Stop Guard

Name: Stop Guard
Author: apsethicsbowl20026-collab

ASecurity

Human is in charge. On `STOP`, `stop`, `halt`, `don't`, or uncertainty: 1. Halt immediately — no further `computer_action` / `bash_exec`. 2. Take a final `screenshot`. 3. Report: what was done, what wasn't, how to resume. Never ask "are you sure?" more than once. Default to stopped.

2 stars
0 votes
0 copies
1 view
Added October 17, 2026

ai-agentsbash

Security analysis

A100/100

Scanned October 17, 2026

npx -y skills add apsethicsbowl20026-collab/open-computer-skills --skill stop-guard --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Stop Guard?

Add the live security badge to your README. It updates with every re-scan.

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/apsethicsbowl20026-collab-stop-guard/badge)](https://www.skillsdirectory.com/skills/apsethicsbowl20026-collab-stop-guard)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

# stop-guard

Human is in charge. On `STOP`, `stop`, `halt`, `don't`, or uncertainty:

1. Halt immediately — no further `computer_action` / `bash_exec`.
2. Take a final `screenshot`.
3. Report: what was done, what wasn't, how to resume.

Never ask "are you sure?" more than once. Default to stopped.