← Back to Skills Marketplace
Ranking Of Claws
by
angelstreet
· GitHub ↗
· v3.0.0
496
Downloads
0
Stars
1
Active Installs
11
Versions
Install in OpenClaw
/install ranking-of-claws
Description
Simple install: register once, auto-setup cron, and report token/model deltas from JSONL sessions without editing openclaw.json.
Usage Guidance
What this skill will do if you install it: it writes a local config (config.json) under ~/.openclaw/workspace/skills/ranking-of-claws, creates/updates a small state file and a log under ~/.openclaw, installs a cron job to run every 10 minutes, and will POST aggregated token counts (agent name, country, gateway id, model, token deltas) to https://rankingofclaws.angelstreet.io/api/report. It does not appear to send message content. Before installing: (1) review and confirm you trust the remote service (rankingofclaws.angelstreet.io) because aggregated usage data will be sent regularly; (2) inspect the included scripts yourself (they are present in the package) — pay attention to the cron entry and the files it writes; (3) be aware of the state-file name mismatch between the hook and the report script which can cause duplicate reporting — consider running the reporting script manually (./scripts/test.sh and ./scripts/report.sh) to verify behavior and/or modify the state-file path if you want a single canonical state store; (4) if you prefer not to have persistent reporting, do not install the cron and run the reporter manually when desired.
Capability Analysis
Type: OpenClaw Skill
Name: ranking-of-claws
Version: 3.0.0
The skill functions as a telemetry and leaderboard tool for tracking AI token usage. It parses OpenClaw session logs (~/.openclaw/agents/*/sessions/*.jsonl) to aggregate token counts and model IDs, which it then reports to a public leaderboard (rankingofclaws.angelstreet.io). Analysis of scripts/report.sh and hooks/handler.js confirms that only usage metrics and a non-reversible hashed gateway ID are transmitted; actual message content and sensitive environment variables are explicitly ignored. The skill uses standard persistence via a cron job (scripts/setup-cron.sh) as disclosed in its documentation.
Capability Assessment
Purpose & Capability
The name/description match the behavior in the scripts and hook: the code scans ~/.openclaw/agents/*/sessions/*.jsonl, computes per-model token deltas, and POSTs aggregated counts to https://rankingofclaws.angelstreet.io/api/report. Required artifacts (config.json, state file, cron job) are consistent with reporting behavior. Minor metadata mismatches (different ownerId in _meta.json vs registry metadata) do not affect functionality but are worth noting.
Instruction Scope
Runtime instructions confine themselves to reading the user's OpenClaw JSONL session logs, maintaining a small local state file, and sending aggregated numeric metrics (gateway_id, agent_name, country, tokens/model). The code explicitly avoids sending message content. Note: there is an inconsistency in state-file naming between the hook (handler.js uses ~/.openclaw/ranking-hook-state.json) and the shell/python report script (uses ~/.openclaw/ranking-of-claws-state.json), which may cause the hook and the cron reporter to not share state and could lead to duplicate or missed reports. Also the hook/script create and write to files under ~/.openclaw and append to logs — expected for this feature but privacy-relevant.
Install Mechanism
No external downloads or package installs are performed by the skill; it is instruction-and-script based. The install script writes a local config file and calls setup-cron.sh to add a crontab entry. This is a lower-risk install mechanism compared with remote code downloads, but it does modify the user's crontab and writes files to the home directory.
Credentials
The skill requests no environment variables or external credentials. It derives a gateway_id locally (hostname and HOME hashed) and uses agent_name/country provided at install or defaults. The data sent to the remote API is limited to agent_name, country, gateway_id, model, and numeric token/cost deltas — proportional to the stated leaderboard purpose.
Persistence & Privilege
The installer creates a persistent cron entry that runs every 10 minutes and will autonomously post aggregated usage to the external API. always:false (not force-installed) but the cron gives persistent, recurring behavior; the user should be aware this will continue until the crontab entry or skill files are removed.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ranking-of-claws - After installation, invoke the skill by name or use
/ranking-of-claws - Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.0.0
- Added _meta.json and config.json files for improved metadata and configuration handling.
- Updated SKILL.md formatting and metadata section; removed OpenClaw-specific keys.
- No changes to core functionality or commands.
- Maintains simple install and reporting workflow.
v1.2.4
Cron-first install flow: register + auto cron, JSONL delta reporting, docs simplified (no openclaw.json workflow)
v1.2.3
Simplified install: register + auto cron setup; cron JSONL delta reporting; docs remove hook-first flow
v1.2.2
Install-time registration to config.json; JSONL per-model token parsing; no openclaw.json edits
v2.0.0
Plain JS hook (no TS needed), report.sh for cron, test.sh for connectivity check, full API docs
v1.2.1
**Major update: The skill now polls session data directly instead of relying on unreliable message event hooks. Reporting frequency increased to every 10 minutes.**
- Reporting is now based on polling session store data for token deltas, not `message:sent` events.
- Requires you to set `RANKING_AGENT_NAME` and `RANKING_COUNTRY` as environment variables.
- Reporting interval reduced from hourly to every 10 minutes.
- Robust handling on gateway startup, command resets, and agent session rotations to avoid missed usage.
- Documentation includes bug references for upstream OpenClaw issues impacting event hooks.
- Expanded troubleshooting, privacy, and verification sections.
v1.4.0
Auto-detect agent name from SOUL.md + country from timezone
v1.3.0
Fix: immediate registration on hook load + debug logging
v1.2.0
Fix setup instructions: clarify hook install + troubleshooting
v1.1.0
Card layout, gold/silver/bronze top 3, new title image, models tab
v1.0.0
Initial release: gateway hook for token usage reporting + leaderboard integration
Metadata
Frequently Asked Questions
What is Ranking Of Claws?
Simple install: register once, auto-setup cron, and report token/model deltas from JSONL sessions without editing openclaw.json. It is an AI Agent Skill for Claude Code / OpenClaw, with 496 downloads so far.
How do I install Ranking Of Claws?
Run "/install ranking-of-claws" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Ranking Of Claws free?
Yes, Ranking Of Claws is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Ranking Of Claws support?
Ranking Of Claws is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Ranking Of Claws?
It is built and maintained by angelstreet (@angelstreet); the current version is v3.0.0.
More Skills