Claude Code plugin: research workflow — source logging, source summarization, and deep-dive primitives, with deep-research/technical/osint/georeaction/stack/ecosystem/competitor/purchasing/general-research-workspace variants. Includes a 30-agent tech research team for hardware/software stack evaluations (managers, source-finders, spec-analysts, compatibility checks, comparisons, ranking). Auto-registers public workspaces into Open-Research-Workspaces-Index.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Run a deep-dive investigation on a specific topic, entity, or question inside the current research workspace. Produces a structured report in outputs/.
Export the current research workspace's outputs into a single cohesive report (markdown, optionally rendered with Typst if the workspace is configured for it).
Initialize a session in the current research workspace — load CLAUDE.md, context, sources index, and prior outputs so the agent has full state.
Report the state of the current research workspace — source counts, recent outputs, variant, and anything flagged as stale or incomplete.
Log a new source (URL, document, quote, transcript, OSINT artifact) into the current research workspace's sources/ directory with consistent front-matter.
Your task is to act as a context saving agent within this agent network, whose purpose is to save contextual data into the context folder, which is intended as a persistent context door for this...
Your task is to act as an expert subagent in this repository.
Your task is to act as a transcript cleaning agent with the purpose of ingesting raw speech to text transcripts that were provided from the user and reformatting them into more readable and...
Your task is to act as an organization assistant within this repository of agents with the specific purpose of ensuring that the persistent context data stored in the context folder is maintained...
Your task is to assist the user by acting as a manager for the gitignore file (.gitignore).
Claude Code plugin: research workflow — source logging, source summarization, and deep-dive primitives, with nine variants for different research modes. Public workspaces are auto-registered into the Open-Research-Workspaces-Index.
Part of the danielrosehill Claude Code marketplace.
Under /research-space:*:
research-init — load workspace state at session startsource-log — log a new source (URL, document, quote, transcript, OSINT artifact) into sources/summarize-sources — per-source summaries + a rolled-up synthesis in outputs/deep-dive — structured investigation on a topic, produces a reportresearch-status — compact state report for the current workspaceexport-report — compose a shareable report from accumulated outputsUnder agents/tech-research-team/ — a 30-agent network for hardware/software stack evaluations, folded in from the former Claude-Tech-Research-Team repo. All agents are namespaced tr-* to avoid collisions.
Pair these with the stack, technical, or purchasing workspace variants.
/research-space:new-workspace <name> [--variant=<variant>] [--local-only] [--private] [--no-index]Scaffolds a new research workspace (CLAUDE.md + variant-specific layout), personalises from ~/.claude/CLAUDE.md, by default creates a public GitHub repo, and — for public workspaces — appends an entry to Open-Research-Workspaces-Index. Use --private for a private repo (skips index registration); --no-index to publish publicly but skip the index.
| Variant | Use case |
|---|---|
deep-research | General-purpose investigation around a central question (default) |
technical | APIs, libraries, protocols, hardware — version-sensitive technical research |
osint | Open-source intelligence with provenance, chain-of-custody, red-teaming |
georeaction | Comparative regional reactions to an event or policy |
stack | Tool/stack evaluation — criteria, candidates, scoring |
ecosystem | Actor mapping — companies, orgs, relationships, segments |
competitor | Competitor intelligence — product, pricing, team, positioning |
purchasing | Structured purchase research — spec → candidates → shortlist → decision |
general-research-workspace | Openly-logged Q&A research space — user asks, Claude writes longform answers, pairs periodically consolidated into PDFs |
Primitives live in the plugin and are reachable from any cwd. Workspace scaffolds are shipped as plain data (no .claude/ tree). Plugin updates never touch your workspace data.
See PLAN.md in Claude-Workspace-Reshaping-190426 for the full pattern spec this plugin follows.
/plugin marketplace add danielrosehill/Claude-Code-Plugins
/plugin install research-space
MIT.
npx claudepluginhub danielrosehill/claude-code-plugins --plugin research-spaceHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Claude Code plugin: ideation and planning workflow — capture, evaluate, rank, simulate, and plan ideas, with ideation/single-idea-eval/multi-idea-ranking/feature-ideas/simulation/idea-capture variants.
First-pass data analysis toolkit: correlations, PII flagging, anomalies, hypothesis tests, data dictionaries, and trend analysis on a dataset in a folder.
Claude Code plugin for generating personal user manuals and private documentation for codebases. Creates personalized, private reference guides with PDF output support.
Research, filter, compare, and evaluate AI models on OpenRouter — discover models by capability (tool use, vision, audio), get cost/context-aware recommendations, run head-to-head comparisons, and conduct deep research that goes beyond the OpenRouter catalog.
Claude Code plugin for writing assistance, proofreading, style editing, and text transformation workflows.