Caveman Cloud evidence review: where your LLM spend goes
Read-only audit of Caveman cost evidence — measured list-price cost, Cave Score, traces, latency, errors, routing, verified savings
- What
- Read-only audit of Caveman cost evidence — measured list-price cost, Cave Score, traces, latency, errors, routing, verified savings
- Cost
- Free
- Needs
- a Caveman Cloud account with the caveman CLI (or MCP) configured and a project selected — the skill is a read-only methodology, nothing to deploy
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Selected by Skill Harbor — short listing (the repo states no license, so no content is reproduced): @juliusbrussee's read-only review workflow for Caveman Cloud evidence — answer "where does the LLM spend go" without ever changing anything. Hard rules: keep measured provider list-price cost, inferred daily headroom, verified ledger savings and evidence cost strictly separate; never fetch payloads (metadata, timing, token counts and status are enough); never supply an organization id; cite trace ids and exact time windows. The workflow: load context (caveman_context or caveman cloud CLI), establish a baseline (caveman_report for overview/costs/score/workflows/verified_savings, caveman_plan for ranked headroom), test the leading explanation against bounded trace searches with a control cohort (never infer causality from one expensive trace), inspect representative traces, and report in a fixed shape — scope, measured cost, verified savings, inferred headroom, findings with trace ids, an "unproven" section, one next read-only check, and a proposal-only possible action. Never start, approve, cancel or roll back an experiment from this skill. Honest caveats: requires a Caveman Cloud account with the caveman CLI/MCP configured and a selected project; the evidence discipline is demanding — empty results mean no signal, not zero cost; license not stated by the source repo — short listing with a link only, nothing copied. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Caveman Cloud evidence review is a free Muse skill offering a read-only audit of Caveman cost evidence, answering where your LLM spend goes without ever changing anything. It covers measured list-price cost, Cave Score, traces, latency, errors, routing and verified savings, keeping measured provider list prices separate from estimates.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 2e08b91Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a Caveman Cloud account with the caveman CLI (or MCP) configured and a project selected — the skill is a read-only methodology, nothing to deploy Install "Caveman Cloud evidence review: where your LLM spend goes" for me. It gives my agent @juliusbrussee's read-only evidence-review workflow: keep measured cost, inferred headroom, verified savings and evidence cost separate; establish a baseline with caveman_report/caveman_plan; test the leading explanation against bounded trace searches with a control cohort; inspect representative traces; and report findings with trace ids, an "unproven" section and one next read-only check — never starting, approving, canceling or rolling back anything. IMPORTANT: the repo states no license — fetch from the link only, and reproduce nothing beyond the link. Repository: https://raw.githubusercontent.com/juliusbrussee/caveman/2e08b9177c07bb7249a8a2d1a6758e5db281d002/skills/caveman-evidence-review/SKILL.md Pinned version: install the code at commit 2e08b9177c07bb7249a8a2d1a6758e5db281d002 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "caveman-evidence-review". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. log in with `caveman login` and select a project — the agent must never guess; nothing else). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 2e08b91 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.