researcher
v0.16.4Code-grounded research workflows: ground in the codebase (or given materials), gather external knowledge, and propose improvements, design briefs, library evaluations, and new ideas. Every claim is cited and tiered; local-first with disclosed, fail-closed egress. It proposes and hands implementation to the other suites. Developer-in-the-loop.
By SkylarLicense: MIT0 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 7 skill or MCP entries
- Source updated
- Sep 30, 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 researcher for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install researcher-3@agent-plugin-marketplacePaste 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/skylarsabo/code-opsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/researcher/.
Plugin files
├── .claude-plugin/plugin.json├── skills/ecosystem-watch/SKILL.md├── skills/library-eval/SKILL.md├── skills/research-ideate/SKILL.md├── skills/research-improve/SKILL.md├── skills/research-spike/SKILL.md├── skills/research-sweep/SKILL.md└── skills/research-verify/SKILL.md
Included Skills7
Use to learn what changed in our stack that needs action: dependency updates, CVEs, deprecations, and new capabilities. Schedulable, discovery only, no code.
Use to decide on adopting a library or approach, A versus B versus building it, with code-grounded fit, migration cost, and a tiered verdict. Writes no code.
Use for novel feature ideas grounded in our code, its domain, and opt-in web trends. Writes no code. For code-only ideas, use code-ops-suite:feature-discovery.
Use for improvements to our existing code grounded in external best practice, not a generic checklist. Writes no code, and proposes and hands off instead.
Use when a task, feature, or plan needs a code-grounded design brief before anyone builds it. Writes no code.
Use for code-grounded research as one developer-in-the-loop pipeline, local-first with opt-in disclosed web. Orchestrates and proposes; writes no code.
Use to fact-check a claim, recommendation, or draft research adversarially against sources and our code before anyone acts on it. Review only; writes no code.
Plugin manifests1
{
"name": "researcher",
"description": "Code-grounded research workflows: ground in the codebase (or given materials), gather external knowledge, and propose improvements, design briefs, library evaluations, and new ideas. Every claim is cited and tiered; local-first with disclosed, fail-closed egress. It proposes and hands implementation to the other suites. Developer-in-the-loop.",
"version": "0.16.4",
"license": "MIT",
"author": {
"name": "Skylar"
},
"keywords": [
"research",
"design",
"prior-art",
"library-evaluation",
"ideation",
"evidence",
"grounding",
"egress",
"local-first",
"workflow",
"agents"
]
}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.
[researcher on Agent Plugins Marketplace](https://pluginsmp.com/plugins/researcher-3)