@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
@kentcdodds: It's now 1.2 million lines of code... I recorded this ad a few weeks ago. Turns out that you need a lot of code to supp…
Kent C. Dodds notes his codebase has reached 1.2 million lines of code while quoting MEGA's take that humans—not tools—become the bottleneck in agent-driven development, pointing to async, remote agents as the architectural fix.
Rust off Rails: The opinionated web stack for the AI era
Rust off Rails introduces an opinionated, AI-first web stack that ships as Markdown conventions rather than code, instructing coding agents (like Claude Code) to generate full-stack Rust applications following a single blessed set of decisions. The project emphasizes that all code is written by AI, with humans only providing intent, specs, and interview answers.
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.
@tvytlx: The father of Rails, DHH, had an agent rewrite his company's chat software Campfire once each in Elixir, Go, and Rust. …
DHH had AI agents rewrite Basecamp's Campfire chat app in Elixir, Go, and Rust, showing nearly 150x performance gaps versus Ruby, and argued that AI agents writing code may shift language choice from developer ergonomics to runtime efficiency.
@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.