toolgate

by Jaz · ★ 28 · updated 18 days ago

Status lineGuardsCommandswarnings

0

Tool-call firewall for Claude Code built on TypeSafe's Jev: seven risk questions, an action ledger that judges files at write time, floors on the axes that must not soften, and ask instead of allow when the model is unreachable. Every verdict logged with its probabilities.

install toolgate

Install

/plugin marketplace add RiskAverseTech/toolgate
/plugin install toolgate@riskaverse

Then run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.

View source on GitHub

What it hooks into

From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.

Events
session.starttool.checktool.callcommand.run
API calls
$.command.register$.process.run$.session.cwd$.session.id$.session.messages$.settings.read$.ui.status$.ui.toast
Can see
every tool call
Reach
level 2 of 3 runs processesreads settingsreads the transcriptdraws

Origin

How it got here
Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
Repository
github.com/RiskAverseTech/toolgate
Path in repo
plugin
Source commit
dec68c9 the exact code the scan read
Author
Jaz @RiskAverseTech
License
MIT
First published
Last pushed
First listed here

Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.