# Manage Caveman Experiments

Inspects and gates experiment start, approval, cancel and rollback steps.

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

## Install

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

## Description

Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.

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

# Manage eval-gated experiments

Treat every lifecycle change as a production control action. Read current state
and results, then report one supported recommendation or block.
Current agent MCP is intentionally read-only: control-api does not yet enforce a
complete lifecycle transition table and evidence gate atomically.

## Non-negotiable gates

1. A request to review, inspect, explain, or recommend authorizes reads only.
2. Never approve an experiment whose results are pending, whose required
   guardrails are absent, or whose evidence reports a breach.
3. Never convert experiment lift into `verified_savings`. Only active real
   traffic plus provider-causal, provider-complete ledger evidence can do that.
4. Never supply an organization id. Project and tenant scope come from the
   logged-in Caveman identity and server RBAC.
5. Never execute a lifecycle mutation, even after user approval. Exact
   `<action>:<experiment_id>` strings are agent-generatable and are not proof of
   human intent.
6. Unknown states and server errors fail closed. Report exact
   `cave_snake_code`.

## Step 1, Load project and experiment

Prefer MCP:

```text
caveman_context {}
caveman_experiment_get {"action":"get","experiment_id":"<id>"}
caveman_experiment_get {"action":"results","experiment_id":"<id>"}
```

Use `{"action":"list"}` when the user has not named an id.

CLI fallback:

```bash
caveman cloud experiments list
caveman cloud experiments show <id>
caveman cloud experiments results <id>
```

Stop if login, project, experiment, or results are unavailable.

## Step 2, Evaluate evidence

Report:

- current lifecycle state and safety class;
- control and candidate sample sizes;
- quality or eval result;
- latency, error, cost, retry, drop, and escalation guardrails when present;
- evidence cost;
- rollback or hold reason;
- whether result is pending, failed, promotable, or active.

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