careful

careful is a command for Claude Code from Achitokun14/claude-universal. It costs 34 tokens per session (323 once invoked), scanned C, original, MIT.

A safety mode that asks for exact confirmation before commands that could delete data, rewrite history, publish packages, or change sensitive files.

In plain words
What is it for?
Use it before risky shell, database, Git, Docker, Kubernetes, Terraform, deployment, publishing, or credential-file operations.
Why use it?
It reduces the risk of accidental destructive changes by explaining the affected targets and requiring the user to type a specific confirmation.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: built for gstack.

Good fit Use it before risky shell, database, Git, Docker, Kubernetes, Terraform, deployment, publishing, or credential-file operations.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/achitokun14/claude-universal/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.

Clone the repo
git clone --depth 1 https://github.com/Achitokun14/claude-universal

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/commands/achitokun14/claude-universal/careful/github.svg)](https://agentmods.dev/commands/achitokun14/claude-universal/careful)
Your own site
<a href="https://agentmods.dev/commands/achitokun14/claude-universal/careful"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/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/commands/achitokun14/claude-universal/careful"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/careful.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 323 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 original No closer match found 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 $0.00034 $0.00323
Opus 5 $0.00017 $0.00161
Sonnet 5 $0.00007 $0.00065
Haiku 4.5 $0.00003 $0.00032

Measured 8d ago against content hash bf0cd8289496, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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.

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.

description: Warn before destructive commands (rm -rf, DROP TABLE, git push --force, docker prune). Pairs with /freeze and /guard. Inspired by gstack.
user/commands/careful.md · 25 lines

What it actually says

You are in CAREFUL mode for the next action. Before running any command that could lose data:

  1. State EXACTLY what the command will do in plain English.
  2. List the files/paths/services that would be affected.
  3. Ask for explicit confirmation: "Type 'yes, ' to proceed."
  4. Never proceed if user types anything other than the exact confirmation string.

Trigger list (require confirmation for any of these):

  • rm -rf, rm with wildcards, find … -delete
  • DROP TABLE, DROP DATABASE, TRUNCATE, DELETE FROM … WHERE 1=1
  • git push --force, git reset --hard, git clean -fd, git rebase -i of pushed commits
  • docker system prune, docker volume rm, kubectl delete namespace
  • terraform destroy, railway destroy, vercel rm
  • npm publish, cargo publish, gh release create
  • any sudo operation
  • writes to .env*, *.key, *.pem, .credentials.json

If the user has $ARGUMENTS specified, they're describing a specific action — audit that action against the above, and explain the risk before executing.

CAREFUL mode persists for this session. To turn off: user types "exit careful mode".

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 · 25 lines · 34 tokens per session scan C bf0cd8289496

Subscribe to this mod's changes

careful is a command published in the GitHub repository Achitokun14/claude-universal (2 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 323 once invoked, about $0.0002 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 2026-08-31.