Skip to content

codelittinc/ai-native-development

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AI-native development

Guides and best practices for building software with LLMs, from the team at Codelitt.

These aren't theoretical. They come from shipping production software where Claude Code, codemode-x, and other LLM tools do a significant share of the implementation work. When something wastes tokens, breaks the feedback loop, or confuses the model, we write it down.

Guides

Guide What it covers
AI-native architecture 9 principles for structuring codebases so LLMs can work in them effectively. Contracts, error handling, idempotency, file structure, and more.
Claude Code workflows Practical setup and habits: planning mode, context-mode plugin, /documents/ folder, CLAUDE.md wiring, subagents, task tracking, and workflow orchestration rules.
The AI quality paradox Why AI-assisted development needs more QA, not less. The math behind rework spirals, the speed limit on generation velocity, and what to do about it. Based on Mennillo 2026.

Skills

Claude Code skills you can install as plugins or copy individually.

Install as plugins (recommended)

First add the marketplace. Inside Claude Code:

/plugin marketplace add codelittinc/ai-native-development

Or from the CLI:

claude plugin marketplace add codelittinc/ai-native-development

Then install the plugins you want:

claude plugin install qa-check@ai-native-development
claude plugin install supply-chain-check@ai-native-development

Installed plugins receive updates when new versions are published.

Or copy individually

Copy a skill folder from plugins/<name>/skills/<name>/ to ~/.claude/skills/ to use it without the plugin system.

Skill Command What it does
qa-check /qa-check Reviews code changes for rework risk, weakened or missing tests, dependency provenance, missing specs, AI slop, and validation gaps. Complements the built-in /code-review, which hunts correctness bugs. Based on the AI Quality Paradox research.
supply-chain-check /supply-chain-check Single-command supply chain security audit. Queries live advisory sources (npm audit, OSV.dev, GitHub Advisory Database) and scans for dangerous version ranges, lock file issues, typosquatting, slopsquatting, and local IOC artifacts.

Related projects

  • codemode-x -- MCP plugin that compresses N APIs, databases, and doc sets into 2 tools (search + execute) for Claude Code

Contributing

Open an issue or PR. We're especially interested in:

  • Patterns you've found that make LLM-assisted development faster or more reliable
  • Anti-patterns that waste tokens or break feedback loops
  • Real examples from production codebases (anonymized if needed)

License

MIT

About

Best practices and guides for building software with LLMs

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages