@alphabatcher: 540,000 lines of Rails is a brutal way to learn the agent era Garry's List shipped with: > 262,000 lines of app code > …
Summary
A critique of large Rails codebases in the AI agent era, proposing a shift to skill-based development with agents, markdown skills, and TypeScript for deterministic I/O.
View Cached Full Text
Cached at: 06/02/26, 07:38 PM
540,000 lines of Rails is a brutal way to learn the agent era
Garry’s List shipped with:
262,000 lines of app code 276,000 lines of tests 127 background jobs 33 cron jobs a 1,778-line claim verifier
Then GStack hit 105k GitHub stars
Do not copy the Rails pattern
- Finish the task with an agent
- Say
skillify it - Save the markdown skill
- Keep TypeScript only for deterministic I/O
- Add a unit test for the code
- Add an LLM eval for the skill
- Add an integration test across both
- Add a resolver so the agent loads the skill next time
A Rails feature serves one app
A skill pack can run against the next hackathon, repo, customer inbox, research folder, or QA run
Audit your repo this week
Cut code that only exists to:
re-check model output retry the same model call validate what the model already has context for schedule work because the agent has no reusable procedure preserve a one-off prompt in chat history
Keep the code that touches files, APIs, auth, billing, devices, databases
Move the judgment into markdown Test the markdown Reuse the skill
Similar Articles
I rebuilt a Claude Code–style coding agent from scratch — the whole agent loop is 6 lines. 20 chapters, ~5k lines, no frameworks, runs on local models too
A developer shares a 20-chapter tutorial rebuilding a Claude Code–style coding agent from scratch, showing the entire agent loop in ~6 lines, with support for local models and multiple LLM APIs.
@mitchellh: My heuristic is that any diff an agent generates over ~1500 lines is too big and is indicative that the problem needs t…
Mitchell Hashimoto shares a heuristic for using AI agents: any diff over 1500 lines indicates a need for decomposition, and outlines a pattern for iterative development with agent-generated code.
@sharbel: Someone built a free collection of production-grade engineering skills that teaches your AI coding agent to work exactl…
Agent Skills is a free, open-source collection of production-grade engineering skills that teaches AI coding agents to follow senior engineer workflows, including spec-first, atomic builds, and quality gates, compatible with Claude Code, Codex, Cursor, and Gemini CLI.
@jasonzhou1993: I gave my coding agent a map across 3 of my repos: - Reduce ~50% token - a grep hook so every grep call has much richer…
Jason Zhou shares a technique to give coding agents a map across repos, reducing token usage by ~50% and enabling richer grep and call chain tracing. He also releases a Claude Code plugin marketplace called AI Builder Club Skills for setting up codebase harness and compounding agent loops.
@kentcdodds: I used Fable and Grok 4.5 (in two separate chats) to go find all the hilariously bad AI-generated code in my codebase a…
The author recounts using Fable and Grok 4.5 to identify and remove poor AI-generated code from their codebase.