Free Ride 1

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 and instructions match its stated purpose (managing OpenRouter free models for OpenClaw); the main incoherence is metadata mismatches (registry listing shows no required env/config when the packaged files clearly require and use an OPENROUTER_API_KEY and an OpenClaw config path).

Purpose & Capability

The skill's name and description (manage free OpenRouter models and configure fallbacks) align with the bundled code and runtime instructions. It legitimately needs an OpenRouter API key and access to OpenClaw's config (~/.openclaw/openclaw.json) to perform its work. However, the top-level registry metadata included with the submission claims no required env vars or config paths, while skill.json, SKILL.md, and the Python code clearly require OPENROUTER_API_KEY and reference ~/.openclaw/openclaw.json — this metadata mismatch is an incoherence to be aware of.

Instruction Scope

SKILL.md instructs the agent to install the package locally, set OPENROUTER_API_KEY, run 'freeride' commands, and restart the OpenClaw gateway. The code and instructions only read and modify the OpenClaw config, cache and state files under ~/.openclaw, and call OpenRouter APIs — all within the announced scope. The watcher optionally runs as a daemon and performs periodic health checks; it is explicit and user-invocable.

Install Mechanism

There is no platform install spec in the registry entry (instruction-only), but the package includes setup.py and SKILL.md / README instruct using 'pip install -e .' from the local skill directory. That installs local console scripts (freeride, freeride-watcher) via setuptools. This is a common and expected install method, but the registry metadata omission (no install spec) is inconsistent with the packaged setup.py and recommended install steps.

Credentials

The code requires a single credential: OPENROUTER_API_KEY, which is appropriate for calling OpenRouter and is declared in skill.json and explained in SKILL.md. The initial registry summary incorrectly listed no required env vars — an inconsistency. The skill reads/writes only OpenClaw-related config and per-skill cache/state files under ~/.openclaw, which is proportionate to its purpose.

Persistence & Privilege

The skill does not request always:true and is user-invocable. It can be run as a background watcher/daemon if the user chooses; this creates state files under ~/.openclaw for rate-limit tracking and rotation history, which is reasonable for its stated functionality. It does not attempt to modify other skills or system-wide settings beyond the OpenClaw config it is designed to manage.

Assessment

This skill appears to do what it says: it fetches free models from OpenRouter using your OPENROUTER_API_KEY, ranks them, and updates ~/.openclaw/openclaw.json to set primary and fallback models. Before installing: 1) Note the metadata mismatch — the registry summary omitted the required OPENROUTER_API_KEY and config path; treat the skill.json/SKILL.md as authoritative. 2) Back up ~/.openclaw/openclaw.json so you can restore your original config if needed. 3) Only provide an OpenRouter API key you control (no broader credentials are required). 4) Inspect the package locally before running pip install -e . If you run the watcher daemon, understand it will periodically call OpenRouter (using your key) and update your config; run it only if you want an automated rotation service. Overall the package is coherent with its purpose, but the metadata inconsistencies and the fact it will modify your OpenClaw config and run network calls warrant the usual caution and review before installation.

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