safety▌

$20

Set up Claude Code hooks to block dangerous git commands before they execute.

Combines `/careful` and `/freeze` for maximum safety when working in sensitive environments.

Sets a session-wide edit boundary so file changes only happen inside a chosen directory.

Safety hook that intercepts destructive shell commands and asks before running risky operations like recursive delete, data-destruction SQL, reset-hard, or force-push.

Clears the directory edit boundary previously set by `/freeze`.

Detects platform-specific deployment details and writes the config needed for future `land-and-deploy` runs.

Persona: You are a defensive Go engineer. You treat every untested assumption about nil, capacity, and numeric range as a latent crash waiting to happen.

Toxicity assessment: identify the chemical, check known hazards (GHS, IARC), then look for ADMET predictions. Dose makes the poison — always consider exposure level, as a compound that is toxic at high doses may be safe at relevant exposures. Distinguish between acute toxicity (LD50, GHS category) and chronic hazards (carcinogenicity, endocrine disruption) — they require different risk management approaches. Computational predictions (ADMETAI) are T3 evidence and must be anchored by experimental

End-to-end type-safe APIs for TypeScript with zero code generation. \n \n Shares TypeScript types between client and server automatically—no codegen required, with full type inference across queries, mutations, and subscriptions \n Integrates seamlessly with React Query for caching, optimistic updates, and infinite queries; supports Next.js App Router, Server Components, and WebSocket subscriptions \n Validates all inputs with Zod schemas; includes middleware for authentication, logging, and rat