token-panel-ultimate
Know exactly where your AI tokens go. Multi-provider tracking, budget alerts, and a REST API—all in one dashboard.
Why use this skill?
Track Anthropic, OpenAI, Gemini, and Manus tokens in one local dashboard. Set budget alerts, access via REST API, and gain full control over your AI costs.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/globalcaos/token-panel-ultimateWhat This Skill Does
Token Panel Ultimate serves as your unified command center for AI spending. It is a comprehensive observability tool that aggregates usage data from Anthropic, Gemini, OpenAI, and Manus into a single, localized SQLite database. By centralizing your consumption metrics, it eliminates the need to navigate across disparate developer consoles to calculate your monthly burn rate. The skill runs as a lightweight daemon, featuring a robust REST API on port 8765 that allows for programmatic access to your token logs. Beyond simple tracking, it provides a crucial budget alerting system, ensuring you are notified of potential overages before they appear on your credit card statement.
Installation
To integrate this into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/globalcaos/token-panel-ultimate
Ensure that you have the necessary system-level permissions to run the background daemon. Once installed, navigate to the source directory and run pip install -r requirements.txt, followed by python3 api.py to initialize the SQLite storage backend and start the collection service. The system is designed to be zero-dependency, requiring no external databases like Redis or Postgres, making it ideal for self-hosted or local deployments.
Use Cases
Token Panel Ultimate is designed for power users, solo developers, and small teams who utilize multiple LLM providers concurrently. It is essential for:
- Cost Optimization: Identifying which specific AI model or provider is consuming the majority of your budget.
- Budget Enforcement: Setting strict monthly caps to prevent surprise invoices after intense development or data processing sessions.
- Custom Reporting: Using the REST API to feed your own business intelligence dashboards or internal Slack notifications.
- Audit Trails: Maintaining a local, queryable history of every token spent across your development lifecycle.
Example Prompts
- "@token-panel-ultimate list all my spending for OpenAI for the last 30 days."
- "@token-panel-ultimate set a budget limit of $50 for Anthropic and warn me when I hit 80 percent."
- "@token-panel-ultimate show me the current total cost across all providers today."
Tips & Limitations
- Security: Since this runs as a local daemon and tracks usage data, ensure your local filesystem permissions are restricted to the user running the OpenClaw agent.
- Data Integrity: Because the skill relies on local SQLite storage, ensure you have a backup strategy for the database file if you plan on tracking years of historical data.
- Scope: The skill automatically parses OpenClaw transcripts, but manual tracking for external API usage outside of OpenClaw may require custom integration via the REST API.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-globalcaos-token-panel-ultimate": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api
Related Skills
jarvis-voice
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
shell-security-ultimate
Classify every shell command as SAFE, WARN, or CRIT before your agent runs it.
memory-pioneer
Benchmark your agent's memory. Contribute anonymized scores to open research. Citizen science for AI memory.
subagent-overseer
Monitor sub-agent health and progress via a pull-based bash daemon. Use when spawning sub-agents that need progress tracking, staleness detection, and automatic status reporting. Replaces manual heartbeat polling with a deterministic status file the agent reads every 3 minutes. Zero AI tokens for monitoring — pure OS-level process checks and filesystem diffs.
model-router
Automatic LLM model selection for sub-agent tasks. Classifies tasks by complexity and type, then routes to the optimal model (cost vs capability). Use when spawning sub-agents, choosing models for cron jobs, or deciding which model to use for any task. Eliminates manual model specification by providing a decision tree and optional cheap-model classifier for ambiguous cases.