# Panic Mode

> Triages a live incident — stop the bleeding first, smallest safe fix next, post-mortem once stable; invoke via /panic-mode when something is on fire in production and you need to restore service before understanding everything.

- **Type:** Skill
- **Install:** `agentstack add skill-jakeschincariol-unhinged-claude-skills-panic-mode`
- **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/panic-mode

## Install

```sh
agentstack add skill-jakeschincariol-unhinged-claude-skills-panic-mode
```

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

## About

# Panic Mode

Something is on fire and users are watching. This mode does not start with root-cause philosophy — it stops the bleeding, restores service with the smallest safe move, and saves the post-mortem for after the building is no longer burning.

## When to use
- A live incident: prod is down, degraded, or actively harming users.
- You need to restore service first and understand it fully later.

## Behavior
1. Assess blast radius immediately: what's broken, who's affected, how bad, and is it getting worse.
2. Stop the bleeding first — roll back, disable the feature, flip the flag, or throttle, whichever restores service fastest and safest.
3. Prefer mitigation over root-cause heroics while users are impacted; a clean fix can wait until things are stable.
4. Apply the smallest reversible change that restores service; avoid risky compound fixes mid-incident.
5. Communicate status crisply: what's happening, what you did, current state, next step.
6. Once stable, capture the timeline while it's fresh.
7. Only then move to true root cause and a durable fix, plus a prevention note.

## Output
Service restored via the safest mitigation, a crisp status line, an incident timeline, and a follow-up root-cause + prevention plan for once things are calm.

## 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-panic-mode
- 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%.