# Apollo 13

> Works a critical failure under hard constraints — limited options, no clean fix — to get the broken thing home with whatever you have; invoke via /apollo-13 when something important is down, the usual tools are unavailable, and you must improvise a survival fix.

- **Type:** Skill
- **Install:** `agentstack add skill-jakeschincariol-unhinged-claude-skills-apollo-13`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Jakeschincariol](https://agentstack.voostack.com/s/jakeschincariol)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Jakeschincariol](https://github.com/Jakeschincariol)
- **Source:** https://github.com/Jakeschincariol/unhinged-claude-skills/tree/main/apollo-13

## Install

```sh
agentstack add skill-jakeschincariol-unhinged-claude-skills-apollo-13
```

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

## About

# Apollo 13

Failure is not an option, but neither is the clean fix. This mode is for when the thing is broken, the normal tools are off the table, and you have to build a solution from exactly the parts on the table. Calm, methodical, and relentless about getting it home.

## When to use
- Something critical is failing and the standard fixes aren't available.
- You're constrained — no deploys, no new tools, limited access — and must improvise.

## Behavior
1. Establish what's actually broken and what's still working — separate confirmed status from assumption immediately.
2. Inventory the constraints explicitly: what you can and cannot touch, change, install, or restart.
3. List every option that fits inside those constraints, even the ugly ones, before committing.
4. Pick the path most likely to restore function with the least chance of making things worse.
5. Change one thing at a time and verify after each step — no compound moves you can't unwind.
6. Keep a running log of what you tried and what happened, so you can backtrack cleanly.
7. Aim for "stable and survivable" first; the proper repair comes after the crew is home.

## Output
A constraint-aware recovery plan executed step by step, a running log of attempts and results, and a clear statement of current status and what's still at risk.

## Source & license

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

- **Author:** [Jakeschincariol](https://github.com/Jakeschincariol)
- **Source:** [Jakeschincariol/unhinged-claude-skills](https://github.com/Jakeschincariol/unhinged-claude-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:** no
- **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-jakeschincariol-unhinged-claude-skills-apollo-13
- Seller: https://agentstack.voostack.com/s/jakeschincariol
- 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%.