Hypa
Hypabolic/Hypa
Context-optimized command runtime. An agent skill from Hypabolic/Hypa.
Safety guardrails for destructive commands. An agent skill from mr-daedalium/ostack-saas.
Install Careful
$ npx skills add mr-daedalium/ostack-saas --skill careful -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mr-daedalium/ostack-saas careful --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mr-daedalium/ostack-saas.git skills-src && mkdir -p .claude/skills && cp -r skills-src/careful .claude/skills/careful && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "careful" agent skill from https://github.com/mr-daedalium/ostack-saas/tree/main/careful into .claude/skills/careful/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "careful", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mr-daedalium/ostack-saas/tree/main/carefulType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mr-daedalium/ostack-saas --skill careful -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mr-daedalium/ostack-saas careful --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mr-daedalium/ostack-saas.git skills-src && mkdir -p .agents/skills && cp -r skills-src/careful .agents/skills/careful && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "careful" agent skill from https://github.com/mr-daedalium/ostack-saas/tree/main/careful into .agents/skills/careful/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "careful", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mr-daedalium/ostack-saas --skill careful -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mr-daedalium/ostack-saas careful --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mr-daedalium/ostack-saas.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/careful .cursor/skills/careful && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "careful" agent skill from https://github.com/mr-daedalium/ostack-saas/tree/main/careful into .cursor/skills/careful/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "careful", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mr-daedalium/ostack-saas.git --path careful--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mr-daedalium/ostack-saas --skill careful -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mr-daedalium/ostack-saas careful --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mr-daedalium/ostack-saas.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/careful .gemini/skills/careful && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "careful" agent skill from https://github.com/mr-daedalium/ostack-saas/tree/main/careful into .gemini/skills/careful/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "careful", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mr-daedalium/ostack-saas carefulInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mr-daedalium/ostack-saas --skill careful -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mr-daedalium/ostack-saas.git skills-src && mkdir -p .github/skills && cp -r skills-src/careful .github/skills/careful && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "careful" agent skill from https://github.com/mr-daedalium/ostack-saas/tree/main/careful into .github/skills/careful/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "careful", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mr-daedalium/ostack-saas --skill careful -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mr-daedalium/ostack-saas careful --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mr-daedalium/ostack-saas.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/careful .opencode/skills/careful && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "careful" agent skill from https://github.com/mr-daedalium/ostack-saas/tree/main/careful into .opencode/skills/careful/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "careful", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
careful- GitHub stars
- 114
- Used in
- 1 other repo
- Token cost
- ~545 tokens
- SKILL.md length
- 186 words
- Files
- 3
- Skills in repo
- 23
- Repo updated
- First seen
- Licence
- MIT
At a glance
Safety guardrails for destructive commands. An agent skill from mr-daedalium/ostack-saas.
- Debugging live systems
- SKILL.md covers What's protected, Safe exceptions and How it works
- Runs Shell scripts from its folder; calls git, docker and kubectl
- Working in a shared environment
What it does
Careful is an agent skill from mr-daedalium/ostack-saas. Safety guardrails for destructive commands. 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".
Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `bin/check-careful.sh`).
It sits in AI & LLM Engineering, covering Container orchestration and LLM guardrails. It works with Git, Kubernetes and Docker. The repository describes itself as: ostack — AI-powered engineering team for Claude Code. Fork of gstack by Garry Tan. The licence is MIT.
When your agent uses it
- Debugging live systems
- Working in a shared environment
- Asked to be careful
Example prompts
- “be careful”
- “safety mode”
- “prod mode”
- “/careful”
Requirements
- A Bash shell
- Docker
- Pre-approved tools (allowed-tools): Bash, Read
What it can do on your machine
Read from SKILL.md and the folder at commit a67256d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashRead
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Shell), which the agent can run.
Shell commands in SKILL.md call:
gitdockerkubectl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, docker and kubectl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Careful loads about 545 tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 186 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mr-daedalium/ostack-saas at commit a67256d, republished under its MIT licence (© mr-daedalium). 186 words, ~545 tokens.
Download SKILL.mdSave it as
.claude/skills/careful/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- careful
- description
- Safety guardrails for destructive commands. 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".
- allowed-tools
- Bash, Read
- version
- 0.1.0
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --><!-- Regenerate: bun run gen:skill-docs -->/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.
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.
© mr-daedalium, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in careful of mr-daedalium/ostack-saas.
