--- id: 2026-05-14-library-evaluation-policy prd: docs/work/prds/2026-05-14-library-evaluation-policy.prd.md title: Library evaluation policy — skill, traces, enforcement stack type: epic status: done features: [scripts, tooling, docs] created: 2026-05-14 --- ## Goal Implement a four-layer enforcement stack — Claude hook, skill, pre-commit hook, sandcastle reviewer prompt — that makes every new runtime dependency in a feature- or core-tier package produce a permanent **library trace** at `docs/library-decisions/-.md`. Rejection traces are first-class records. Codifies ADR-022. ## Why The repo's narrow third-party surface is uncodified. New dependencies enter via `pnpm add` with no checkpoint. Three signals exposed the gap: a near-miss adding a build-time-only library, post-hoc ADR records (002/014/017), and a silent EU-data-residency risk from US-only SaaS defaults. The enforcement stack mirrors the 5-gate conformance pattern — same vocabulary, same agent feedback loop. ## Stories - [ ] [01 — Trace schema module + docs/library-decisions/ foundation](01-trace-schema-foundation/_story.md) - [ ] [02 — Pre-commit check script](02-pre-commit-check-script/_story.md) - [ ] [03 — Claude PreToolUse / PostToolUse hooks](03-claude-hooks/_story.md) - [ ] [04 — evaluate-library skill](04-evaluate-library-skill/_story.md) - [ ] [05 — Human guide: docs/guides/adding-a-library.md](05-human-guide/_story.md) - [ ] [06 — Sandcastle reviewer prompt update](06-sandcastle-reviewer-prompt/_story.md) - [ ] [07 — Generator pre-shipped traces for optional cores](07-generator-pre-shipped-traces/_story.md) - [ ] [08 — Backfill traces for existing runtime deps](08-backfill-traces/_story.md) - [ ] [09 — CLAUDE.md Key Conventions bullet](09-claude-md-update/_story.md)