Agent Plugins Marketplace
← All plugins

jev-expert

v0.1.1

Production-integration discipline for TypeSafe Jev: rollout modes, failure handling, versioning, evaluation, and audits. Complements the official typesafe plugin.

Claude Code1 Skill

By Mark JedrzejczykLicense: MIT0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 26, 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-expert for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install jev-expert@agent-plugin-marketplace

Paste 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/Nostoi/jev-expert

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

jev-expert/
├── .claude-plugin/plugin.json
└── skills/jev-engineering/SKILL.md

Included Skills1

jev-engineeringskills/jev-engineering/SKILL.md

Engineering discipline for putting TypeSafe Jev (System One) decisions into real software safely: choosing the insertion point, off/shadow/active rollout, keeping API failures distinct from negative answers, versioning questions and thresholds, decision logging, retry and side-effect safety, outcome verification, and evaluation. Use this whenever you are adding Jev or the TypeSafe API to an existing codebase, replacing an LLM prompt-and-parse step or a brittle classifier with Jev, auditing or debugging a Jev-assisted decision, or preparing a Jev integration for rollout — even if the user only says "use Jev here" or "wire up TypeSafe". Pair it with the official typesafe-ai skill, which owns the API contract and question design.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "jev-expert",
  "version": "0.1.1",
  "description": "Production-integration discipline for TypeSafe Jev: rollout modes, failure handling, versioning, evaluation, and audits. Complements the official typesafe plugin.",
  "author": {
    "name": "Mark Jedrzejczyk"
  },
  "license": "MIT"
}

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-expert on Agent Plugins Marketplace](https://pluginsmp.com/plugins/jev-expert)