agentleFS
Sign inStart free
aprameyakaprameyak/coding-skills/shell-safety/SKILL.md

shell-safety

Skill1 starsChanged 41 days agoMITView on GitHub

Run shell commands safely and predictably. Use when writing scripts, running destructive commands, or automating terminal workflows.

  • Deletes or force-pushes

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Prefer non-interactive flags.

    line 10
  2. Distinctive:

    Use absolute paths when cwd is ambiguous.

    line 12
  3. Very specific:

    Avoid rm -rf on broad paths.

    line 14
  4. Distinctive:

    Do not exfiltrate secrets into logs or argv that may be recorded.

    line 15
  5. Distinctive:

    Read command help/version when flags differ across platforms.

    line 16
  6. Distinctive:

    Check exit codes for critical steps.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Shell Safety

Rules

  • Prefer non-interactive flags; never rely on prompts.
  • Quote variables and paths: "$var".
  • Use absolute paths when cwd is ambiguous.
  • Chain with && when later steps depend on earlier success.
  • Avoid rm -rf on broad paths; narrow the target.
  • Do not exfiltrate secrets into logs or argv that may be recorded.
  • Read command help/version when flags differ across platforms.

Dangerous Ops

Require explicit user intent for: force push, hard reset, mass delete, dropping databases, rewriting history, chmod/chown on large trees.

Scripts

  • Set strict mode when appropriate (set -euo pipefail in bash).
  • Check exit codes for critical steps.
  • Make scripts idempotent when used in retries/CI.

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