'Full safety mode: destructive command warnings + directory-scoped edits.
Pro scans all 2 files and shows the line behind each finding
Scanned 9/20/2026
Skills Directorynpx -y skills add nota-america/forgecat-agent-profiles --skill garrytan_gstack_guard --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Garrytan Gstack Guard?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nota-america-garrytan-gstack-guard-forgecat-agent-profiles)More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.
---
name: guard
description: 'Full safety mode: destructive command warnings + directory-scoped edits.
Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with
/freeze (blocks edits outside a specified directory). Use for maximum safety
when touching prod or debugging live systems. Use when asked to "guard mode",
"full safety", "lock it down", or "maximum safety". (gstack)'
---
# guard
Resolve `scripts/entry.py` relative to this SKILL.md, then invoke it by absolute path:
Set `SKILL_DIR` to the absolute directory containing this file, as supplied by skill discovery.
```sh
python3 "$SKILL_DIR/scripts/entry.py" instructions --host codex --skill guard
```
Use `claude-code`, `cursor`, `codex`, `openclaw`, or `hermes` for the current platform.
Follow the returned runtime contract and read the complete referenced workflow before acting.
Repeat the returned environment prefix on each shell call; variables do not persist between tool calls.
If setup is missing, explain the exact preparation command and obtain consent before downloads or builds.
Never silently use another gstack installation. Preserve the source workflow's questions and permission boundaries.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
