README Clew 2: Built with AdaL. Labeled by Jev. Judged by Code. Explained by Haiku.
Description and use
Jev labels the line. Code makes the call. TL;DR: README Clew 2 checks whether a public GitHub...
*Jev labels the line. Code makes the call.*
> **TL;DR:** README Clew 2 checks whether a public GitHub README matches its code, for JavaScript and TypeScript repos. A small decision model called Jev labels what kind of claim each README line is, five fixed code checks decide whether it's true, and [Claude Haiku](https://docs.claude.com/en/docs/about-claude/models/overview) writes the summary. I built it in five days with [AdaL](https://adalagent.ai), SylphAI's coding agent, for AdaL's "What Woul
Problem
Jev labels the line. Code makes the call. TL;DR: README Clew 2 checks whether a public GitHub...
*Jev labels the line. Code makes the call.*
> **TL;DR:** README Clew 2 checks whether a public GitHub README matches its code, for JavaScript and TypeScript repos. A small decision model called Jev labels what kind of claim each README line is, five fixed code checks decide whether it's true, and [Claude Haiku](https://docs.claude.com/en/docs/about-claude/models/overview) writes the summary. I built it in five days with [AdaL](https://adalagent.ai), SylphAI's coding agent, for AdaL's "What Woul
Outcome
Jev labels the line. Code makes the call. TL;DR: README Clew 2 checks whether a public GitHub...
*Jev labels the line. Code makes the call.*
> **TL;DR:** README Clew 2 checks whether a public GitHub README matches its code, for JavaScript and TypeScript repos. A small decision model called Jev labels what kind of claim each README line is, five fixed code checks decide whether it's true, and [Claude Haiku](https://docs.claude.com/en/docs/about-claude/models/overview) writes the summary. I built it in five days with [AdaL](https://adalagent.ai), SylphAI's coding agent, for AdaL's "What Woul
Evidence
README Clew 2: Built with AdaL. Labeled by Jev. Judged by Code. Explained by Haiku.
- Record date: 2026-11-02T14:28:48.005Z