Structured reasoning tools for AI workflows — isolated cognitive sessions with persistent state and structured output
Structured reasoning tools for AI workflows. Isolated cognitive sessions that don't pollute your context or reinforce your biases.
4 MCP servers, installed with two commands:
| Tool | What it does |
|---|---|
| Structured Reflection | Work through complex logic in an isolated session |
| Decision Matrix | Systematic comparison against weighted criteria |
| Context Switcher | Parallel perspectives from multiple stakeholders/roles |
| Sequential Thinking | Linear reasoning with confidence tracking and contradiction detection |
# 1. Add this marketplace (once)
/plugin marketplace add reasoning-services/marketplace
# 2. Install the plugin
/plugin install reasoning-services@reasoning-services-marketplace
Restart Claude Code. All 4 servers appear in /mcp.
All tools require a subscription. Sign up at reasoning.services.
After subscribing, Claude Code will prompt for OAuth credentials on first tool use.
structured-reflection)Use when thinking feels muddy, you're stuck, or you need to articulate a problem to force clarity. Runs in a separate session — won't pollute your main conversation context.
decision-matrix)Use when you have multiple viable options with real trade-offs. Define criteria, weight them, score each option. Returns structured scoring you can act on.
context-switcher)Use when a decision affects multiple stakeholders or you need to surface blind spots. Runs the same question from different roles/perspectives in parallel.
sequential-thinking)Use when a problem requires explicit step-by-step reasoning. Tracks confidence per step, maps dependencies between steps, detects contradictions.
For complex decisions:
MIT
External network access
Connects to servers outside your machine
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.
npx claudepluginhub reasoning-services/marketplace --plugin reasoning-servicesA deterministic thinking partner that challenges assumptions and applies 150+ mental models to sharpen decisions, solve problems, and think more clearly. Features orientation detection, cognitive operations framework, and structured diagnostic workflows.
A structured toolkit of thinking skills for Claude Code — covering logic, ethics, creativity, decision-making, systems thinking, communication, and more. Each skill is an invokable command that applies a specific reasoning framework to any situation.
A decision operating system for high-stakes choices. Simulates disagreement across 5 independent personas, stress-tests assumptions, and converges on what actually holds up.
Structured thinking methods that counteract LLM reasoning biases during problem exploration — first principles, inversion, constraint manipulation, perspective forcing, analogy search, and more, with user-gated parallel subagent exploration for deep dives
Truth-seeking sparring partner for Claude Code. Challenges claims, decisions, and documents through structured dialectical analysis.
Structured thinking methods as multi-agent sessions — Six Thinking Hats, Adversarial Debate, Disney Method, Pre-Mortem, Polarity Management, TRIZ, W³, Troika Consulting, Wise Crowds, First Principles Decomposition, Analogical Transfer, Morphological Box, Futures Cone — plus meta-cognitive modules (Bias Check, Frame Check, Method Check) that reflect on the thinking itself