Free Ride - Unlimited free AI

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) but there are inconsistencies in the declared metadata (registry vs skill.json/SKILL.md), and it installs/runs a daemon that can autonomously modify your OpenClaw config — so review before installing.

Purpose & Capability

The skill's code, README, and SKILL.md all clearly implement OpenRouter free-model discovery, ranking, and updating of ~/.openclaw/openclaw.json. That functionality is coherent with the name/description. However, the registry summary at the top of this package evaluation claims "Required env vars: none" and "Primary credential: none", while skill.json and SKILL.md require OPENROUTER_API_KEY and the code reads it. This metadata mismatch is an incoherence that could mislead less-technical users.

Instruction Scope

The SKILL.md instructs installing the package, setting OPENROUTER_API_KEY, running CLI commands (freeride auto, list, switch, etc.) and restarting the OpenClaw gateway. The code performs exactly those actions: it queries OpenRouter, ranks models, and updates only the OpenClaw keys under agents.defaults.model and agents.defaults.models. It also creates a cache file (~/.openclaw/.freeride-cache.json) and a watcher state file (~/.openclaw/.freeride-watcher-state.json). These file reads/writes are within the declared purpose but are persistent changes to your OpenClaw config and state.

Install Mechanism

There is no high-risk remote download; the package is a standard Python package with setup.py and a normal pip editable install recommended in SKILL.md/README. The skill.json includes an install string invoking npx clawhub and pip install -e ., and README describes the same. The mismatch between 'No install spec' in the registry summary and the presence of an install string is an inconsistency to be aware of, but the install mechanism itself is a common pip install from local workspace (moderate risk, expected for CLI skills).

Credentials

The skill requires OPENROUTER_API_KEY to call OpenRouter — that single credential is proportional to the task. However, the registry metadata incorrectly listed no required env vars while skill.json marks the key as required and SKILL.md instructs the user to set it. That discrepancy is concerning because it could hide the fact that a secret (API key) is needed and used. The code reads the key from environment or from the OpenClaw config; no other unrelated secrets or credentials are requested.

Persistence & Privilege

The watcher can run as a daemon and will autonomously monitor and rotate models, updating OpenClaw config files and writing a watcher state file. always:false (not force-included) and disable-model-invocation:false (normal) — so the skill can be invoked autonomously by agents. Combined with the ability to modify ~/.openclaw/openclaw.json, this gives it meaningful persistent influence over your agent's behavior. This is coherent with the skill's purpose but worth conscious consideration before enabling daemon/autonomous behavior.

What to consider before installing

What to check before installing: - Metadata mismatch: The registry summary omitted required env vars but skill.json and SKILL.md require OPENROUTER_API_KEY. Treat that as a red flag: the skill will use an API key and make network calls to openrouter.ai. - Review and back up: Backup ~/.openclaw/openclaw.json before running the installer or any freeride commands (the skill updates agents.defaults.model and agents.defaults.models). - Inspect the code: The bundled Python files are readable and make requests only to openrouter.ai and write cache/state under ~/.openclaw — review them yourself if you can. If you cannot, restrict installation to an isolated environment. - Daemon behavior: The freeride-watcher can run as a daemon and will autonomously rotate models; don’t enable or run the watcher as a system daemon unless you trust the code and the key you provide. - Limit the API key: Use a dedicated OpenRouter key (not shared credentials) and revoke it if you stop using the skill. - Verify provenance: The skill references a GitHub repo but the registry homepage is missing. Try to locate and review the upstream repository (https://github.com/Shaivpidadi/FreeRide is mentioned) and confirm the author before trusting and enabling autonomous behavior. If you want me to, I can highlight exact lines in the code that read/write config, call the API, or persist state so you can inspect them quickly.

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