careful SKILL.md skillA

careful from yonatangross/orchestkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yonatangross/orchestkit/careful@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
yonatangross/orchestkit
Path
plugins/ork/skills/careful/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Oct 1, 2026
Size
4,980 bytes
Repository stars
296
License
MIT

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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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

| Rule | Blocks | Still allowed |
|------|--------|---------------|
| `rm-rf` | `rm` 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-force` | `git push --force`, `-f` (also inside `-uf`), `--force-with-lease[=...]`, a `+branch` refspec, to any branch | `git push`, `git push -u origin <branch>` |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yonatangross/orchestkit/careful@sha256:2a4bff743d74a1e5

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_b6mthi6ufy3ejblc.svg)](https://markdownregistry.com/a/art_b6mthi6ufy3ejblc)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 1, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-01 7ce7810 4,980 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4980 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

yonatangross/orchestkit · 296 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_b6mthi6ufy3ejblc
GET https://markdownregistry.com/api/v1/resolve?ref=yonatangross/orchestkit/careful
GET https://markdownregistry.com/api/v1/blob/2a4bff743d74a1e5fa1801d5e3832f2ff94215dcd238354376b82345fc87352a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from yonatangross/orchestkit

AGENTS.md AGENTS.md file
yonatangross/orchestkit · AGENTS.md
git:20260721.df25757 · audit A · 296 stars
CLAUDE.md CLAUDE.md file
yonatangross/orchestkit · CLAUDE.md
git:20261010.c1cfa0b · audit A · 296 stars
AGENTS.md@docs/site AGENTS.md file
yonatangross/orchestkit · docs/site/AGENTS.md
git:20260823.5e31893 · audit A · 296 stars
CLAUDE.md@docs/site CLAUDE.md file
yonatangross/orchestkit · docs/site/CLAUDE.md
git:20260823.5e31893 · audit B · 296 stars
ork-assess SKILL.md skill
yonatangross/orchestkit · plugins/ork-codex/skills/ork-assess/SKILL.md · Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use…
git:20260819.cf231c6 · audit A · 296 stars
ork-brainstorm SKILL.md skill
yonatangross/orchestkit · plugins/ork-codex/skills/ork-brainstorm/SKILL.md · Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a…
git:20260819.cf231c6 · audit A · 296 stars
ork-explore SKILL.md skill
yonatangross/orchestkit · plugins/ork-codex/skills/ork-explore/SKILL.md · Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when a…
git:20260819.cf231c6 · audit A · 296 stars
ork-glyph SKILL.md skill
yonatangross/orchestkit · plugins/ork-codex/skills/ork-glyph/SKILL.md · Render an answer inline as compact ASCII or box-drawing art with semantic status icons. Use for status, inventories…
git:20260919.ab8d756 · audit A · 296 stars
ork-implement SKILL.md skill
yonatangross/orchestkit · plugins/ork-codex/skills/ork-implement/SKILL.md · Make an approved, scoped change and prove the affected behavior. Use when a request asks to implement, build, add, or…
git:20260825.dc3bfe8 · audit A · 296 stars
ork-review-pr SKILL.md skill
yonatangross/orchestkit · plugins/ork-codex/skills/ork-review-pr/SKILL.md · Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use…
git:20260819.cf231c6 · audit A · 296 stars
ork-verify SKILL.md skill
yonatangross/orchestkit · plugins/ork-codex/skills/ork-verify/SKILL.md · Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a…
git:20260819.cf231c6 · audit A · 296 stars
CLAUDE.md@plugins/ork CLAUDE.md file
yonatangross/orchestkit · plugins/ork/CLAUDE.md
git:20261011.1894035 · audit A · 296 stars

Every file in yonatangross/orchestkit

Other files named careful

careful SKILL.md skill
garrytan/gstack · careful/SKILL.md · Safety guardrails for destructive commands. (gstack)
v0.1.0 · audit A · 136,966 stars
careful SKILL.md skill
yonatangross/orchestkit · src/skills/careful/SKILL.md · Blocks destructive shell commands once invoked: a PreToolUse Bash guard denies rm -rf outside temp dirs, force pushes…
v1.0.0 · audit A · 296 stars
careful SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/gstack/.agents/skills/gstack-careful/SKILL.md · Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl…
git:20260328.17430b8 · audit A · 12 stars
careful SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/gstack/careful/SKILL.md · Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl…
v0.1.0 · audit A · 12 stars
careful SKILL.md skill
tonydzi/second-brain-starter-kit · skills/gstack/careful/SKILL.md · Safety guardrails for destructive commands. (gstack)
v0.1.0 · audit A · 12 stars
careful SKILL.md skill
tonydzi/second-brain-starter-kit · skills/careful/SKILL.md · Safety guardrails for destructive commands. (gstack)
v0.1.0 · audit A · 12 stars
careful SKILL.md skill
timurgaleev/vibestack · skills/careful/SKILL.md · Safety guardrails that warn before destructive commands like rm -rf, DROP TABLE, force-push or reset --hard.
git:20261015.7f2ac1c · audit A · 7 stars
careful SKILL.md skill
tekkiiiii/the-agency · skills/careful/SKILL.md · Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl…
v0.1.0 · audit A · 6 stars

Browse by kind, by grade A, or by owner.