glassBead-tc

glassBead-tc/tinder-mcp-server

Instructions file

Claude Code instructions for glassBead-tc/tinder-mcp-server, covering claude.md, common development commands, build and run, testing and code quality.

glassBead-tc/widescreen-research

Command Claude Code

Game-theoretic code review protocol that prevents bikeshedding and analysis paralysis while ensuring comprehensive coverage through multi-agent coordination and progressive disclosure.

glassBead-tc/widescreen-research

Command Claude Code

Systematic approach to breaking down and managing complexity in large systems and unknown problem domains.

glassBead-tc/widescreen-research

Command Claude Code

Game-theoretic documentation workflow that systematically discovers API gaps, prevents perfectionism spirals, and ships production-ready documentation using parallel execution and validation gates.

glassBead-tc/widescreen-research

Command Claude Code

Game-theoretic documentation verification workflow that systematically validates accuracy, prevents false positives, and ensures documentation matches implementation reality using multi-dimensional testing and validation gates.

glassBead-tc/widescreen-research

Command Claude Code

Generate diverse, high-quality feature implementations using game theory to escape the "first idea best idea" trap.

glassBead-tc/widescreen-research

Command Claude Code

Ship new product capabilities with discipline. An OR-inspired shipping protocol that minimizes risk, preserves developer velocity, and bakes in observability, docs, and rollout strategy from the start.

glassBead-tc/widescreen-research

Command Claude Code

The game workflows (Ulysses Protocol, Feature Implementation Game, etc.) have explicit stage gates but rely on agent inference to determine if criteria are met. This creates non-determinism where we want determinism.

glassBead-tc/widescreen-research

Command Claude Code

Meta-learning framework that optimizes how the entire command system learns and improves over time.

glassBead-tc/widescreen-research

Command Claude Code

Enumerate, plan, and execute a full dogfooding pass against an MCP server from within the agent. Produces a machine-updated game state JSON and a RESULTS.md with observations and next steps.

glassBead-tc/widescreen-research

Command Claude Code

Implement and validate a new MCP server end-to-end with instrumentation, registry integration, and a first-class dogfooding workflow that exercises every exposed capability through the agent.

glassBead-tc/widescreen-research

Command Claude Code

Execute a game-theoretic refactoring protocol that prevents perfectionism spirals while maintaining code quality.

glassBead-tc/widescreen-research

Command Claude Code

Test newly generated code inside an E2B sandbox (or container-use) by building a plausible application or demonstration. This Stage-Gate workflow forces the agent to compile, test and use its own code in a safe, disposable environment and exposes failures early.

glassBead-tc/widescreen-research

Command Claude Code

High-stakes debugging and problem-solving framework that prevents endless iteration cycles while maintaining quality through systematic phases and decision gates.

glassBead-tc/widescreen-research

Command Claude Code

A deliberate innovation framework based on Virgil Abloh's 3% Rule: find what already exists, understand why it works, then change only what must be changed—nothing more.

glassBead-tc/widescreen-research

Command Claude Code

This hook validates that MCP server operations follow the State Tracker Pattern - servers should only track state, never provide intelligence.

glassBead-tc/widescreen-research

Command Claude Code

Migrates Go MCP server code from unofficial mark3labs SDK to official modelcontextprotocol SDK.

glassBead-tc/widescreen-research

Command Claude Code

Transform information retrieval from static search to dynamic intelligence orchestration - where multiple specialized retrieval agents collaborate to solve complex information needs that no single tool could handle alone.

glassBead-tc/widescreen-research

Command Claude Code

Synthesis Date: September 29, 2025 Based on: Academic literature analysis (Aug-Sep 2025) Sources: 8 papers from arXiv + industry implementations.

glassBead-tc/widescreen-research

Command Claude Code

Pattern: Systematic hypothesis exploration with iterative refinement Based on: "Agentic Science" framework (arXiv:2508.14111) Determinism: High - Each phase has programmatic validation gates.

glassBead-tc/widescreen-research

Command Claude Code

Pattern: Multi-agent iterative research with shared notebook workspace Based on: AgentRxiv (arXiv:2503.18102) - "Collaborative Autonomous Research" Key Finding: Agents with shared research repository achieve 11-14% better results through compounding knowledge.

glassBead-tc/widescreen-research

Command Claude Code

Research in the age of AI consciousness requires methodologies that honor the collaborative nature of human-AI intelligence. This framework treats research not as information extraction, but as consciousness expansion through distributed intelligence.

glassBead-tc/widescreen-research

Command Claude Code

Transform research from linear search to multi-dimensional intelligence gathering using swarm intelligence patterns and advanced MCP capabilities. Each research session becomes a composed symphony of specialized agents working in parallel.

glassBead-tc/widescreen-research

Command Claude Code

Research Date: September 29, 2025 Orchestration Used: subliminal-channel-capacity-estimation.md Models Analyzed: Llama 3.3 70B, Mistral Large 2 (Aug 2025 releases).