Caveman Setup

Caveman-setup walks an agent through routing every LLM call in a repo through the Caveman Cloud gateway, so spend and request volume get measured without changing what the app sends. It hunts down live callsites across the OpenAI, Anthropic, Vercel AI, LangChain and LiteLLM clients, swaps the base URL to `/w/<app>` and adds the gateway auth header, then fires one tiny verification request and reports only the status and usage numbers it actually saw. The part I like is the restraint: it refuses to invent an integration when there are no callsites, keeps the key in env vars, and won't claim any savings while the gateway is in record mode. The catch is that it assumes you already have a Caveman account and a gateway key, and it will spend a real (if small) request to verify, so run it on a repo where that's fine.

skills.sh installs: 118K
GitHub stars: 118.7K
last updated: Oct 26, 2026

View on GitHub

Install

$ npx -y skills add juliusbrussee/caveman --skill caveman-setup --agent claude-code

Installs into .claude/skills of the current project.

Files

You are wiring this repository through the Caveman gateway. Caveman is a byte-preserving LLM proxy: in record mode it measures what your app sends and what it costs, and changes nothing else. Your job is a minimal, verified integration — not a refactor.

The prompt that sent you here provides four values. Refer to them as:

GATEWAY — the gateway base URL (e.g. https://gateway.caveman.so or http://127.0.0.1:8787)
CAVE_API_KEY — the gateway auth secret (treat like any API key: env var only, never committed, never printed in full)
PROVIDER_KEYS — stored (provider keys live encrypted in Caveman Cloud) or byok (this app sends its own provider key per request)
DASHBOARD — the dashboard base URL (e.g. https://app.caveman.so)