← ClaudeAtlas

researching-codebaseslisted

Codebase research contract for the researcher agent — the evidence constraints on findings and the compressed research-report output format. Loaded when neutral research questions need factual, file-referenced answers.
bostonaholic/team · ★ 11 · AI & Automation · score 75
Install: claude install-skill bostonaholic/team
# Researching Codebases The researcher's procedure: answer a list of neutral research questions with compressed, objective, file-referenced findings. ## Investigation contract Answer every question in `questions.md`, scoped by its "Codebase context" section — and by `repos.md` when present (each repo's slug and absolute path; which repo each question targets). How you investigate is yours to choose. The output format below defines what complete findings look like; two constraints hold on the way there: - **Evidence over recall.** Every claim traces to code you read in this run — cite file:line. When a question concerns behavior, follow the execution path far enough to see the code that runs, not just a name that suggests it. - **Cross-repo contracts are findings.** In multi-repo mode, contracts that cross repo boundaries (shared types, API schemas) go in `## Constraints`, and conventions that differ between repos go in `## Patterns Observed`. ## Output format Report findings in this structure. Keep the entire report under 100 lines (under 150 in multi-repo mode — extra budget for the per-repo sections). The orchestrator writes the findings to `docs/plans/<id>/research.md`. In multi-repo mode, prefix every file reference with the repo slug, e.g. `frontend:src/App.tsx:42`. The slug is the `name` field from the matching entry in `repos.md`. ``` ## Tech Stack - Language, framework, key libraries with versions if visible (multi-repo: list per repo, e.g. "fron