# Ralph Status

> Report truthful Ralph loop progress from runtime state, chunks, manifests, hooks, markers, commits, and logs. Use when the user asks what Ralph is doing, whether a sprint or chunk finished, why it stopped, whether it is safe to resume, or what remains. This is read-only unless the user separately requests repair.

- **Type:** Skill
- **Install:** `agentstack add skill-zacharygcook-agent-skills-ralph-status`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [zacharygcook](https://agentstack.voostack.com/s/zacharygcook)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [zacharygcook](https://github.com/zacharygcook)
- **Source:** https://github.com/zacharygcook/agent-skills/tree/master/skills/ralph-status

## Install

```sh
agentstack add skill-zacharygcook-agent-skills-ralph-status
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Ralph Status

Report evidence, not optimism.

1. Run `just status` when the project exposes it; otherwise inspect `.ralph/status.sh` and
   `.ralph/config.env` directly.
2. Read the active sprint's `chunks.json`, `manifest.json`, `SCRATCHPAD.md`, hook markers, latest run
   logs, and relevant Git status/commits.
3. Distinguish chunk completion, all-chunks completion, hook completion, interruption, validation
   failure, exhausted turn budget, and full sprint completion.
4. Treat completion markers as claims. Confirm the expected sequential chunk transition, validation
   evidence, and commit boundary before calling work complete.
5. Report the current phase, completed and remaining chunks, hook state, latest meaningful event,
   blockers, and the exact safe next action.

Do not edit sprint state, rerun hooks, resume the loop, or mark chunks complete during a status request.
When installed beside `$ralph-loop`, consult `references/status.md` for the full shared state model.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [zacharygcook](https://github.com/zacharygcook)
- **Source:** [zacharygcook/agent-skills](https://github.com/zacharygcook/agent-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-zacharygcook-agent-skills-ralph-status
- Seller: https://agentstack.voostack.com/s/zacharygcook
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.