slb

SKILL.md

A Go CLI that implements a two-person rule for running potentially destructive commands from AI coding agents. When an agent wants to run something risky (e.g., rm -rf, git push --force, kubectl delete, DROP TABLE), SLB requires peer review and explicit approval before execution.

Coding agents can get tunnel vision, hallucinate, or misunderstand context. A second reviewer (ideally with a different model/tooling) catches mistakes before they become irreversible.

SLB is built for multi-agent workflows where many agent terminals run in parallel and a single bad command could destroy work, data, or infrastructure.

Bouton de lancement simultané - Règle à deux pour les commandes destructives dans les flux de travail multi-agents. Classification par niveaux de risque, liaison de hachage de commande, 5 portes d'exécution, exécution côté client avec héritage d'environnement. Allez CLI. Source : dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations.

Voir l'original