claudecodemods.dev

All mods / riskaversetech/toolgate

toolgate

CAUTION

★ 26 by riskaversetech Repository ↗ Mod source ↗

Safety & guards

Description

A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on TypeSafe Jev, measured on real sessions with a blind second labeler.

What it can do

Reach level 2 — writes or runs What does this mean? →

runs processesdrives Claudereads settingsreads the transcriptdrawsother: $.tool.check
Raw API calls (12) +
  • $.command.register
  • $.command.run
  • $.process.run
  • $.session.cwd
  • $.session.id
  • $.session.messages
  • $.session.start
  • $.settings.read
  • $.tool.call
  • $.tool.check
  • $.ui.status
  • $.ui.toast

Not validated against a Claude Code release.

Install

$/plugin marketplace add riskaversetech/toolgate
$/plugin install toolgate

Check the repo for the exact name.

Details

Repository
riskaversetech/toolgate
Path in repo
plugin
License
Unknown
Last updated
Oct 15, 2026
First seen
Oct 15, 2026
Last scanned
Oct 15, 2026

Related mods — reach level 2

Capability data is machine-generated by static analysis and may be incomplete. A SAFE badge is not a guarantee — read the code before installing anything with broad access. Not affiliated with Anthropic.

Found a mistake in this listing or verdict? Report an issue →