caveman-discover
Find every LLM workflow in the current repository and label it, so Caveman Cloud groups spend by what the code actually does (support-reply, nightly-digest) instead of one anonymous bucket. Use when the user pastes the Caveman discovery prompt, says "discover workflows", or asks to break LLM spend down by workflow. The repo should already route through the Caveman gateway (the caveman-setup skill does that part).
Install
git clone https://github.com/JuliusBrussee/caveman /tmp/caveman && ln -s /tmp/caveman/skills/caveman-discover ~/.claude/skills/caveman-discoverFrom README
Step 1 — Inventory the workflows Walk the repo from its entry points, not from its imports: HTTP/RPC handlers that call an LLM (directly or through layers) Scheduled jobs: cron definitions, queue consumers, workers, GitHub Actions that invoke LLM code CLI commands and scripts (scripts/, bin/, package.json scripts) Eval / test harnesses that burn real tokens Distinct agents or chains inside a framework (each LangGraph graph, each crew, each agent definition is usually its own workflow) One workflow = one job a human would name. Ten callsites inside the same request handler are one workflow; one shared llm.ts helper used by three jobs is three workflows (label at the callers, never the shared helper). Step 2 — Name them Slug grammar (the gateway enforces this): lowercase [a-z0-9-], 1–96 chars.
More from this repo
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
caveman-evidence-review
Used to review Caveman Cloud evidence read-only: costs, Cave Score, Cave Plan, workflows, traces, latency, errors,...
cavecrew
Decision guide for delegating to caveman-style subagents.