Over the past few days, I've been improving HEXZ, an upgrade layer for OpenCode focused on security workflows, design generation, project memory, and AI output quality.
This release isn't a major feature drop, but it improves several areas that affect day-to-day usage.
Table Of Contents
What's New
MiMo Code Support
One of the biggest additions in this update is support for MiMo Code. HEXZ can now integrate with MiMo Code workflows, making it easier to use the same upgrade layer across different coding environments without changing how you work.
"One workflow. Multiple coding assistants."
Better Design Generation
I've spent time refining how HEXZ handles design-related tasks. Previous versions could generate usable layouts, but results weren't always consistent. This update improves:
- UI structure generation & reasoning
- Component organization & visual consistency
- Layout planning
The result is that simple prompts can now produce more complete interfaces with less manual guidance.
Security and Code Quality
HEXZ includes built-in security and review workflows. This release improves internal systems related to code analysis and security scanning. The objective remains a structured flow:
Research → Plan → Build → Scan → Review
Instead of generating code and hoping for the best, HEXZ enforces a quality-first approach.
Reduced AI Slop
A core feature of HEXZ is reducing repetitive, generic "AI-style" output. This update improves the anti-slop system and response formatting, helping generated content stay technical and focused.
Installation Fixes
A number of users reported installation issues involving Puppeteer and dependency setup. This release includes fixes for:
Click here to see the installation fixes
Why I'm Building HEXZ
Most AI coding tools focus on generating code. HEXZ focuses on improving the workflow around code generation.
Instead of writing larger prompts, I'm experimenting with moving intelligence into:
- Project memory & Tool orchestration
- Security workflows & Design scaffolding
The result is often shorter prompts and more consistent output.
Project Status
HEXZ is still under active development.
Current priorities:
- Testing
- Bug hunting
- Performance improvements
- Workflow refinement
- Expanding ecosystem support
If you're interested in OpenCode, MiMo Code, AI coding workflows, or developer tooling, feedback is welcome.
check out the source here:
HexZoNetwork
/
opencode-hexz
simple plugin that will make your model smarter
HEXZ
OpenCode & MiMo Code Upgrade Layer
A plugin for OpenCode, MiMo Code, Claude Code, and OpenAI Codex — anti-slop enforcement, 769+ cybersecurity skills, design scaffolding, web search, OCR, screenshots, MCP, persistent memory, and PR automation
Important
Claude Code and Codex support is untested and experimental. OpenCode remains the primary target — contributions welcome.
Warning
Recommended for Linux. Windows support via install.bat is experimental — contributions welcome.
Contents
- Features
- Installation
- Usage
- Model Routing
- Cybersecurity Suite
- Build Workflow
- Anti-Slop Rules
- Configuration
- Development
- Uninstall
- Security
Features
Anti-Slop Engine
Banned filler words (delve, leverage, robust, etc.), forced technical writing, varied sentence structure
Cybersecurity Suite
769+ skills across 15 domains with MITRE ATT&CK, NIST CSF 2.0, and OWASP Top 10 mappings
Design Scaffold
HTML/CSS mockups across 150+ design systems and 109+ templates
Web Search
DuckDuckGo integration — called before writing code
Image OCR
Text extraction from screenshots, errors, diagrams via tesseract.js
Web
Discussion
I'm curious—how are you all handling "AI slop" in your current workflows? Are you relying on prompt engineering, or are you looking for tooling layers like HEXZ to handle the formatting?
Let me know your thoughts or any bugs you find in the comments!
Top comments (0)