Description
safety-guard is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It guards against destructive operations and offers three modes of protection. The Careful mode intercepts dangerous commands, such as rm -rf, git push --force and DROP TABLE, before they run and asks for confirmation. The listing describes two further modes, one of which restricts edits to a particular directory. The skill is intended for working on production systems, for runs where agents operate autonomously in full-auto mode, for keeping edits within one directory, and for sensitive operations such as migrations, deploys and data changes. It is a SKILL.md file of instructions that an AI agent loads when a task calls for it. It is free and open source, and the skills.sh listing shows all three security audits passing.…
Highlights
- Careful mode intercepts destructive commands
- Asks for confirmation before risky steps
- Directory restriction for edits
- Guards migrations, deploys and data changes
Ratings & Reviews
No ratings yet
Be the first to rate safety-guard.
People also visit
safety-guard FAQ
What does the safety-guard skill do?
It stops an agent from running destructive commands without confirmation, such as rm -rf, git push --force or DROP TABLE.
What are the three modes?
Careful mode is described in detail. The listing names two other modes, one of which restricts edits to a specific directory.
When is it useful?
On production systems, during autonomous full-auto agent runs, during migrations and deploys, and when edits should stay in one directory.
How do I install it?
Run: npx skills add https://github.com/affaan-m/ecc --skill safety-guard
Is it free?
Yes. It is free and open source.
Are there security findings?
The skills.sh listing shows Gen Agent Trust Hub, Socket and Snyk all passing.
What are the best safety-guard alternatives?
Popular alternatives to safety-guard include convex-deploy-guard, git-guardrails-claude-code and gateguard. See all safety-guard alternatives