Claude Code Plugins
Interpretive Orchestration: Epistemic Partnership for Qualitative Research
Interpretive Orchestration gives qualitative research sessions a staged workflow, specialist agents, and enforceable checks.
AI can automate coding, but interpretive depth demands deliberate partnership.
Interpretive Orchestration is a Claude Code plugin for structured human-AI collaboration in qualitative research. It is not a tool for faster coding; it is infrastructure for deeper thinking.
Info
Created by: Xule Lin & Kevin Corley (Imperial College London)
Version: v0.2.4
Framework: Cognitio Emergens (Lin, 2025) — Partnership Agency for interpretive inquiry
Paper: Interpretive Orchestration (Lin, 2026, Strategic Organization) — the methodology this plugin operationalizes
GitHub: linxule/interpretive-orchestration
Starter project: interpretive-orchestration-starter — a ready-to-use VS Code workspace with beginner-friendly settings
Warning
This plugin deliberately enforces methodological rigor. You cannot skip stages or bypass human judgment. If you want speed over depth, this is not the right tool. If you want to become a better interpretive researcher, welcome to the atelier.
Host support
| Host | Status | Notes |
|---|---|---|
| Claude Code (CLI) | Full | The plugin's native target. The starter project ships a VS Code workspace tuned for CLI use. |
| Claude Code (Desktop "Code" tab) | Full | Same engine; identical commands and agents. |
| Codex CLI / Codex Desktop | Adjacent | The plugin runs inside Claude Code, but a Codex session can install it for you cross-host (claude plugin marketplace add linxule/interpretive-orchestration && claude plugin install interpretive-orchestration@interpretive-orchestration), after which you switch over to run the /qual-* commands and methodology hooks. The methodology itself — staged solo→partnership→tradition work, the Cognitio Emergens framework — is also portable on its own: Codex users can read the paper and recreate the workflow without the plugin's enforcement layer. |
| Cursor / other clients | Out of scope | Plugin format is CC-only. |
The bundled MCPs (Sequential Thinking, Lotus Wisdom, Markdownify) are reusable across any MCP client even when the plugin itself isn't.
What makes this different?
Traditional AI approach:
- Give AI your data → Get instant analysis → Review output
- AI automates manual labor (the "calculator mindset")
- Faster but not necessarily deeper
Interpretive Orchestration approach:
- Build your foundation first → Collaborate with visible reasoning → Synthesize with tradition
- AI asks questions that deepen YOUR reflexivity
- Scale and interpretive depth through Partnership Agency
"Human and AI boundaries dissolve into unified epistemic system generating insights neither could produce independently." — Cognitio Emergens (Lin, 2025)
The philosophy: Friction over flow. If the plugin stops you, it's asking you to think.
The atelier of co-apprenticeship
Both human and AI are apprentices to the craft tradition of interpretive inquiry. Neither masters the other. Both learn from craft principles: rigor, reflexivity, theoretical sensitivity, interpretive depth.
Solo practice
What you do: Manual coding of 10-15 documents, memo-writing, framework development
AI role: @stage1-listener watches but doesn't intervene
Why it matters: Builds the irreplaceable theoretical sensitivity that makes partnership meaningful. This stage is enforced - doors to collaborative workspace stay locked until complete.
Side-by-side collaboration
What you do: Guide AI, refine patterns, parallel theoretical + empirical streams
AI role: @dialogical-coder with 4-stage visible reasoning:
- What I observe in the data
- What patterns I'm noticing
- What theoretical connections emerge
- What remains uncertain
@research-configurator translates technical decisions to research language, so you do not need coding knowledge for this step.
Dialogue with tradition
What you do: Interpret significance, synthesize findings
AI role: @scholarly-companion asks tradition's questions (Gioia, Corley, Constructivist GT)
Outcome: Work that can withstand methodological scrutiny
Skills architecture
Skills are auto-discoverable capability packages that Claude loads when relevant to your request.
| Skill | Triggers | Purpose |
|---|---|---|
project-setup | "initialize", "new project" | Socratic onboarding + config |
gioia-methodology | "data structure", "Gioia" | Data structure building (1st→2nd→aggregate) |
literature-sweep | "literature", "Stream A" | Search + fetch + organize papers |
interview-ingest | "transcribe", "convert audio" | Audio/PDF conversion |
deep-reasoning | "think through", "plan" | Sequential Thinking integration |
paradox-navigation | "tension", "both/and" | Lotus Wisdom integration |
Full list of all 12 skills with complete triggers in CLAUDE.md on GitHub.
