OpenLatch

OpenLatch/saferskills

Hook Claude Code

Runs before the agent uses a tool for Edit and Write tool calls, executing block-generated.sh via bash. From OpenLatch/saferskills.

OpenLatch/saferskills

Hook Claude Code

Runs after a tool call finishes for Edit and Write tool calls, executing auto-format.sh via bash. From OpenLatch/saferskills.

OpenLatch/saferskills

Hook Claude Code

Runs when the agent finishes a response, executing type-check.sh via bash. From OpenLatch/saferskills.

OpenLatch/saferskills

Settings file Claude Code

Agent settings declaring 4 hook events (PreToolUse, PostToolUse, Stop, SessionStart).

OpenLatch/saferskills

Instructions file

Instructions for OpenLatch/saferskills, covering claude.md — saferskills, quick start, backend, frontend and codegen.

OpenLatch/saferskills

Agent

Pinned known-good config shapes the 8 writers target, with the official source + retrieval date. The MEDIUM/LOW (volatile) surfaces carry a live-verification gate: their checkbox stays ☐ until a maintainer installs the entry against a real running agent and confirms it loads, then ticks it here. A surface that cannot…

OpenLatch/saferskills

Skill Claude CodeCodex

Use SaferSkills to find, evaluate, and safely install AI agent capabilities (skills, MCP servers, hooks, plugins, rules) and to assess a whole agent. Run this before you install, add, recommend, or trust any capability — or when asked whether one is safe or what its score is: scan and score it first with npx…