agentleFS
Sign inStart free
apsethicsbowl20026-collabapsethicsbowl20026-collab/open-computer-skills/skills/safe-bash/SKILL.md

safe-bash

Skill2 starsChanged 31 days agoMITView on GitHub

Run shell via bash_exec. Server blocks destructive commands — don't try to bypass. rm -rf /, rm -rf ~, mkfs, dd of=/dev/, shutdown, reboot, diskpart, registry deletes, net user /add, disabling Defender/Firewall.

  • Deletes or force-pushes

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run shell via bash_exec. Server blocks destructive commands — don't try to bypass.

    line 3
  2. Very specific:

    Prefer read-only first: ls, pwd, git status, echo.

    line 11
  3. Distinctive:

    Never run curl-piped-to-shell from untrusted URLs.

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

safe-bash

Run shell via bash_exec. Server blocks destructive commands — don't try to bypass.

Blocked (non-exhaustive)

rm -rf /, rm -rf ~, mkfs, dd of=/dev/, shutdown, reboot, diskpart, registry deletes, net user /add, disabling Defender/Firewall.

Rules

  • Prefer read-only first: ls, pwd, git status, echo.
  • Chain with && only after first command succeeds.
  • Paste full stdout/stderr + exit code in your report.
  • Never run curl-piped-to-shell from untrusted URLs.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free