Write the spec tight in Kiro, and the agents build it end to end
The secret is all in the spec. They pressure-test a structured one in Kiro for hours or days, then hand it to Kiro CLI and Claude Code in tmux. Usually the agents finish without stopping.
Done withKiroClaude CodeSpotted· by HN user wenc· Oct 15, 2026
Result A one-line TDD rule lifted every test's quality
“With a solid Kiro spec and task list, agents usually implement everything end-to-end without stopping -- I haven’t found a need for Ralph loops.”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
Uses Kiro IDE as a spec generator: it writes specs in structured formats (EARS, INCOSE), checks them for consistency, then generates a design document, a task list and property-based tests. They spend hours to days pressure-testing the spec, add a “do red/green TDD” instruction, then hand it to several headless CLI agents in tmux, including Kiro CLI and Claude Code.
How it went
The results have been very good. With a solid spec and task list, the agents usually implement everything end to end without stopping, and the one-line TDD instruction improved the quality of all their tests.
Try it yourself with Kiro
Before writing any code, turn this feature request into a spec: [request]. Write the requirements in EARS format, check them for contradictions and gaps and ask me about each one, then produce a design document and a numbered task list where every task has acceptance tests. Use red/green TDD when implementing.
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.