kostyk348/sint-marketplace-mcp
MCP server Claude CodeCodexCursor
MCP server "sint-marketplace-mcp" as configured in kostyk348/sint-marketplace-mcp. Runs locally from the sint-marketplace-mcp Python package.
kostyk348/sint-marketplace-mcp
MCP server Claude CodeCodexCursor
MCP server "sint-marketplace-mcp" as configured in kostyk348/sint-marketplace-mcp. Runs locally from the sint-marketplace-mcp Python package.
MCP server Claude CodeCodexCursor
MCP server "sint-resonance-mcp" as configured in kostyk348/sint-resonance-mcp. Runs locally from the sint-resonance-mcp Python package.
MCP server Claude CodeCodexCursor
MCP server "sint-epistemic-mcp" as configured in kostyk348/sint-epistemic-mcp. Runs locally from the sint-epistemic-mcp Python package.
Agent
Independent verification agent. Checks outputs from other agents for register violations, missing sources, logical errors, and drift. Use when verifying facts, reviewing code quality, or auditing conclusions.
Agent
Primary agent. Always runs first. Reads memory, classifies task, delegates to specialists. Session lifecycle management. Use as defaultagent.
Agent
Classifies user tasks by semantic register and domain, recommends which skills to load and which agent should handle. Use when starting a session or when task type is ambiguous.
Agent
Memory management agent. Reads/writes structured memory blocks, maintains hash-chain, manages session logs. Use when recording findings, updating project state, starting/ending sessions, or querying memory.
Command
Full dashboard view of memory system, projects, and agent status.
Command
Query memory system. Search blocks, show stats, check chain.
Command
End session. Write summary, update state, verify chain.
Command
Start session with memory context. Reads state, recent blocks, greets with summary.
Command
Verify last output or finding. Runs sint-critic checks on specified content.
Skill Claude CodeCodex
Use when working with agent, multi-agent, pipeline, orchestration, tool use, memory, context. Multi-agent systems: pipelines, orchestration, verification, semantic integrity.
Skill Claude CodeCodex
Use when working with DSO, MPTC, DataTrace, SINT, jitter, arena allocator, tick-aware, ensemble stability, non-minimum-phase, trust score, hash-chain, semantic register, taint tracking. Project-specific patterns from DSO, MPTC, DataTrace, SINT-UA, DSO Control.
Skill Claude CodeCodex
Use for reading/writing structured memory blocks, hash-chain audit, session logs. Replaces flat STATE.MD with typed JSON blocks and provenance chain. Load when starting/ending sessions, recording decisions, or verifying facts.
Skill Claude CodeCodex
Use when needing to align agent behavior with Konstantin's decision style, preferences, and anti-preferences. Owner model for calibrating tone, tradeoff decisions, and avoiding known dead ends. Read-only — agent never modifies.
Skill Claude CodeCodex
Use for session management, project status tracking, continuation prompts. Session working memory: current focus, active projects, pending decisions, verified patterns, session log. Read at session start.
Skill Claude CodeCodex
Use when creating a new artifact or checking if something already exists. Artifact registry of all created scripts, benchmarks, prototypes, data, templates. Cross-reference with dso.md for verified patterns.
MCP server Claude CodeCodexCursor +2
MCP server "sint-memory-mcp" as configured in kostyk348/sint-ua-v2.1. Runs locally from the sint-memory-mcp Python package.