review-implementation

# Review Implementation (internal engine) The findings engine the review/audit skills compose: it **produces findings and a decision table, and stops** — never refactors or edits code. It owns the **review axes** (Phase 1) and the **classification rubric** (Phase 2) that `review-change`, `audit-pr`, and `product-audit` reference instead of restating. ## When to use - Invoked by `review-change` (the user-facing review entry) as its engine; the audit skills reference its rubric. - Run directly only when you want the raw classified pass without the platform-adaptive orchestration `review-change` adds. ## Scope Default target is the **current change** (branch diff vs. the default branch); accept an explicit path/glob to widen or narrow it. State the scope at the top of the report so the reader knows what was and wasn't reviewed. ## Step 0 — Discover the project (always first) Per the agent guide's **Workflow conventions** + **documentation map**, then read what THIS skill needs: the architecture/layering rules, the testing philosophy, and any runtime/platform, security, money, i18n/SEO/a11y and bundle rules. Pull the project's specific risk axes from its guardrail skills where present (architecture-pattern, runtime/platform, domain-rules). The axis list below is the default; the project's docs refine it. ## Context budget (hard rule) The scope is the diff. Beyond it, read **at most 10 non-diff files in full** for surrounding context (callers, contracts, tests); targe...