other features like performance monitoring and compliance checks. Generate revenue through platform licensing or enterprise contracts with larger organizations.
💬 Integration Tip
Install CodexBar CLI first via Homebrew, then ensure the Python script can access the cost JSON output. For automation, set up scheduled runs to generate daily usage reports.
Scored Apr 19, 2026
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.
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.
AI-native OCR platform that turns documents into high-accuracy data in minutes. Using multi-model consensus, DeepRead achieves 97%+ accuracy and flags only uncertain fields for Human-in-the-Loop (HIL) review—reducing manual work from 100% to 5-10%. Zero prompt engineering required.