ucsandman/DashClaw

🛡️ The approval and policy layer for AI agents. Intercept risky actions before they run, block them, or approve them remotely.

296Stars on the repository
40Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

PreToolUse

01

ucsandman/DashClaw

Hook

Runs before the agent uses a tool for Agent, Task, Bash, Edit, Write, MultiEdit and mcp__.* tool calls, executing run_hook.cjs via node. From ucsandman/DashClaw.

296 3d ago A tokens not measured original MIT

PostToolUse

02

ucsandman/DashClaw

Hook

Runs after a tool call finishes for Agent, Task, Bash, Edit, Write, MultiEdit and mcp__.* tool calls, executing run_hook.cjs via node. From ucsandman/DashClaw.

296 3d ago A tokens not measured original MIT

Stop

03

ucsandman/DashClaw

Hook

Runs when the agent finishes a response, executing run_hook.cjs via node. From ucsandman/DashClaw.

296 3d ago A tokens not measured original MIT

SessionStart

04

ucsandman/DashClaw

Hook

Runs when a session starts, executing run_hook.cjs via node with --source. From ucsandman/DashClaw.

296 3d ago A tokens not measured original MIT