agentsclimarketplace

Careful

Skill nota-america/forgecat-agent-profiles/profiles/garrytan/gstack/for-codex/.agents/skills/garrytan_gstack/careful

Safety guardrails for destructive commands. (gstack)From its SKILL.md

Install
npx -y skills add nota-america/forgecat-agent-profiles --skill careful

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

2.5 KB, 567 tokens by cl100k_base, as published. Nobody here has run it

<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --> <!-- Regenerate: bun run gen:skill-docs -->

When to invoke this skill

Warns before recursive remove commands, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".

/careful — Destructive Command Guardrails

Safety mode is now active. Every bash command will be checked for destructive patterns before running. If a destructive command is detected, you'll be warned and can choose to proceed or cancel.

mkdir -p ~/.gstack/analytics
echo '{"skill":"careful","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true

What's protected

PatternExampleRisk
recursive rm commandsrm against /var/data with recursive flagsRecursive delete
DROP TABLE / DROP DATABASEDROP TABLE users;Data loss
TRUNCATETRUNCATE orders;Data loss
git push --force / -fgit push -f origin mainHistory rewrite
git reset --hardgit reset --hard HEAD~3Uncommitted work loss
git checkout . / git restore .git checkout .Uncommitted work loss
kubectl deletekubectl delete podProduction impact
docker rm -f / docker system prunedocker system prune -aContainer/image loss

Safe exceptions

These patterns are allowed without warning:

  • recursive remove of node_modules / .next / dist / __pycache__ / .cache / build / .turbo / coverage

How it works

The hook reads the command from the tool input JSON, checks it against the patterns above, and returns permissionDecision: "ask" with a warning message if a match is found. You can always override the warning and proceed.

To deactivate, end the conversation or start a new one. Hooks are session-scoped.

What ships with it: 1 file

4.2 KB alongside SKILL.md, 1 of them executable

bin/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.