Claude Code plugin for LLM research with typed claims and conflict detection

Research sprint orchestrator for Claude Code. Ask a question, get a decision-ready brief. Every finding is tracked as a typed claim, adversarially challenged, confidence-graded, and compiled into self-contained output. Zero third-party dependencies. grainulator.app — interactive demo with in-browser AI. No install needed. claude plugin marketplace add https://github.com/grainulation/grainulator/blob/main/.claude-plugin/marketplace.json claude plugin install grainulator Requirements: Node.js >= 20 (needed for MCP servers that run via npx). Troubleshooting: SSH permission denied If you see [email protected]: Permission denied (publickey) , the plugin installer is trying SSH but you don't have SSH keys set up with GitHub. Fix with one command: git config --global url."https://github.com/".insteadOf "[email protected]:" Then retry claude plugin install grainulator . This tells git to use HTTPS instead of SSH for all GitHub repos. Alternatively, clone manually: git clone https://github.com/grainulation/grainulator.git ~/.claude/plugins/grainulator claude plugin add ~/.claude/plugins/grainulator For team-wide deployment, commit to your project's .claude/settings.json : { "enabledPlugins": ["grainulator@grainulation-marketplace"] } Once installed, just talk to Claude: - "research how our auth system works" — runs a multi-pass research sprint - "challenge r003" — adversarial testing of a specific claim - "what are we missing?" — blind spot analysis - "write it up" — generates a compiled brief No slash syntax required. The intent router detects what you want and runs the right workflow. Claims are the unit of knowledge. Every finding from research, challenges, witnesses, and prototypes is stored as a typed claim in claims.json . | Claim type | What it means | |---|---| constraint | Hard requirements, non-negotiable boundaries | factual | Verifiable statements about the world | estimate | Projections, approximations, ranges | risk | Potential failure modes, concerns | recommendation | Proposed courses of action | feedback | Stakeholder input, opinions | Evidence tiers grade confidence: stated → web → documented → tested → production . The compiler runs 7 passes over your claims — type coverage, evidence strength, conflict detection, bias scan — and produces a confidence score. If there are unresolved conflicts, it blocks output until you resolve them. | Skill | Description | |---|---| /init | Start a new research sprint | /research | Multi-pass investigation with evidence gathering | /challenge | Adversarial testing of a claim | /witness | Corroborate a claim against an external source | /blind-spot | Structural gap analysis | /brief | Generate a compiled decision brief | /present | Generate a presentation deck | /status | Sprint dashboard snapshot | /pull | Import knowledge from external sources (DeepWiki, Confluence) | /sync | Publish artifacts to external targets | /calibrate | Score predictions against actual outcomes | /resolve | Adjudicate conflicts between claims | /feedback | Record stakeholder input | The grainulator subagent (agents/grainulator.md ) runs multi-pass research sprints autonomously. It reads the compiler output to decide what command to run next — research, challenge, witness, blind-spot — until the sprint reaches decision-ready confidence. Launch it from Claude Code with: "research X using grainulator" . grainulator.app is a PWA that demos the research sprint concept in-browser: - Mobile-first chat interface — no shader on mobile, dark background - In-browser AI via WebLLM (SmolLM2-360M, ~200MB download) - 50 pre-generated demo topics with fuzzy matching (instant Track A) - Live local inference when model downloads (Track B) - Conversational responses with progressive claim disclosure - Compile flow with 7-pass confidence scoring - Plugin manifest: .claude-plugin/plugin.json - MCP servers: wheat (claims engine), mill (format conversion), silo (knowledge store), DeepWiki (codebase research) - Skills: skills//SKILL.md — 13 prompt-engineered workflows - Agent: agents/grainulator.md — autonomous sprint subagent - Hooks: Auto-compile on claim mutation, write-guard on claims.json andcompilation.json - Orchard: Multi-sprint orchestration via orchard.json dependency graphs Part of the grainulation ecosystem. Eight tools, each does one thing. | Tool | What it does | Install | |---|---|---| | wheat | Research engine — grow structured evidence | npx @grainulation/wheat init | | farmer | Permission dashboard — approve AI actions in real time | npm i -g @grainulation/farmer | | barn | Shared tools — templates, validators, sprint detection | npm i -g @grainulation/barn | | mill | Format conversion — export to PDF, CSV, slides | npm i -g @grainulation/mill | | silo | Knowledge storage — reusable claim libraries and packs | npm i -g @grainulation/silo | | harvest | Analytics — cross-sprint patterns and prediction scoring | npm i -g @grainulation/harvest | | orchard | Orchestration — multi-sprint coordination | npm