Agent Plugins Marketplace
← All plugins

logical-research

v1.1.1

Scan a question or Pack a bounded corpus into reusable, traceable context with evidence-graded claims.

CodexClaude Code1 Skill

By Nathan Wong1 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 27, 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 logical-research for Codex and Claude Code

Installs for the current user
codex plugin marketplace add thelogicmatrix/lm-tools
codex plugin marketplace upgrade lm-tools
codex plugin add logical-research@lm-tools

Paste and run these commands in a terminal with Codex. They add and refresh the lm-tools catalog, then install this plugin.

Compatibility: the page URL and API slug “logical-research” remain stable.

  • Codex: logical-research@agent-plugin-marketplace → logical-research@lm-tools

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/thelogicmatrix/lm-tools

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

Plugin files

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

Included Skills1

logical-researchskills/logical-research/SKILL.md

Use whenever research is asked for or a body of source material must become reusable, traceable context. Triggers on "research X", "look into X properly", "what do the docs or sources say about X", "research this channel/author/book", "build me a knowledge pack on X", "read all of these and synthesise", or when a later task needs principles extracted from sources with every claim traceable. Self-selects a tier, Scan (a question or a small source set, one graded file) or Pack (a bounded corpus, the full pipeline). A single fact lookup with no synthesis is a plain search, not this.

Plugin manifests2

logical-research/.codex-plugin/plugin.json
{
  "name": "logical-research",
  "version": "1.1.1",
  "description": "Scan a question or Pack a bounded corpus into reusable, traceable context with evidence-graded claims.",
  "author": {
    "name": "Nathan Wong"
  },
  "skills": "./skills/",
  "interface": {
    "displayName": "Logical Research",
    "shortDescription": "Scan a question or Pack a corpus into traceable context",
    "longDescription": "Scan a question or a small source set into one graded file, or Pack a bounded corpus end to end into evidence-graded synthesis, per-item notes, and a traceable bibliography.",
    "developerName": "Nathan Wong",
    "category": "Research",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": "Research this bounded corpus and build reusable context from it."
  }
}
logical-research/.claude-plugin/plugin.json
{
  "name": "logical-research",
  "version": "1.1.1",
  "description": "Logical Research — Scan a question or Pack a bounded corpus into reusable, traceable context: evidence-graded claims, sources ranked by authority, per-item notes and a bibliography at Pack.",
  "author": {
    "name": "Nathan Wong"
  }
}

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.

[logical-research on Agent Plugins Marketplace](https://pluginsmp.com/plugins/logical-research)