research-council
v0.2.0Claude Code integration for portable research-council: bounded investigations, competing explanations, evidence-linked reports, and structured handoffs for people and agents. Model-neutral workflow with return-only council roles and a script-gated skill library.
By Abhishek SharmaLicense: MIT0 GitHub starsUpdated yesterday
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 3 skill or MCP entries
- Source updated
- Sep 22, 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-council for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install research-council-2@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/abhisheksharma001/research-councilClone 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
├── .claude-plugin/plugin.json├── skills/code-writer-council/SKILL.md├── skills/research-council/SKILL.md└── skills/self-improve/SKILL.md
Included Skills3
Run a bounded write-review-verify loop whenever the agent is about to write or change code in a repository where this plugin is installed. A frozen task record carries the request, allowed paths, test command and the user's caps; the diff size picks the reviewers; a script runs the tests and prints "done", the model never does. A diff of ten lines or fewer takes the exit, scripts only, no subagent. Not for research questions, unknown causes, or competing explanations; send those to research-council.
Run a bounded investigation of a hard research, decision, or debugging problem before committing to a solution. Use when asked to research, investigate, explain a behaviour, or compare competing explanations, especially when a wrong answer costs money or data. Produces evidence-linked FINDINGS.md, a practical HANDOFF.md, and optional structured JSON for the next agent. Not for small tasks that one command or one test can settle.
Run research-council on its own repository to find the weakest part of the plugin and turn the findings into proposed register steps. Use when asked to improve, audit, or review research-council itself, or to continue its self-improvement loop. Ends with FINDINGS.md in an ignored run folder, a run note in docs/runs/, and S-n rows in docs/spec-v1.md. Never merges, never spends money, never leaves this repository.
Plugin manifests1
{
"name": "research-council",
"description": "Claude Code integration for portable research-council: bounded investigations, competing explanations, evidence-linked reports, and structured handoffs for people and agents. Model-neutral workflow with return-only council roles and a script-gated skill library.",
"version": "0.2.0",
"author": {
"name": "Abhishek Sharma",
"email": "[email protected]"
},
"license": "MIT"
}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-council on Agent Plugins Marketplace](https://pluginsmp.com/plugins/research-council-2)