Stop AI coding agents from guessing. MCP server + Claude Code plugin that enforces intent alignment BEFORE coding: PRD → intent-confidence gate → Mermaid contracts (state machines / sequence diagrams / decision tables) → mechanical lint with zero CRITICAL → then code. Human-in-the-loop, file-persisted, zero-config.
DeepSeek Harness plugin: GitLab and GitHub API tokens stay out of the model context — encrypted at rest (AES-256-GCM), tools on demand, web settings panel.
A DeepSeek Harness (DSH) dynamic plugin that adds an ✨ optimize-prompt button to the chat composer — context-aware LLM rewriting with model fallback and visible errors.
Layered memory plugin for DeepSeek Harness (dsh) — auto-distills conversations into L0–L3 memories (raw dialogue → atomic facts → scenes → persona) and injects relevant context before every model step. Pipeline ported from MemoryCore (TencentDB-Agent-Memory).
DeepSeek Harness native plugin: Settings UI for the Roblox Studio MCP bridge - list connected Studio instances, pick the active one, and expose the selection to agents as runtime context.