jev-gate
v0.1.1Gate agent tool calls before they run: plain-code lock rules ask before dangerous commands, a REUSE ledger stops unchanged expensive re-runs, and TypeSafe Jev judges the gray zone. Runs in shadow mode first (hooks + review skill).
By AgentRelay Maintainers1 GitHub starsUpdated 2 hours ago
Directory evidence
- Runtimes
- Claude Code and Agent Plugins
- Parsed components
- 1 skill or MCP entry
- Source updated
- Sep 28, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install jev-gate for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install jev-gate@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/trisjr/agent-relayClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/jev-gate/.
Plugin files
├── .claude-plugin/plugin.json├── plugin.json└── skills/gate-review/SKILL.md
Included Skills1
Review jev-gate shadow-mode data and decide, with the user, whether to switch the gate to enforce mode, narrow a lock rule, tune a threshold, or build output pruning. Use when the user asks how jev-gate is doing, what it would have asked, reused, or allowed, whether to enable enforce mode, or whether large tool outputs justify pruning.
Plugin manifests2
{
"name": "jev-gate",
"version": "0.1.1",
"description": "Gate agent tool calls before they run: plain-code lock rules ask before dangerous commands, a REUSE ledger stops unchanged expensive re-runs, and TypeSafe Jev judges the gray zone. Runs in shadow mode first (hooks + review skill).",
"author": {
"name": "AgentRelay Maintainers"
},
"userConfig": {
"typesafe_api_key": {
"type": "string",
"title": "TypeSafe API Key",
"description": "API key for the TypeSafe Jev model that judges gray-zone tool calls. Without it, only the lock rules and the REUSE ledger run.",
"sensitive": true,
"required": false
},
"mode": {
"type": "string",
"title": "Gate mode",
"description": "shadow: only lock rules act, everything else is logged. enforce: also apply Jev asks and REUSE denials. Switch only after reviewing shadow data (gate-review skill).",
"default": "shadow"
}
}
}{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "jev-gate",
"version": "0.1.1",
"description": "Gate agent tool calls before they run: plain-code lock rules ask before dangerous commands, a REUSE ledger stops unchanged expensive re-runs, and TypeSafe Jev judges the gray zone. Runs in shadow mode first (hooks + review skill).",
"author": {
"name": "AgentRelay Maintainers"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[jev-gate on Agent Plugins Marketplace](https://pluginsmp.com/plugins/jev-gate)