careful

careful is a skill for Claude Code from CarbeneAI/Forge. It costs 83 tokens per session (670 once invoked), scanned C, a copy of careful, MIT.

A safety mode that warns before running commands that could delete data, rewrite Git history, or affect production systems.

In plain words
What is it for?
Use it when working with destructive shell commands, databases, Git history, containers, Kubernetes, or production systems.
Why use it?
It reduces the chance of accidentally losing work or changing live infrastructure during development and troubleshooting.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: built for gstack.

Good fit Use it when working with destructive shell commands, databases, Git history, containers, Kubernetes, or production systems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/carbeneai/forge/careful
Install

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.

Any agent
npx skills add CarbeneAI/Forge --skill careful
Clone the repo
git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for careful

README.md
[![agentmods](https://agentmods.dev/badge/skills/carbeneai/forge/careful/github.svg)](https://agentmods.dev/skills/carbeneai/forge/careful)
Your own site
<a href="https://agentmods.dev/skills/carbeneai/forge/careful"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/careful/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for careful

Your own site · 80×15
<a href="https://agentmods.dev/skills/carbeneai/forge/careful"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/careful.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 670 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.00670
Opus 5 $0.00042 $0.00335
Sonnet 5 $0.00017 $0.00134
Haiku 4.5 $0.00008 $0.00067

Measured 8d ago against content hash 8c77c3a95afd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (bin/check-careful.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE,
Origin

This is a copy

100% identical to careful — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/careful/SKILL.md · 60 lines

What it actually says

/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 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.

Files

What ships with it

2 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.

Changes

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.

  1. 8d ago First seen · 60 lines · 83 tokens per session scan C 8c77c3a95afd

Subscribe to this mod's changes

careful is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 670 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 100% identical to careful, differing in 5 lines, and is treated as a copy.

Related

Other skills, from other repositories

implementing-secret-scanning-with-gitleaks

This skill covers implementing Gitleaks for detecting and preventing hardcoded secrets in git repositories. It addresses configuring pre-commit hooks, CI/CD pipeline integration, custom rule authoring for organization-specific secrets, baseline management for existing repositories, and remediation workflows for…

xalgorix/xalgorix · 63 tokens

public-release-prep

Audit a private git repository for secrets and personally-identifying info before it goes public, then carry out the cleanup. Use this whenever the user wants to open-source a repo, flip a GitHub repo from private to public, "clean up before going public," or asks whether a repo is safe to share externally — even if…

S24DeFi/global-lib-skills · 151 tokens

git-security-history

A small recipe over the already-cloned repo. It runs git log --grep for security/CVE/fix patterns, maps the touched files into ranked hot files, and emits historicalsignal.json. It optionally folds in two signals you may have ALREADY produced this phase — osv-scanner JSON (dependency CVEs) and gitleaks JSON (history…

tr4m0ryp/shor · 86 tokens

openspec-archive-change

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

MingyiSecLab/Mingyi-Atlas · 31 tokens

implementing-semgrep-for-custom-sast-rules

Write custom Semgrep SAST rules in YAML to detect application-specific vulnerabilities, enforce coding standards, and integrate into CI/CD pipelines.

xalgorix/xalgorix · 37 tokens

release

Prepare, verify, and publish Sutando engine releases. Use when asked to prepare a release proposal, determine a version bump, audit release documentation, validate release gates, create a release PR, tag a confirmed release, or publish GitHub release notes. Preparation is safe and non-publishing; tagging and…

sonichi/sutando · 68 tokens