ergo

v0.5.0

Read and write checkable data pages that preserve dataset pitfalls and sanctioned practices.

CodexClaude Code1 Skill

By Marc LavalleeLicense: MIT0 GitHub starsUpdated 2 months ago

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Aug 18, 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 ergo for Codex and Claude Code

Installs for the current user

codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add ergo@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. 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/lavallee/ergo

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

ergo/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/ergo/SKILL.md

Included Skills1

ergoskills/ergo/SKILL.md

Work with ergo data pages — the per-dataset documentation format with a structured, code-linked registry of known defects and sanctioned practices. Use when starting work with a documented dataset (read the digest, the core issues, and the practices for your question first), when hitting an unexplained oddity in data (check the registry before diagnosing), when working around a data problem in code (register the issue and anchor the fix), when deciding how a number may be computed (check for a practice before inventing one), or when authoring/revising a data page. Spec: https://github.com/lavallee/ergo

Plugin manifests2

.codex-plugin/plugin.json

{
  "name": "ergo",
  "version": "0.5.0",
  "description": "Read and write checkable data pages that preserve dataset pitfalls and sanctioned practices.",
  "author": {
    "name": "Marc Lavallee"
  },
  "homepage": "https://lavallee.github.io/ergo/",
  "repository": "https://github.com/lavallee/ergo",
  "license": "MIT",
  "keywords": [
    "data",
    "datasets",
    "documentation",
    "data-journalism",
    "open-data",
    "provenance",
    "etl",
    "codex"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "ergo — dataset pitfalls, written down",
    "shortDescription": "Dataset pitfalls and sanctioned practices",
    "longDescription": "Check what is already known before touching a dataset, record new pitfalls in a durable format, and preserve the practices that govern honest use.",
    "developerName": "Marc Lavallee",
    "category": "Research",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "websiteURL": "https://lavallee.github.io/ergo/",
    "defaultPrompt": [
      "Use Ergo to inspect this dataset's known pitfalls.",
      "Use Ergo to document the data problem I just found.",
      "Recover an Ergo data page from this existing loader."
    ]
  }
}

.claude-plugin/plugin.json

{
  "name": "ergo",
  "displayName": "ergo — dataset pitfalls, written down",
  "version": "0.5.0",
  "description": "Teaches your agent to look for what is already known about a dataset before touching it, to record what it learns in a checkable format, and to offer the public-safe part back. One skill covers working with data pages and recovering one from code that already parses the data.",
  "author": {
    "name": "Marc Lavallee"
  },
  "homepage": "https://lavallee.github.io/ergo/",
  "repository": "https://github.com/lavallee/ergo",
  "license": "MIT",
  "keywords": [
    "data",
    "datasets",
    "documentation",
    "data-journalism",
    "open-data",
    "provenance",
    "etl"
  ]
}