Skip to content
Skill

saferun

by Cocabadger

AI Summary

SafeRun provides automatic safety guardrails for AI agents by classifying shell commands as BLOCK, ASK, or ALLOW before execution, preventing dangerous operations like force pushes and recursive deletes. Developers and AI systems that execute shell commands benefit from this protection without needing manual configuration.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to install the "saferun" skill in my project.

Please run this command in my terminal:
# Install skill into the correct directory
mkdir -p .claude/skills/saferun-openclaw && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/saferun-openclaw/SKILL.md "https://raw.githubusercontent.com/Cocabadger/saferun-openclaw/main/SKILL.md"

Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.

Description

Safety guardrails for AI agents. Classifies shell commands as BLOCK, ASK, or ALLOW before execution. Prevents dangerous operations like force pushes, recursive deletes, and credential destruction. Works automatically — no configuration needed.

What gets blocked (examples)

• git push --force origin main — Rewrites production branch history • rm -rf / or rm -rf ~ — Destroys filesystem • chmod 777 /etc — Opens system config to everyone • curl ... | bash — Executes untrusted remote code • git branch -D main — Deletes critical branch • git reset --hard on protected branches — Discards all work • Deleting .env, ~/.ssh/ files — Destroys credentials

What needs approval (examples)

• git merge feature into main — Production branch change • kubectl apply / terraform apply — Infrastructure deployment • npm publish — Public package release • docker push — Container registry update

What passes through (examples)

• git status, git log, ls, cat — Read-only operations • git checkout -b feature — Local branch creation • pytest, npm test — Running tests • npm install, pip install — Installing dependencies

SafeRun — Safety Guardrails

You have access to a command safety classifier. Before executing ANY shell command via the exec tool, you MUST check it with SafeRun first.

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 2mo ago
Active
AdoptionUnder 100 stars
0 ★ · Niche
DocsREADME + description
Well-documented

GitHub Signals

Issues0
Updated2mo ago
View on GitHub
MIT License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Claude Code