# Review LLM Evidence

Reads Caveman Cloud cost, latency and error evidence without changing anything.

- Repository: https://github.com/JuliusBrussee/caveman (116680 stars)
- Category: Data and ML
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add JuliusBrussee/caveman --skill caveman-evidence-review -g -a claude-code -y`
Codex: `npx skills add JuliusBrussee/caveman --skill caveman-evidence-review -g -a codex -y`
Cursor: `npx skills add JuliusBrussee/caveman --skill caveman-evidence-review -g -a cursor -y`
Gemini CLI: `npx skills add JuliusBrussee/caveman --skill caveman-evidence-review -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add JuliusBrussee/caveman`

## Description

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.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# 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.

## Step 2, Establish baseline

Use `caveman_report` for:

- `overview`
- `costs`
- `score`
- `workflows`
- `verified_savings`

Then use `caveman_plan` for ranked daily headroom. If question is narrow, skip
unrelated reports. Read shortest set that can answer it.

CLI fallback:

```bash
caveman cloud costs
caveman cloud score
caveman cloud plan --json
```

State report window and basis before interpreting direction.

## Step 3, Test the leading explanation with traces

Use `caveman_trace_search`. Choose a bounded window and closed filters:
workflow, agent, model, provider, error code, runtime mode, cache status,
optimization id, status class, token/cost/latency bounds, compression, or
monitor verdict.

Useful groupings:

The rest: https://github.com/JuliusBrussee/caveman/blob/HEAD/skills/caveman-evidence-review/SKILL.md