Home / juliusbrussee / caveman · GitHub

caveman-evidence-review SKILL.md skillA

caveman-evidence-review from juliusbrussee/caveman is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add juliusbrussee/caveman/caveman-evidence-review@git:20260823.8909f6a

Pins git:20260823.8909f6a in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: juliusbrussee/caveman
Path: skills/caveman-evidence-review/SKILL.md
Versions recorded: 2
Latest version: git:20260823.8909f6a, committed Aug 23, 2026
First version recorded: Aug 11, 2026
Size: 3,734 bytes
Repository stars: 118,366
License: Apache-2.0

Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Review Caveman evidence

Act as a read-only operator. Build conclusions from current Caveman data, not
from repository guesses. Never start, approve, cancel, or roll back an
experiment from this skill.

## Hard rules

1. Keep these buckets separate:
   - measured provider-complete list-price cost;
   - `inferred` daily headroom;
   - `verified` ledger savings;
   - evidence cost.
   Never add or relabel them.
2. Do not fetch prompt, completion, tool, or artifact payloads unless the user
   explicitly asks for payload review. Metadata, spans, timing, models, token
   counts, status, and optimizer attribution are enough for the default review.
3. Scope every read to the project selected by Caveman context. Never supply an
   organization id.
4. Empty results are evidence of no current signal, not zero cost or zero risk.
5. Cite trace ids and exact time windows used. Do not claim a cause from an
   aggregate alone.

## Step 1 — Load context

Prefer MCP:

```text
caveman_context {}
```

CLI fallback:

```bash
caveman cloud whoami
caveman cloud projects list
```

Stop if login or project selection is missing. Ask the user to run
`caveman login` or select a project; never guess.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add juliusbrussee/caveman/caveman-evidence-review@sha256:05bd896c76a41918

The line at the top of this page pins the label git:20260823.8909f6a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_ky576iggm5yjt75s.svg)](https://markdownregistry.com/a/art_ky576iggm5yjt75s)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 11, 2026 and Aug 23, 2026, about one every 12 days.

version	committed	commit	size	audit
git:20260823.8909f6a latest	2026-08-23	8909f6a	3,734 B	A	view · diff
git:20260811.82864c8	2026-08-11	82864c8	3,930 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (3734 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

juliusbrussee/caveman · 118,366 stars · license Apache-2.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ky576iggm5yjt75s
GET https://markdownregistry.com/api/v1/resolve?ref=juliusbrussee/caveman/caveman-evidence-review
GET https://markdownregistry.com/api/v1/blob/05bd896c76a41918fe7b87113dabe852117727a579a7e445891aa41391ed57c2

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.