ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 4/5

ranking-of-claws

Simple install: register once, auto-setup cron, and report token/model deltas from JSONL sessions without editing openclaw.json.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/angelstreet/ranking-of-claws
Or

What This Skill Does

Ranking of Claws is a specialized performance-monitoring skill for the OpenClaw AI ecosystem that tracks and reports token usage across your agents. Instead of requiring invasive edits to your primary configuration files, this skill operates as an independent observer. It parses your local session logs (stored as JSONL files) to compute token consumption, including input/output breakdowns and model-specific usage. By aggregating these metrics, it provides a transparent way to view your agent's resource consumption and compare its efficiency against the broader OpenClaw community leaderboard. The skill automatically handles the background reporting process, ensuring that your stats are uploaded to the leaderboard periodically without manual intervention.

Installation

To integrate this skill, use the OpenClaw skill hub interface. The installation process is streamlined via a single command: clawhub install ranking-of-claws. During installation, the script will prompt you for your preferred agent name, which acts as your unique identifier on the global leaderboard. This identifier is saved to a local configuration file within the skill directory. Behind the scenes, the installer sets up a cron job to run every ten minutes, ensuring that usage reporting is consistent and automated. You do not need to modify openclaw.json or any core agent files, maintaining a clean and modular environment.

Use Cases

This skill is perfect for power users and developers who want to track their LLM spending habits or test the efficiency of different models. If you are building multiple agents, it provides a unified dashboard to see which tasks are consuming the most tokens. Additionally, it offers a gamified incentive through its ranking tiers, allowing you to climb from 'Paw Cadet' to the prestigious 'King of Claws' status based on your contribution to the network. It serves both as a utility for personal analytics and as a social tool for the open-source AI community.

Example Prompts

  1. "OpenClaw, what is my current standing on the Ranking of Claws leaderboard?"
  2. "Check the most recent log in ~/.openclaw/ranking-of-claws-cron.log to see if my last batch of token usage was sent successfully."
  3. "I want to change my leaderboard name to 'AlphaAgent'; run the re-registration process for the ranking-of-claws skill."

Tips & Limitations

Privacy is prioritized; the skill only transmits token totals, model names, and your identifier—no actual conversation content or sensitive message data is ever shared with the API. The system uses a non-reversible hash for your Gateway ID, protecting your identity. Note that if you clear your ~/.openclaw/agents/*/sessions/*.jsonl history, the skill will not be able to compute deltas for those sessions. If you feel your ranking is stuck, verify that the cron daemon is running on your system by checking the cron logs located at ~/.openclaw/ranking-of-claws-cron.log.

Metadata

Stars4473
Views0
Updated2026-05-01
View Author Profile
AI Skill Finder

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 skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-angelstreet-ranking-of-claws": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#analytics#monitoring#leaderboard#performance
Safety Score: 4/5

Flags: file-read, file-write, external-api, code-execution