free

Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates opencla...

Security Scan

The skill's code, README, and runtime instructions are consistent with its stated purpose (managing OpenRouter free models for OpenClaw); it only needs an OpenRouter API key and updates OpenClaw config and local cache/state files.

Purpose & 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.

FreeRide - Free AI for OpenClaw

What This Skill Does

Configures OpenClaw to use free AI models from OpenRouter. Sets the best free model as primary, adds ranked fallbacks so rate limits don't interrupt the user, and preserves existing config.

Prerequisites

Before running any FreeRide command, ensure:

1. OPENROUTER_API_KEY is set. Check with echo $OPENROUTER_API_KEY. If empty, the user must get a free key at https://openrouter.ai/keys and set it:

   export OPENROUTER_API_KEY="sk-or-v1-..."
   # Or persist it:
   openclaw config set env.OPENROUTER_API_KEY "sk-or-v1-..."
   

2. The freeride CLI is installed. Check with which freeride. If not found:

   cd ~/.openclaw/workspace/skills/free-ride
   pip install -e .
   

Primary Workflow

When the user wants free AI, run these steps in order:

# Step 1: Configure best free model + fallbacks
freeride auto

# Step 2: Restart gateway so OpenClaw picks up the changes
openclaw gateway restart

That's it. The user now has free AI with automatic fallback switching.

Verify by telling the user to send /status to check the active model.

Commands Reference

Command	When to use it
freeride auto	User wants free AI set up (most common)
freeride auto -f	User wants fallbacks but wants to keep their current primary model
freeride auto -c 10	User wants more fallbacks (default is 5)
freeride list	User wants to see available free models
freeride list -n 30	User wants to see all free models
freeride switch <model>	User wants a specific model (e.g. freeride switch qwen3-coder)
freeride switch <model> -f	Add specific model as fallback only
freeride status	Check current FreeRide configuration
freeride fallbacks	Update only the fallback models
freeride refresh	Force refresh the cached model list

After any command that changes config, always run openclaw gateway restart.

What It Writes to Config

FreeRide updates only these keys in ~/.openclaw/openclaw.json:

• agents.defaults.model.primary — e.g. openrouter/qwen/qwen3-coder:free
• agents.defaults.model.fallbacks — e.g. ["openrouter/free", "nvidia/nemotron:free", ...]
• agents.defaults.models — allowlist so /model command shows the free models

Everything else (gateway, channels, plugins, env, customInstructions, named agents) is preserved.

The first fallback is always openrouter/free — OpenRouter's smart router that auto-picks the best available model based on the request.

Watcher (Optional)

For auto-rotation when rate limited, the user can run:

freeride-watcher --daemon    # Continuous monitoring
freeride-watcher --rotate    # Force rotate now
freeride-watcher --status    # Check rotation history

Troubleshooting

Problem	Fix
freeride: command not found	cd ~/.openclaw/workspace/skills/free-ride && pip install -e .
OPENROUTER_API_KEY not set	User needs a key from https://openrouter.ai/keys
Changes not taking effect	openclaw gateway restart then /new for fresh session
Agent shows 0 tokens	Check freeride status — primary should be openrouter/<provider>/<model>:free