AGENTS.md instructions for Dicklesworthstone/destructive_command_guard, covering agents.md — dcg (destructive command guard), rule 0 - the fundamental override prerogative, rule number 1: no file deletion, git branch: only use main, never master and toolchain: rust & cargo.
Copilot instructions for SafeAI-Lab-X/ClawKeeper, covering openclaw codebase patterns, tech stack, anti-redundancy rules, source of truth locations and formatting utilities (src/infra/).
AGENTS.md instructions for Dicklesworthstone/slb, covering agents.md — slb, rule 0 - the fundamental override prerogative, rule number 1: no file deletion, git branch: only use main, never master and toolchain: go & make.
AGENTS.md instructions for XiaoYiWeio/deepsafe-scan, covering deepsafe scan — agent instructions, what this tool does, when to use, how to invoke and modules.
Claude Code instructions for XiaoYiWeio/deepsafe-scan, covering deepsafe scan — claude code integration, what it does, when to use, how to run and openclaw users (auto-reads gateway config).
Instructions for karanb192/bouncer: Bouncer enforces these rules at the door via a fail-closed preToolUse hook. This list is the advisory, defense-in-depth layer: do not propose or run any of the following destructive shell commands. The hook will deny them anyway, so don't waste a turn.
Instructions for karanb192/bouncer: A door-guard sits in front of your shell. Every runshellcommand call passes the door before it runs; destructive commands are blocked by an enforced BeforeTool hook, not by you, and not negotiable.