Careful logo

Careful

Community
yonatangross
careful

Blocks destructive shell commands once invoked: a PreToolUse Bash guard denies rm -rf outside temp dirs, force pushes and remote branch deletes, git reset --hard, DROP TABLE / DROP DATABASE / TRUNCATE, kubectl delete and terraform or tofu destroy, including inside ssh remote commands, and makes Claude ask the operator. Use before touching production, a shared branch, a live database or a cluster.

Overview

Publisheryonatangross
Repositoryorchestkit
Skill namecareful
Stars
298
Forks
35
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by yonatangross on GitHub. Read the source before you install it.

Installation

Install the Careful AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yonatangross/orchestkit/tree/main/plugins/ork/skills/careful
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yonatangross/orchestkit.git /tmp/orchestkit
mkdir -p .claude/skills
cp -r /tmp/orchestkit/plugins/ork/skills/careful .claude/skills/careful
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Careful in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Careful on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Careful is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

careful, block destructive commands for this session

Invoking this skill registers a PreToolUse hook on Bash (the hooks: block above). Claude Code keeps a skill's hooks registered for the rest of the session, on every later turn, so careful stays on until the session ends. There is no off switch: start a new session to work without it.

What it blocks

RuleBlocksStill allowed
rm-rfrm with recursive and force flags (-rf, -fr, -r -f, --recursive --force), xargs rm -rf, and any target the shell expands: $TMPDIR/x, $TMP, $TEMP, $X, $( ), globs, braces, ~the same command when every target is a LITERAL absolute path that lands, after following existing symlinks, strictly inside /tmp, /private/tmp or the configured TMPDIR (trusted only when it is two or more levels deep); write /tmp/build, not $TMPDIR/build, because a command can reassign TMPDIR first (TMPDIR=/ ; rm -rf $TMPDIR/usr); rm -r; rm -f file
git-push-forcegit push --force, -f (also inside -uf), --force-with-lease[=...], a +branch refspec, to any branchgit push, git push -u origin <branch>
git-push-deletegit push origin --delete <b>, -d <b>, :<b>git push origin <b>:<b>
git-reset-hardgit reset --hardgit reset --soft, git reset HEAD <file>
sql-dropDROP TABLE, DROP DATABASE, DROP SCHEMA anywhere in the command, heredocs includeda SELECT that mentions drop
sql-truncateTRUNCATE TABLE, or a TRUNCATE <name> statement sent to a SQL clienttruncate -s 0 file.log
kubectl-deletekubectl ... deletekubectl get, kubectl logs
terraform-destroyterraform destroy, terraform apply -destroy, the same with tofuterraform plan, terraform apply

Matching is on shell words, not substrings: a commit message or grep pattern that quotes git push --force is text, not a push. Compound commands are split on ;, &&, | and newlines, and the bodies of bash -c, eval, $( ) and the remote command of ssh host '...' are checked as well.

When a command is blocked

The hook exits 2 and Claude sees the reason, for example:

[ork:careful] blocked by rule git-push-force: git push with --force-with-lease.
careful mode is on for this session, so destructive commands do not run unattended.
To proceed, ask the operator: they can run the command themselves, or confirm it and run it outside careful mode.

Then stop and ask. Do not rewrite the command to slip past the matcher (a different flag spelling, a script file, an alias): the operator turned careful on to be asked, and a workaround defeats that even when the matcher misses it.

Limits

careful is a pattern matcher on the text of each Bash call. It is a seatbelt, not a sandbox. It does NOT see:

  • shell aliases and functions (alias nuke='rm -rf', then nuke src);

  • scripts, Makefiles, npm scripts or binaries that run these commands inside (./deploy.sh, make clean, npm run reset-db);

  • eval or bash -c built from variables, base64 or other indirection it cannot read as text; it only reads literal strings;

  • interpreters and other shells running the same thing (python -c "shutil.rmtree(...)", node -e, fish -c, pwsh), or a remote shell other than plain ssh host '...';

  • a link created in the same command (ln -s / /tmp/r9 && rm -rf /tmp/r9/usr): the guard follows links that already exist when it runs (a temp path through a link to /usr is denied), but one made by the command itself is out of reach for a text check, like python -c "shutil.rmtree(...)";

  • MCP tools, file edits, and anything outside the Bash tool.

  • If the hook cannot read its input it blocks (exit 2) rather than guess.

  • To also fence file edits to one directory, use the freeze skill.

The guard is scripts/careful-guard.mjs (Node, no dependencies); its matcher cases live in tests/unit/test-careful-guard.mjs.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Careful AI skill do?

Blocks destructive shell commands once invoked: a PreToolUse Bash guard denies rm -rf outside temp dirs, force pushes and remote branch deletes, git reset --hard, DROP TABLE / DROP DATABASE / TRUNCATE, kubectl delete and terraform or tofu destroy, including inside ssh remote commands, and makes Claude ask the operator. Use before touching production, a shared branch, a live database or a cluster.

Why use Careful on TypingMind?

Because you install it once and use it with any model. Careful is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Careful in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yonatangross/orchestkit/tree/main/plugins/ork/skills/careful. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Careful?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Careful?

As many as you like. As long as a model supports skills, you can use Careful with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Careful AI skill free?

Yes. It is published on GitHub by yonatangross under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