Write the spec, hand it over, get a working app for $10-20 in tokens
Detailed Markdown specs go to OpenClaw, which spawns and tests Claude Code instances for hours until the app works as described. "Is the code any good? Probably not." They check before trusting it.
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
They write massive markdown files describing every feature they want, use a standard AI chatbot to check their work and add details, then upload the finished spec to OpenClaw and tell it to build it. OpenClaw sometimes works for 2+ hours, spawning Claude Code instances, testing the code, and using browser automation to check that a web app works as described.
How it went
For roughly $10-20 in tokens, it produces a functional application with everything they asked for. They’re candid about the trade-off (“Is the code any good? Probably not.”) and review the libraries it imports before running the code on any machine with access to anything they care about.
Try it yourself with OpenClaw
Write a detailed markdown spec describing every feature you want in your application, refine it with a chatbot's help, then hand the finished spec to an agent that can spawn and supervise a coding agent. Let it work unattended through implementation, testing, and browser-based verification, and review the finished code yourself before trusting it with sensitive data.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.
Markdown files should just open, so they asked Claude Code for a viewer. It opens instantly: faster, they say, than any other macOS app, and faster than Bitwarden's Chrome extension shows its fill menu.
Migrating a password reset flow, Claude Code and Opus produced code on par with a mid level developer. It needed close supervision throughout, and cost roughly 2 months of Pro subscription for about half a day's work.
A URL shortener side project ran on AWS. Claude Code wrote the GitHub Actions workflows for the move and fixed each failure as it came up. The writer reports zero downtime.
A 7-app monorepo needed an 8 GB memory setting and 25 seconds to typecheck. Claude Code made the changes for the move to oxlint, oxfmt and tsgo, and the team validated each step.
Turning plan files into Claude Code workflows took 5-6 hours each. A script that converts them deterministically, and flags what can move out of the LLM, cut that to 20-30 minutes at about 20% of the tokens.
An inherited app on Azure, an error, and a hunt that could easily take 1-2 days by hand. With CLI access to Azure and the repo, Claude Code ran the config and network checks and found the root cause in about 45 minutes.