Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/garrytan/gstack/carefulnpx skills add garrytan/gstack --skill carefulgit clone --depth 1 https://github.com/garrytan/gstackWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00014 | $0.00958 |
| Opus 5 | $0.00007 | $0.00479 |
| Sonnet 5 | $0.00003 | $0.00192 |
| Haiku 4.5 | $0.00001 | $0.00096 |
Grade C, and why
careful scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Warns before rm -rf, DROP TABLE, How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to invoke this skill
Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".
/careful — Destructive Command Guardrails
Safety mode is now active. Every bash command will be checked for destructive patterns before running. If a destructive command is detected, you'll be warned and can choose to proceed or cancel.
mkdir -p ~/.gstack/analytics
echo '{"skill":"careful","ts":"'$(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
| Pattern | Example | Risk |
|---|---|---|
rm -rf / rm -r / rm --recursive |
rm -rf /var/data |
Recursive delete |
DROP TABLE / DROP DATABASE |
DROP TABLE users; |
Data loss |
TRUNCATE |
TRUNCATE orders; |
Data loss |
git push --force / -f |
git push -f origin main |
History rewrite |
git reset --hard |
git reset --hard HEAD~3 |
Uncommitted work loss |
git checkout . / git restore . |
git checkout . |
Uncommitted work loss |
kubectl delete |
kubectl delete pod |
Production impact |
docker rm -f / docker system prune |
docker system prune -a |
Container/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 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.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 88 lines · 14 tokens per session scan C 51c821326dde
careful is a skill published in the GitHub repository garrytan/gstack (130,961 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 958 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…