dangerous-actions

<dangerous_actions> <process> 1. Assess BLAST RADIUS before execution. 2. "THINK THE OPPOSITE" — what if this goes wrong? 3. Consider safer alternatives. 4. MUST REQUIRE EXPLICIT user approval for hard-deny tier (see below). Examples (not limited): - Deleting data from actual servers - Using actual servers in unit testing - git reset, deleting branches, force-push - Generating destructive scripts or commands - Modifying shared infrastructure, CI/CD, permissions - Dropping or truncating database tables Exceptions (only after blast radius): 5. Application code itself. 6. Just-created data you CAN fully recover. 7. Temporary data without side-effects. </process> <pitfalls> - Assuming local action has no remote consequence. - Generating destructive commands in scripts without flagging. </pitfalls> <hook> Active in Claude Code, Cursor, Copilot, and Codex. Windsurf: adapter ships but no plugin yet. An automated PreToolUse hook backs this skill for the highest-blast-radius patterns (Bash destructive commands, file writes to secret paths, DDL payloads in content). The hook is a deterministic tripwire — it does not replace this skill's reasoning process. Use this skill to reason about danger; the hook enforces a last-resort gate if that reasoning is skipped. ## Two-tier policy All patterns are classified as either **reconsider** (dangerous but recoverable) or **hard-deny** (catastrophic, no bypass exists): | Tier | Examples | AI behaviour on deny | |------|---------|--...