Bundled MCPs
Core functionality does not require API keys.
| MCP | Purpose in Plugin | Command |
|---|---|---|
| Sequential Thinking | Structured reasoning chains | /qual-think-through |
| Lotus Wisdom | Navigate paradoxes, integrate tensions | /qual-wisdom-check |
| Markdownify | Convert PDFs, transcribe audio, extract from videos | /qual-import-pdf |
Optional MCPs (require API keys):
| MCP | Purpose | Key Required |
|---|---|---|
| MinerU | High-accuracy PDF parsing (90%+) | MINERU_API_KEY |
| Vox MCP | Multi-model access | Provider API keys |
| Exa | Literature search | EXA_API_KEY |
| Jina | Fetch articles | JINA_API_KEY |
| Zotero | Bibliography management | ZOTERO_API_KEY |
Quick start
New to Claude Code? See INSTALL.md for complete setup instructions (Windows, macOS, Linux).
Want a pre-configured environment? Use the Starter Project — a ready-to-use VS Code workspace with beginner-friendly settings.
Already have Claude Code?
cd your-qualitative-project
claude
/plugin install linxule/interpretive-orchestration
/qual-check-setup # Verify installation
/qual-init # Begin Socratic onboardingThen: Complete Stage 1 manual coding (10-15 documents) before AI-assisted analysis. This builds the irreplaceable theoretical sensitivity that makes partnership meaningful.
Key commands
| Command | Stage | Purpose |
|---|---|---|
/qual-init | 0 | Begin Socratic philosophy establishment |
/qual-status | Any | Check where you are in the journey |
/qual-think-through | 1+ | Deep sequential reasoning |
/qual-wisdom-check | 1+ | Navigate interpretive paradoxes |
/qual-parallel-streams | 2 | Run theoretical + empirical streams |
/qual-synthesize | 2+ | Merge discovery streams |
/qual-reflect | Any | End-of-session dialogue |
Agents
The plugin provides four specialised agents, each scoped to a particular stage of the atelier methodology.
| Agent | Stage | Role |
|---|---|---|
@stage1-listener | 1 | Thinking partner — asks questions, never suggests codes |
@dialogical-coder | 2 | 4-stage visible reasoning for reflexive coding |
@research-configurator | 2 | "The Whisperer" — technical setup without jargon |
@scholarly-companion | 3 | Asks tradition's questions about theoretical significance |
@research-configurator ("The Whisperer") bridges research goals and technical implementation for non-coding researchers, covering model selection, cost estimation, batch processing strategy, saturation monitoring, and more. Invoke with @research-configurator Help me set up my analysis.
Methodology hooks
The plugin enforces the sandwich methodology through automated hooks:
- PreStage2 - Blocks AI coding until Stage 1 foundation complete
- PostFiveDocuments - Triggers interpretive pause every 5 documents
- EpistemicCoherence - Checks philosophical consistency
If you're blocked, it's asking you to think. That's intentional epistemic friction.
Who should use this?
- PhD students learning qualitative methods
- Researchers committed to methodological rigor
- Those working with Gioia methodology or Constructivist GT
- Anyone valuing depth over speed
- Researchers who want defensible AI-assisted work
- Those interested in human-AI epistemic partnership
Connection to Research Memex
This plugin is the practical implementation of interpretive orchestration - the core philosophy that animates Research Memex.
The progression:
- Core Principles → Understand the philosophy
- Individual MCPs → Learn the tools (Sequential Thinking, Lotus Wisdom, Vox)
- Interpretive Orchestration Plugin → Apply it all to qualitative research
Resources
- GitHub: linxule/interpretive-orchestration - Full documentation, INSTALL.md, QUICK-START.md
- Framework Paper: Cognitio Emergens (Lin, 2025)
- Implementation Paper: Interpretive Orchestration (Lin, 2026, Strategic Organization)
- Quick Reference: QUICK-START.md
- Architecture: ARCHITECTURE.md