Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
garrytan avatar

Careful

  • 217 installs
  • 126k repo stars
  • Updated July 15, 2026
  • garrytan/gstack

Apply a conservative change discipline—smaller diffs, explicit verification, and risk callouts—when editing production-critical paths or unfamiliar code.

About

Careful is a gstack behavioral skill that makes Claude Code proceed cautiously: narrower changes, clearer assumptions, and stronger pre-merge verification. It helps teams touching legacy SaaS, APIs, or agent tooling where a rushed patch can cause outages or subtle regressions.

  • Encourages smaller diffs
  • Surfaces risky edits
  • Demands verification steps
  • Reduces silent regressions
  • Works across stacks

Careful by the numbers

  • 217 all-time installs (skills.sh)
  • Ranked #329 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/garrytan/gstack --skill careful

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs217
repo stars126k
Last updatedJuly 15, 2026
Repositorygarrytan/gstack

What it does

Apply a conservative change discipline—smaller diffs, explicit verification, and risk callouts—when editing production-critical paths or unfamiliar code.

Files

SKILL.mdMarkdownGitHub ↗

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

When to invoke this skill

Warns before rm -rf, 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
rm -rf / rm -r / rm --recursiverm -rf /var/dataRecursive 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:

  • rm -rf 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.

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.