MCPInstall

careful

Safety guardrails for destructive commands. (gstack)

Installs
376
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/garrytan/gstack --skill careful
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads careful automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

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

/careful — Destructive Command Guardrails

Safety mode is now active. Every Bash and PowerShell 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.

GSTACK_STATE_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get GSTACK_STATE_ROOT); : "${GSTACK_STATE_ROOT:?gstack-paths failed; reinstall with ./setup or /gstack-upgrade}"
mkdir -p "$GSTACK_STATE_ROOT"/analytics
echo '{"skill":"careful","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> "$GSTACK_STATE_ROOT"/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

PowerShell and cmd (Windows)

The hook also checks the PowerShell tool (Claude Code's main Windows shell) and any pwsh/powershell/cmd launched from Bash. Matching ignores case, covers aliases in command position, accepts parameter prefixes (-r, -fo) and strips cmd ^ escapes. All rows above apply there too.

PatternExample
Remove-Item/rm/ri/del/erase/rd/rmdir + -Recurse or -Forcegci | ri -r -fo
cmd rd /s, rmdir /s, del /s, erase /scmd /c rd /s /q C:\proj
Format-Volume, Clear-Disk, Clear-Content, [IO.Directory]::Delete, [IO.File]::DeleteClear-Disk -Number 1
-EncodedCommand, iex, Start-Process of a shell, & $cmd (can't be inspected)irm $url | iex

Best-effort on PowerShell. String matching can't see a command built at runtime. For a hard stop, add Claude Code permission deny rules, which parse PowerShell and its aliases: "deny": ["PowerShell(Remove-Item *)"] in .claude/settings.json. The hook runs through bash, so Windows needs Git Bash.

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 tool_name and the command from the tool input JSON, checks it against the patterns above, and returns a hookSpecificOutput payload with permissionDecision: "ask" and a warning reason if a match is found (the decision must be nested under hookSpecificOutput — Claude Code ignores a top-level permissionDecision). You can always override a MEDIUM warning and proceed.

HIGH tier (hard deny)

Two catastrophic shapes are denied, not asked: rm -r/-R of exactly /, ~, or $HOME, and force-push to the repo's default branch. SIMPLE commands only (no ;, &&, ||, |, newline) — compound shapes fall through to the MEDIUM ask; --force-with-lease is never HIGH. A best-effort advisory hard-stop, not a policy boundary: the escape hatch is ending the opt-in, session-scoped /careful session.

Project patterns (additive only)

Add warn rules — one POSIX ERE per line, # comments OK — in ~/.gstack/careful-patterns.txt (global) or ~/.gstack/projects/<slug>/careful-patterns.txt (per-project). Consulted after the built-in families, so config can only ADD rules, never suppress a baseline warning. Invalid regex lines are skipped.

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

FAQ

What does the careful skill do?

Safety guardrails for destructive commands. (gstack)

How do I install careful?

Run npx skills add https://github.com/garrytan/gstack --skill careful in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/careful/ (personal) or .claude/skills/careful/ (project).

Which AI agents can use careful?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is careful safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains careful?

It is published by garrytan in garrytan/gstack. It has 376 recorded installs.

More from garrytan/gstack

View all →

gstack

garrytan/gstack

Open the skill to read its SKILL.md instructions.

24.2K installs

office-hours

garrytan/gstack

YC Office Hours — two modes. (gstack)

587 installs

design-review

garrytan/gstack

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)

plan-eng-review

garrytan/gstack

Eng manager-mode plan review. (gstack)

plan-ceo-review

garrytan/gstack

CEO/founder-mode plan review. (gstack)

plan-design-review

garrytan/gstack

Designer's eye plan review — interactive, like CEO and Eng review. (gstack)

Popular other skills

View category →

hyperframes-cli

heygen-com/hyperframes

The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.

1.3M installs

triage

mattpocock/skills

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

1M installs

ask-matt

mattpocock/skills

Ask which skill or flow fits your situation. A router over the skills in this repo.

778.4K installs

to-questionnaire

mattpocock/skills

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

508.9K installs

wait-what

mattpocock/skills

Stop. That last message did not land: re-pitch it.

459.7K installs

loop-me

mattpocock/skills

Grill me about specs for the workflows I want to build, within this workspace.

447.9K installs