jszmajda

jszmajda / lid

Public

Linked-Intent Development - a SDD methodology for agentic coding

12
0
100% credibility
Found Apr 12, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
AI Summary

A plugin collection for Claude Code that enforces a structured workflow of design documents before coding to maintain intent alignment throughout development.

How It Works

1
🔍 Discover LID

You hear about LID while using your AI coding helper, a smart way to ensure it builds exactly what you envision without misunderstandings.

2
📥 Add the Plugins

You easily add the special plugins to your AI coding space with simple instructions.

3
✨ Set Up Your Project

Run the setup and see your project organize itself with folders ready for your ideas and designs.

4
Choose Your Path
🌱
New Project

Follow guided steps to sketch high-level ideas, detailed plans, clear requirements, and a build roadmap.

🏗️
Existing Project

Map out what's already there by exploring files and creating designs that match the current reality.

5
✅ Review Designs

Carefully check and approve each design layer, filling any gaps in your vision.

6
🔗 Build with Links

Watch as code and tests get created perfectly tied to your approved designs, feeling confident it's spot on.

🎉 Perfect Alignment

Your project stays clear, coherent, and easy to update forever, with designs always leading the way.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is lid?

LID, or Linked-Intent Development, is a lightweight SDD methodology and plugin set for Claude Code, turning agentic coding into a traceable chain from high-level designs to code. It solves intent drift in AI-driven projects by making design docs the source of truth—update HLDs, LLDs, and EARS specs, then cascade changes to tests and code via simple slash commands like `/linked-intent-dev:lid-setup`. Developers get structured workflows for greenfield or brownfield projects, with automatic spec annotations in code for full traceability.

Why is it gaining traction?

Unlike BMAD or spec-kit, which focus on one-off changes, LID prioritizes long-term coherence: regenerate code from specs anytime, keeping docs always current across sessions. The hook is its simplicity—just two plugins relying on Claude's smarts, no complex orchestration—making it dead simple for maintaining large codebases without drift. Early adopters praise the "arrow of intent" for agentic coding, where specs win over buggy code fixes.

Who should use this?

Agentic coding teams at scale using Claude Code, especially those refactoring lid-driven cavity simulations or github lid angle sensor prototypes into maintainable systems. Backend leads on brownfield monoliths needing codebase mapping, or startups enforcing design reviews before implementation. Avoid if you're solo hacking quick scripts—discipline required.

Verdict

Worth a spin for Claude Code users tackling linked-intent development in messy projects, but at 12 stars and 1.0% credibility, it's raw: solid docs, no tests visible, early alpha vibes. Install the plugins and test on a side project before betting the farm.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.