caveman-setup

caveman-setup is a skill for Claude Code, Codex from mrDesign-ww/vault-os. It costs 82 tokens per session (2,875 once invoked), scanned A, a copy of caveman-setup, MIT.

A setup procedure for routing an app's large-language-model requests through Caveman Cloud, a gateway that records request cost, token use, and response time. It is designed to leave the app's behavior unchanged and requires a gateway URL and API key.

In plain words
What is it for?
Use it to connect every live LLM call in a repository to the gateway while keeping secrets in environment variables and checking the integration.
Why use it?
It adds visibility into LLM spending and performance without requiring a broad code refactor.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to connect every live LLM call in a repository to…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mrdesign-ww/vault-os/caveman-setup
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.

Any agent
npx skills add mrDesign-ww/vault-os --skill caveman-setup
Clone the repo
git clone --depth 1 https://github.com/mrDesign-ww/vault-os

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for caveman-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrdesign-ww/vault-os/caveman-setup.svg)](https://agentmods.dev/skills/mrdesign-ww/vault-os/caveman-setup)
Your own site
<a href="https://agentmods.dev/skills/mrdesign-ww/vault-os/caveman-setup"><img src="https://agentmods.dev/badge/skills/mrdesign-ww/vault-os/caveman-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,875 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00082 $0.02875
Opus 5 $0.00041 $0.01437
Sonnet 5 $0.00016 $0.00575
Haiku 4.5 $0.00008 $0.00287

Measured yesterday against content hash 254ddc40c355, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

caveman-setup scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

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

cheapest path if it has a script for it, otherwise curl **on the path matching
Origin

This is a copy

100% identical to caveman-setup — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

shell/claude/skills/caveman-setup/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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_KEYSstored (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)

If any value is missing, stop and ask for it. Do not guess a URL or mint a key.

Rules (non-negotiable)

  1. Coherent integration. Wire every live LLM callsite through existing configuration and responsible seams. Touch each layer correctness requires. No drive-by refactors or formatting sweeps; add an abstraction only when it clarifies ownership or lowers lifecycle cost.
  2. Secrets stay in env vars. CAVE_API_KEY goes into the env file the repo already uses (.env, .env.local, …). If that file isn't gitignored, add it to .gitignore and say so. Never hardcode the key in source.
  3. Report only what you observed. The final report states the HTTP status and usage numbers from the real verification response — never assumed success. If verification fails, report the failure template instead.
  4. Record mode only. You are adding measurement. You do not enable any optimization, and you do not claim any savings — verified savings are $0 until an optimizer is explicitly turned on and passes its eval gate.
  5. Provider keys are not your business. With PROVIDER_KEYS: stored you never see one. With byok, the app's existing provider key stays exactly where it already is.

Step 1 — Find every live LLM callsite

Read the full file on GitHub · 225 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. yesterday First seen · 225 lines · 82 tokens per session scan A 254ddc40c355

Subscribe to this mod's changes

caveman-setup is a skill published in the GitHub repository mrDesign-ww/vault-os (2 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 2,875 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to caveman-setup, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

mle-workflow

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

affaan-m/ECC · 44 tokens

pytorch-patterns

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

affaan-m/ECC · 32 tokens

architecture-design

Use only when creating new registrable ML components that require Factory or Registry patterns.

Galaxy-Dawn/claude-scholar · 19 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens

memstack-seo-ai-search-visibility

Use this skill when the user says 'AI search', 'AI visibility', 'ChatGPT ranking', 'Perplexity optimization', 'GEO', 'generative engine optimization', or needs to optimize content for AI-powered search engines and LLM citations. Do NOT use for traditional SEO audits or Google Ads.

cwinvestments/memstack · 71 tokens

huggingface-llm-trainer

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

waybarrios/opencode-power-pack · 65 tokens