Is the Freeride skill free?

Yes. The skill itself is free from Shaivpidadi/FreeRide. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Freeride SkillProof Score?

5.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 0/10, docs & honesty 4/5.

How do I install Freeride?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Freeride with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Freeride

Configures OpenClaw to use free OpenRouter models with ranked rate-limit fallbacks

by Shaivpidadi · Shaivpidadi/FreeRide

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 5.6/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 91fdb7a

Fetched SKILL.md, skill.json, README.md and source via the GitHub raw API. Frontmatter parses cleanly (name+description+env+network+writes); all three body-referenced files (main.py, watcher.py, setup.py) return HTTP 200, and main.py confirms the described behavior: it GETs openrouter.ai/api/v1/models, ranks with the documented 0.4/0.3/0.2/0.1 weights, and writes ~/.openclaw/openclaw.json. Could NOT measure output vs baseline: every command (freeride auto/list/switch) needs a real OPENROUTER_API_KEY, live openrouter.ai access, and the OpenClaw platform to write into — none runnable in my context. Security note: the README's curl|sh one-liner is for the separate FreeRideV3 project, not this skill; this skill only sends an app-attribution HTTP-Referer header to OpenRouter and does not exfiltrate the key.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 0/10
Docs & honesty 4/5

What Freeride does

A CLI skill that ranks OpenRouter's free AI models by context length, capabilities, recency, and provider trust, then writes the best one plus a fallback chain into ~/.openclaw/openclaw.json for the OpenClaw agent. Triggers when the user mentions free AI, OpenRouter, model switching, rate limits, or reducing AI API costs. Requires the OpenClaw platform, an OpenRouter API key, and network access to openrouter.ai.

How to install Freeride

git clone --depth 1 https://github.com/Shaivpidadi/FreeRide.git ~/.claude/skills/freeride
# Skill body targets the OpenClaw agent platform, not Claude Code directly.
# To actually run the CLI it configures:
#   pip install -e ~/.claude/skills/freeride
#   export OPENROUTER_API_KEY="sk-or-v1-..."   # free key at openrouter.ai/keys
#   freeride auto && openclaw gateway restart
# Requires: OpenClaw installed (Node >=22), Python 3.8+, network to openrouter.ai

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Freeride

/freeride Configures OpenClaw to use free OpenRouter models with ranked rate-limit fallbacks

It also activates on plain-language prompts like these:

Set up free model fallbacks for OpenClaw
Rank the best free OpenRouter models available
Reduce my AI costs by switching to free models

Frequently asked questions

Is the Freeride skill free?: Yes. The skill itself is free from Shaivpidadi/FreeRide. SkillProof publishes the install command and an independent test verdict at no cost.
Does Freeride work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Works with setup. Fetched SKILL.md, skill.json, README.md and source via the GitHub raw API. Frontmatter parses cleanly (name+description+env+network+writes); all three body-referenced files (main.py, watcher.py, setup.py) return HTTP 200, and main.py confirms the described behavior: it GETs openrouter.ai/api/v1/models, ranks with the documented 0.4/0.3/0.2/0.1 weights, and writes ~/.openclaw/openclaw.json. Could NOT measure output vs baseline: every command (freeride auto/list/switch) needs a real OPENROUTER_API_KEY, live openrouter.ai access, and the OpenClaw platform to write into — none runnable in my context. Security note: the README's curl|sh one-liner is for the separate FreeRideV3 project, not this skill; this skill only sends an app-attribution HTTP-Referer header to OpenRouter and does not exfiltrate the key.
What is the Freeride SkillProof Score?: 5.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 0/10, docs & honesty 4/5.
How do I install Freeride?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Freeride with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.