NourEldinShobier

Toolgate — AI skill for Claude Code

AI community

A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts.

How to install Toolgate

This entry records only its repository, not the path inside it, so there is no exact command to give. Open NourEldinShobier/toolgate and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Toolgate does

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.

Alternatives in AI

Typesafe MCP — An mcp connector to evaluate anything fast and cheap 258 ★
Dsh Auto Review — Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns stru 155 ★
Ask All — Ask GPT, Gemini, Grok, and any configured OpenRouter models in parallel for independent second opinions, then 135 ★

README

toolgate

[![npm](https://img.shields.io/npm/v/@riskaverse/toolgate?label=npm)](https://www.npmjs.com/package/@riskaverse/toolgate) [![release](https://img.shields.io/github/v/release/RiskAverseTech/toolgate?include_prereleases&label=release)](https://github.com/RiskAverseTech/toolgate/releases) [![CI](https://github.com/RiskAverseTech/toolgate/actions/workflows/ci.yml/badge.svg)](https://github.com/RiskAverseTech/toolgate/actions/workflows/ci.yml) [![license](https://img.shields.io/badge/license-MIT-blue)](LICENSE)

**Featured:** AI LABS tested the Jev tools built since launch and kept eight; toolgate is first in [This Just Fixed Your Claude Code Setup's Biggest Flaw](https://www.youtube.com/watch?v=jlEMo6Dsh9E) (October 7, 2026). Their independent test caught a folder deletion at 77% destructive risk, which lands in the ask band, as designed: a delete the task did not call for gets one confirmation, not a block.

**Open auto mode for AI agents.** A calibrated tool-call firewall that runs as a Claude Code mod (or `PreToolUse` hook) or as an MCP proxy in front of any MCP server (Cursor, Claude Desktop, custom agents): before the agent runs a risky action, toolgate asks a decision model — [TypeSafe's Jev](https://typesafe.ai/blog/introducing-system-one-models-and-jev), through its API directly, via [OpenRouter's Decisions API](https://openrouter.ai/docs/api/api-reference/alphadecisions/submit-a-decisions-questions-and-answers-request), or via [Vercel AI Gateway](https://vercel.com/changelog/typesafe-ai-jev-now-available-on-ai-gateway) — seven questions and acts on the probabilities. It is the "permissions / approval" pattern TypeSafe's CEO describes in his [public memo on a typesafe coding agent](https://docs.google.com/document/d/1G61uUB0FifUnmmrPzFQojZ3KpczYKmXGpgEXDJ2l_Zg/) — programmable queries on what may run, and reading what a file does before executing it — built as a plugin to the agents people already use, and measured (see [Evaluation](#evaluation)):