Agent Plugins Marketplace
← All plugins

jev-atlas

v0.1.0

Maps where a codebase makes, avoids, or could make semantic decisions, finds the ones worth a System One model, and rejects Jev where code, an LLM, embeddings, classical ML, or a human fits better. Then validates and implements the survivors.

Claude Code1 Skill

By Harshit BadigerLicense: MIT0 GitHub starsUpdated 2 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 21, 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-atlas 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-atlas@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/v60samurai/jev-atlas

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

Included Skills1

jev-atlasskills/jev-atlas/SKILL.md

Finds, validates, and implements the highest-value places for Jev / System One models in a codebase by mapping its semantic decision surface, and rejects Jev where code, an LLM, embeddings, classical ML, or a human fits better. Use when the user names Jev, System One, TypeSafe, or Jev Atlas about a project or repo: "where could we use Jev here", "find System One opportunities in this codebase", "run Jev Atlas", "could Jev improve this architecture", "review our existing Jev usage", "validate JEV-002", "implement JEV-004". Also use when asked what a project could do if narrow semantic judgements were suddenly cheap, fast, and callable everywhere. For how to call the API, design a question, or build one already-chosen Jev feature, use the typesafe-ai skill.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "jev-atlas",
  "version": "0.1.0",
  "description": "Maps where a codebase makes, avoids, or could make semantic decisions, finds the ones worth a System One model, and rejects Jev where code, an LLM, embeddings, classical ML, or a human fits better. Then validates and implements the survivors.",
  "author": {
    "name": "Harshit Badiger",
    "url": "https://github.com/v60samurai"
  },
  "homepage": "https://github.com/v60samurai/jev-atlas",
  "repository": "https://github.com/v60samurai/jev-atlas",
  "license": "MIT",
  "keywords": [
    "jev",
    "system-one",
    "typesafe",
    "architecture",
    "llm",
    "claude-code",
    "codex",
    "skill"
  ],
  "skills": [
    "./skills/jev-atlas"
  ]
}

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