Apply safety controls when an LLM agent has authority to act on real systems. Covers blast-radius classification, dry-run-first patterns, out-of-band approval gates, scope locking, idempotency, kill switches, and rollback strategies. Invoke when designing an autonomous agent, when granting an LLM write access to production, or after an agent makes an unexpected change.
$npx -y skills add goldenwing-360/claude-security-skills --skill ai-agent-guardrailsInstalls into the current project.
Run `npx skills use "https://github.com/goldenwing-360/claude-security-skills" --skill "goldenwing-360/claude-security-skills/ai-agent-guardrails"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/goldenwing-360/claude-security-skills" that are relevant to the current task. Run `npx skills add "https://github.com/goldenwing-360/claude-security-skills"` and select the relevant skills, then follow their instructions.