research
Research you already did disappears into chat scrollback, so you re-run the same searches and cannot tell which claims were ever sourced. This plugin runs a structured flow (frame, source, execute, synthesize) and persists reusable entries to a central FTS5-searchable corpus with source scoring, claim verification, quantitative analysis, and project-linked views. You stop repeating work and can show where any claim came from.
By Tyrone RossLicense: Apache-2.00 GitHub starsUpdated last month
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 4 skill or MCP entries
- Source updated
- Sep 8, 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 research for Codex and Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install research-14@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
Compatibility: the page URL and API slug “research-14” remain stable.
- Codex: Legacy selector
research-14@agent-plugin-marketplaceremains documented for migration; install from source for this runtime.
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.
Codex has another source with the same manifest name. This directory does not invent numbered install aliases; use the publisher's catalog or inspect the source manually for that runtime.
Get the source manually
git clone https://github.com/tyroneross/research-pluginClone 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
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/audit-dashboard/SKILL.md├── skills/financial-research/SKILL.md├── skills/research/SKILL.md└── skills/research-orchestrator/SKILL.md
Included Skills4
Render an evidence-led capability audit as a self-contained HTML dashboard. Use when the user asks for a dashboard, capability matrix, render the audit, audit dashboard, or compare repos/tools visually. Not for producing the audit's findings from scratch; use `research` to generate the audit content first, then render here.
Use when the user asks about margin, cost of sales, COGS, gross margin, operating margin, EBITDA, working capital, unit economics, cost bucket, P&L, financial model input, comparable companies, filings, 10-K, or earnings call — any financial or operating-model research where terms, periods, denominators, scopes, and attribution confidence must stay explicit.
Use when the user asks to research, investigate, evaluate, compare options, optimize a research question, extract findings, synthesize, analyze CSV/databases, or save to the research library. Frames the request as meta-questions and MECE section contracts before sourcing. Sourced, verified, persisted to ~/dev/research/. Not for rendering an existing audit's findings as a visual HTML dashboard; use `audit-dashboard` instead. Not for a repo-grounded pre-build decision packet tied to an active build-loop run; use the build-loop plugin's own research skill for that.
Plan and coordinate source-backed research with parallel evidence tasks, bounded second- or third-level link traversal, deterministic quantitative receipts, contradiction-preserving merge, and append-only provenance. Use for requests such as "research this deeply", "use parallel research agents", "follow links two levels", "audit the sources", or "verify the math".
Plugin manifests2
{
"name": "research",
"description": "Research you already did disappears into chat scrollback, so you re-run the same searches and cannot tell which claims were ever sourced. This plugin runs a structured flow (frame, source, execute, synthesize) and persists reusable entries to a central FTS5-searchable corpus with source scoring, claim verification, quantitative analysis, and project-linked views. You stop repeating work and can show where any claim came from.",
"author": {
"name": "Tyrone Ross",
"url": "https://github.com/tyroneross"
},
"repository": "https://github.com/tyroneross/research-plugin",
"license": "Apache-2.0",
"keywords": [
"research",
"knowledge-base",
"aggregation",
"fact-checking",
"source-scoring",
"fts5",
"zettelkasten"
],
"skills": "./skills",
"interface": {
"displayName": "Research",
"shortDescription": "Research done in chat disappears into scrollback and gets re-run. This plugin preserves reusable findings to a central searchable corpus with source scoring and claim verification, so you never repeat a search or lose a citation.",
"longDescription": "Research you already did disappears into chat scrollback, so you re-run the same searches and cannot tell which claims were ever sourced. This plugin runs a structured flow (frame, source, execute, synthesize) and persists reusable entries to a central FTS5-searchable corpus with source scoring, claim verification, quantitative analysis, and project-linked views. You stop repeating work and can show where any claim came from.",
"developerName": "Ross Labs",
"category": "Research",
"capabilities": [
"Interactive",
"Read",
"Write"
],
"websiteURL": "https://github.com/tyroneross/research-plugin",
"privacyPolicyURL": "https://github.com/tyroneross/research-plugin/blob/main/PRIVACY.md",
"termsOfServiceURL": "https://github.com/tyroneross/research-plugin/blob/main/TERMS.md",
"defaultPrompt": [
"Research a topic with sourced findings, confidence notes, and optional persistence to ~/dev/research/."
]
},
"homepage": "https://github.com/tyroneross/research-plugin"
}{
"name": "research",
"description": "Research you already did disappears into chat scrollback, so you re-run the same searches and cannot tell which claims were ever sourced. This plugin runs a structured flow (frame, source, execute, synthesize) and persists reusable entries to a central FTS5-searchable corpus with source scoring, claim verification, quantitative analysis, and project-linked views. You stop repeating work and can show where any claim came from.",
"author": {
"name": "Tyrone Ross",
"url": "https://github.com/tyroneross"
},
"repository": "https://github.com/tyroneross/research-plugin",
"license": "Apache-2.0",
"keywords": [
"research",
"knowledge-base",
"aggregation",
"fact-checking",
"source-scoring",
"fts5",
"zettelkasten"
],
"homepage": "https://github.com/tyroneross/research-plugin"
}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.
[research on Agent Plugins Marketplace](https://pluginsmp.com/plugins/research-14)