# Under Shirt

> Use Under Shirt when a catastrophic failure is possible and the system needs a last-resort failsafe that prevents total collapse, leaving it barely functional instead of dead.

- Skill: `hmbown/under-shirt-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add hmbown/under-shirt-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/hmbown/under-shirt-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: CC0-1.0
- Author: Hmbown (https://skillmd.com/u/hmbown)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/hmbown/under-shirt-2

---

# Under Shirt
Survive the unsurvivable by the thinnest margin.
## What This Skill Does
Use Under Shirt when a catastrophic failure is possible and the system needs a last-resort failsafe that prevents total collapse, leaving it barely functional instead of dead.
In this chip pack, Under Shirt is treated as a hybrid battle-chip procedure with a shipping-now delivery profile.
Canonical reference input: Under Shirt.
Hermes shelf: [Defense and Recovery](../DESCRIPTION.md).
## When To Use

- Before deploying a high-risk change that could catastrophically break the system, wire up a last-resort rollback or kill switch.
- A service is in a fragile state and needs a failsafe that prevents total data loss or full outage.
- Setting up incident response and needing a dead-man switch that keeps the system barely functional through worst-case scenarios.

## Prerequisites

- Name which part of this move is real tool use versus battle-chip framing before you act.
- These procedures rely on the normal tools already present in the active Hermes runtime; this repo does not ship a separate integration layer.

## Procedure

1. Restate the target, success condition, and no-touch boundaries before you spend the chip.
2. Identify the catastrophic failure path — the exact scenario where total collapse is possible.
3. Install a minimal survival mechanism at the critical point: a rollback checkpoint, circuit breaker, or data snapshot.
4. Verify the failsafe triggers correctly under simulated lethal conditions and document that it exists.
5. Package the result with concrete evidence, what stayed untouched, and the next recommended chip only if follow-up is truly needed.

## Deliverables

- A one-shot failsafe mechanism that prevents total system collapse.
- Documentation marking the failsafe's location, trigger condition, and that it is a last-resort safety net.

## Pitfalls / Guardrails

- Keep the theatrical framing, but name the concrete mechanism that makes the chip useful right now.
- This is a one-time, last-resort safety net — not a defense strategy. If you rely on it repeatedly, fix the underlying problem.
- The failsafe must leave the system in a minimum viable state, not silently corrupted.
- Never let the existence of an Under Shirt failsafe justify riskier deployments.
- Keep the chip metaphor anchored to a real operating move; do not let flavor substitute for procedure.

## Verification

- Check that the response includes every promised deliverable and leaves an inspectable audit trail.
- Check that confirmed facts, assumptions, and proposed follow-up are visibly separated.
- Check which parts are concrete actions versus framing, so the operator can tell what is real now.

## Example Invocation
```text
/under-shirt install a last-resort failsafe that prevents total catastrophic collapse, leaving the system barely functional if the worst case happens
```