- SKILL.md
- SKILL.md.tmpl
- bin/check-careful.sh
Open the folder on GitHubat commit a67256d
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in mr-daedalium/ostack-saas, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Careful next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Careful this skillmr-daedalium/ostack-saas | 114 | 1 repos | ~545 | Automated safety check: Notes | MIT | |
| HypaHypabolic/Hypa | 212 | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| Tokf Runmpecan/tokf | 199 | — | ~571 | Automated safety check: Pass | MIT | |
| Alloygrafana/skills | 282 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Performing Container Security Scanning With Trivymukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~818 | Automated safety check: Pass | Apache-2.0 | |
| Devops Automationrohitg00/awesome-claude-code-toolkit | 2.7k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Tokf Run
mpecan/tokf
Compress verbose CLI output with tokf before returning results.
- Official
Alloy
grafana/skills
Build a unified telemetry pipeline with Grafana Alloy — one OpenTelemetry-compatible binary that collects metrics, logs, traces, and profiles and ships to Grafana Cloud / Prometheus / Loki / Tempo /…
Performing Container Security Scanning With Trivy
mukul975/Anthropic-Cybersecurity-Skills
Runs Trivy across every target type it supports - container images, filesystems, Git repositories, and Kubernetes clusters - for OS and dependency vulnerabilities, IaC misconfiguration, exposed…
Devops Automation
rohitg00/awesome-claude-code-toolkit
CI/CD pipeline design with GitHub Actions, Docker, Kubernetes, Helm, and GitOps patterns
Dstack Prototyping
dstackai/dstack
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.
More from mr-daedalium/ostack-saas
All 23 skills in this repoBrowse
mr-daedalium/ostack-saas
Fast headless browser for QA testing and site dogfooding. An agent skill from mr-daedalium/ostack-saas.
Benchmark
mr-daedalium/ostack-saas
Performance regression detection using the browse daemon. An agent skill from mr-daedalium/ostack-saas.
Freeze
mr-daedalium/ostack-saas
Restrict file edits to a specific directory for the session.
Ostack
mr-daedalium/ostack-saas
Fast headless browser for QA testing and site dogfooding. An agent skill from mr-daedalium/ostack-saas.
Guard
mr-daedalium/ostack-saas
Full safety mode: destructive command warnings + directory-scoped edits.
Investigate
mr-daedalium/ostack-saas
Systematic debugging with root cause investigation. An agent skill from mr-daedalium/ostack-saas.
Related
Works with
Questions about Careful
What does Careful do?
Safety guardrails for destructive commands. An agent skill from mr-daedalium/ostack-saas. Careful is an agent skill from mr-daedalium/ostack-saas. Safety guardrails for destructive commands.
When should I use Careful?
Careful fits situations like: debugging live systems; working in a shared environment; asked to be careful.
How do I install Careful in Claude Code?
Run `npx skills add mr-daedalium/ostack-saas --skill careful -a claude-code`. Or copy the skill folder (careful in mr-daedalium/ostack-saas) into .claude/skills/careful in your project. Claude Code loads it when a task matches its description.
How do I install Careful in Codex?
Run `npx skills add mr-daedalium/ostack-saas --skill careful -a codex`. Or copy the skill folder (careful in mr-daedalium/ostack-saas) into .agents/skills/careful in your project. Codex loads it when a task matches its description.
Can I use Careful in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mr-daedalium/ostack-saas --skill careful -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/careful, .gemini/skills/careful, .github/skills/careful and .opencode/skills/careful in your project.
What does Careful need to run?
Going by SKILL.md and its folder, Careful needs a shell for the scripts in its folder and the command-line tools its instructions call (git, docker and kubectl). Our summary lists: A Bash shell; Docker. Its frontmatter pre-approves these tools: Bash, Read.
Does Careful access the network?
SKILL.md contains no URLs. Its commands use git and docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Careful safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Careful use?
Careful is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Careful use?
About 545 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Careful?
Skills that share tags, products or a category with Careful: Hypa (Hypabolic/Hypa, 212 stars), Tokf Run (mpecan/tokf, 199 stars), Alloy (grafana/skills, 282 stars) and Performing Container Security Scanning With Trivy (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Careful?
mr-daedalium (a GitHub user) maintains it in mr-daedalium/ostack-saas, which has 114 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on March 31, 2026.
Source: mr-daedalium/ostack-saas on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.