research-reuselisted

Research whether **$ARGUMENTS** already exists before anything is written. Do not propose an implementation — report what can be reused. ## Search order Work through these in order and stop early only when you have a strong match. 1. **This codebase first.** Grep and Glob for existing functions, utilities, base classes, and patterns that already solve part of the problem. A helper that is 60% right and already tested beats a fresh one. 2. **GitHub code search.** `gh search repos` for projects solving the whole problem, then `gh search code` for concrete implementations of the tricky part. Note stars, last commit, and licence. 3. **Package registries.** npm / PyPI / crates.io for a maintained library. Prefer battle-tested packages over hand-rolled utilities. 4. **Vendor documentation.** Confirm API behaviour and version-specific details against the primary docs (or Context7) before assuming an interface. 5. **Broader web search.** Only when the steps above came up short. ## Report - **Reuse from this repo** — file paths and what each already does. - **Candidate libraries** — name, what it covers, maintenance signal, licence, and the gap you would still have to fill. - **Adaptable implementations** — repos that solve 80%+ of the problem and could be ported or wrapped. - **Recommendation** — one option, with the reason. If net-new code really is the answer, say so explicitly and state what you ruled out. Name file paths and URLs concretely. A recommen