Initial commit

docs/work/epics/library-evaluation-policy/_epic.md

@@ -0,0 +1,30 @@
+---
+id: library-evaluation-policy
+prd: docs/work/prds/library-evaluation-policy.prd.md
+title: Library evaluation policy — skill, traces, enforcement stack
+type: epic
+status: done
+features: [scripts, tooling, docs]
+created: 2026-05-14T00:00:00Z
+updated: 2026-05-14T19:21:52.308Z
+---
+
+## 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/<YYYY-MM-DD>-<package-name>.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
+
+- [x] [01 — Trace schema module + docs/library-decisions/ foundation](01-trace-schema-foundation/_story.md)
+- [x] [02 — Pre-commit check script](02-pre-commit-check-script/_story.md)
+- [x] [03 — Claude PreToolUse / PostToolUse hooks](03-claude-hooks/_story.md)
+- [x] [04 — evaluate-library skill](04-evaluate-library-skill/_story.md)
+- [x] [05 — Human guide: docs/guides/adding-a-library.md](05-human-guide/_story.md)
+- [x] [06 — Sandcastle reviewer prompt update](06-sandcastle-reviewer-prompt/_story.md)
+- [x] [07 — Generator pre-shipped traces for optional cores](07-generator-pre-shipped-traces/_story.md)
+- [x] [08 — Backfill traces for existing runtime deps](08-backfill-traces/_story.md)
+- [x] [09 — CLAUDE.md Key Conventions bullet](09-claude-md-update/_story.md)