free
v1.0.0Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates opencla...
⭐ 0· 115·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, SKILL.md, README, skill.json and the Python code all focus on discovering/ranking OpenRouter free models and updating ~/.openclaw/openclaw.json; network calls go to openrouter.ai which is expected. Minor metadata mismatch: the registry summary shown at the top listed 'Required env vars: none' while skill.json and the code clearly require OPENROUTER_API_KEY.
Instruction Scope
Runtime instructions ask the agent to ensure OPENROUTER_API_KEY is set, install the package locally, run the provided freeride commands, and restart the OpenClaw gateway. The code follows that scope: it fetches models from OpenRouter, ranks them, and updates only agents.defaults.model / agents.defaults.models in openclaw.json; it also reads/writes local cache (.freeride-cache.json) and watcher state (.freeride-watcher-state.json). No instructions or code attempt to read unrelated system secrets or send data to unexpected external endpoints.
Install Mechanism
No remote arbitrary downloads. Installation is via pip install -e . from the skill workspace (setup.py) and depends only on requests. setup.py registers console scripts for freeride and freeride-watcher — this is proportionate for CLI tooling.
Credentials
The only secret the skill needs is OPENROUTER_API_KEY (the code looks for it in the environment or in openclaw.json env). That is appropriate for the stated purpose. Note the earlier registry summary that listed 'no required env vars' is inconsistent with skill.json and SKILL.md which mark OPENROUTER_API_KEY required.
Persistence & Privilege
The skill writes to its own cache and watcher state under ~/.openclaw and updates only specific OpenClaw config keys (agents.defaults.model, agents.defaults.models). It does not request always:true, does not modify other skills, and does not request broader system privileges.
Assessment
This skill appears to do what it says: it requires your OpenRouter API key, fetches/ranks free models from openrouter.ai, and writes changes to ~/.openclaw/openclaw.json plus two local files (.freeride-cache.json and .freeride-watcher-state.json). Before installing: 1) Verify you trust the skill source (author and repo link in skill.json). 2) Back up ~/.openclaw/openclaw.json so you can revert changes. 3) Prefer installing in a Python virtualenv (pip install -e .) rather than system Python. 4) Inspect the files yourself if uncomfortable (the code is present and readable). 5) Note the small metadata mismatch (registry said no required env vars while the skill actually requires OPENROUTER_API_KEY); ensure you only provide an API key you control and are comfortable being used by this skill. If you run the watcher daemon, it will periodically make test requests to OpenRouter using your key — treat that as normal network activity tied to this skill.Like a lobster shell, security has layers — review code before you run it.
latestvk97ffpfh5pmrcc2fhxak51vd4n83ae47
License
MIT-0
Free to use, modify, and redistribute. No attribution required.