repo-health-auditlisted

# Repo Health Audit Run a read-only audit of repository structure, naming hygiene, reuse health, and long-term maintainability. Produce a prioritized report of organization problems with evidence and practical fix direction. Default posture: do not edit, move, rename, reformat, stage, or delete files unless the user explicitly asks for cleanup after the audit. ## Core Rules - Stay read-only during the audit. If the user asks for fixes too, audit first, then switch to normal implementation only after the target changes are clear. - Default to a full-repository audit when the user does not provide a specific scope. Inventory the repo's top-level structure, modules, and packages, then inspect the areas with the most naming drift, duplication, dead code, or boundary confusion. - Full-repo audits are breadth-first, then depth-limited. Inventory the repo, rank surfaces by risk, deep-inspect as many high-risk surfaces as the turn allows, and list the rest under **Surveyed But Not Deeply Inspected** with a pointer to run another pass on them. State the surface counts in the report header. Never present a shallow sweep as complete coverage. - Focus on organization, discoverability, naming, boundaries, dead code, duplication, reuse opportunities, and long-term maintainability. Do not report ordinary implementation bugs unless they are caused by structural confusion or repeated code. - Infer conventions from the repo before judging. Existing patterns, framework defaults, monorepo lay