4 workflows

runcastle

A single Claude Code agent that finds the least-tested modules in your repo, writes focused unit tests for them one module at a time, and verifies the suite stays green after every batch — stopping once it hits your coverage target.

runcastle

Reads a sources.md list of papers, fetches each one, and builds a structured literature review — per-source summary of question, method, finding, and limitation — then synthesizes the themes, disagreements, and open gaps across the whole set.

runcastle

Reads a links.md list of URLs, fetches each one inside the sandbox, and has a Claude Code agent write a ready-to-send newsletter digest — a tight 2–3 sentence summary of every link, why it matters to your readers, and the source link, all assembled into a single markdown issue.

runcastle

Fans out a searcher per sub-question to fetch and note public web sources, then an Opus synthesizer writes a fully cited report, then a Codex fact-checker adversarially verifies every claim against the notes and loops until the report holds up.