claude-code

A support layer that lets Claude Code use selected free model providers during an explicitly launched FreeRide session. Claude Code is a coding assistant interface, while FreeRide leaves ordinary Claude sessions unchanged.

In plain words
What is it for?
Use it to install and configure FreeRide, launch Claude through it, and select free providers optimized for speed, quality, routing, or coding.
Why use it?
It lets users switch between their Claude subscription and free providers for individual requests while keeping the conversation history.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/shaivpidadi/freeridev3/claude-code
Clone the repo
git clone --depth 1 https://github.com/Shaivpidadi/FreeRideV3
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,163 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.03163
Opus 5 $0.00000 $0.01581
Sonnet 5 $0.00000 $0.00633
Haiku 4.5 $0.00000 $0.00316

Measured 2d ago against content hash 54b314b1cc35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

claude-code scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -sSL https://api.free-ride.xyz/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sSL https://api.free-ride.xyz/install.sh | sh
docs/agents/claude-code.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Claude Code with FreeRide

FreeRide is a support layer for Claude Code, not a replacement. Your Pro/Max subscription keeps working exactly as before. FreeRide steps in only when you explicitly opt in for a session — and inside that session, you can switch between your subscription and free providers per request.


TL;DR

# install (once)
curl -sSL https://api.free-ride.xyz/install.sh | sh
freeride init                 # collects free-tier provider keys

# any time you want free models available alongside Claude
freeride run claude           # same Claude UI, /model freeride/* now works

# plain `claude` is untouched — uses your subscription, no FreeRide in the path

Inside the wrapped Claude session:

> /model claude-opus-4-7          # your subscription answers
> /model freeride/free            # free providers answer (smart router)
> /model freeride/fast            # free providers, prefers groq (sub-100ms TTFT)
> /model freeride/quality         # free providers, prefers openrouter
> /model freeride/coding          # free providers, code-tuned models first

You flip per request. Conversation history is preserved across switches because Claude Code manages it client-side.


What freeride run claude actually does

  1. Probes http://localhost:11343/health. If the gateway isn't up, autospawns freeride serve in the background (log at ~/.freeride/autospawn.log).
  2. Sets ANTHROPIC_BASE_URL=http://localhost:11343 for the child process only. Your shell environment is untouched.
  3. Sets FREERIDE_ACTIVE=1 so the child (and the freeride doctor --claude-code probe) can detect "we're inside the wrapper."
  4. Passes through ANTHROPIC_AUTH_TOKEN / ANTHROPIC_API_KEY if you have them — never fabricates or modifies them.
  5. execvpes into claude. From this point on the wrapper is out of the way; Ctrl-C, signals, and exit codes behave exactly as without the wrapper.

Outside the wrapper, plain claude hits api.anthropic.com directly. No magic. No system-wide change. No /etc/hosts mutation. Reversible by not typing freeride run.

Read the full file on GitHub · 201 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 201 lines · 0 tokens per session scan C 54b314b1cc35

Subscribe to this mod's changes

claude-code is an agent published in the GitHub repository Shaivpidadi/FreeRideV3 (42 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,163 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.