baldart 4.78.0 → 4.78.2

package/CHANGELOG.md

@@ -5,6 +5,28 @@ All notable changes to BALDART will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [4.78.2] - 2026-06-29
+
+**The "visual-verify every `ui-expert` intervention" hard rule was investigated and deliberately NOT built.** The ask sounded obvious — wire an invariant `UI_VISUAL_UNVERIFIED` forcing a visual check after every `ui-expert` implementation. Three adversarial reviewers (distinct lenses) refuted the diagnosis: (1) standalone skills already verify — `/ui-design` has its generator/evaluator Playwright loop, `/ds-new` + `/ds-edit` delegate to `ui-expert`'s own BLOCKING pre-work + `ds-gate` + the coherence report, `/ds-render` feeds `/e2e-review` Phase 4b; (2) the invariant would be redundant with the existing `DS_*` coherence codes + the `coverage-gap` finding, and would fire **constantly** on every Storybook-less project — the gate-with-no-exit structural false-positive the framework explicitly avoids — plus risk the assertion-fitting the verifier trio forbids; (3) the real driver the obvious diagnosis missed: **visual verification is deliberately deferred to where a ground-truth exists** (a composed route / a mockup) — an inert scaffolded primitive has nothing to be judged against, so verifying it *now* judges the void. The single useful residue (a deterministic `PostToolUse` hook would beat prose if one ever wanted to harden `/new`'s own prose-driven Phase 2.6) was logged, not built. So this release ships only the **zero-cost, non-regressive nudge**: a documentation pointer making explicit *where* route-level fidelity lives.
+
+**PATCH** — doc-only pointers; no new capability, no agent, no invariant, **no `baldart.config.yml` key**. The nudge is a pointer to the existing `/e2e-review` Phase 4, never a blocking obligation; skipped/irrelevant where no render surface exists.
+
+### Changed
+
+- **`/ds-render`** (`framework/.claude/skills/ds-render/SKILL.md`) — added a "Where route-level fidelity lives" note: the harness verifies a primitive in isolation (quality only, no ground-truth); the full fidelity check happens downstream via `/e2e-review` Phase 4 when the primitive is composed into a real route. A pointer, never a blocking obligation.
+- **`/ui-design`** (`framework/.claude/skills/ui-design/SKILL.md`) — added a "Downstream visual verification" note after Step H: the design is verified visually at the mockup stage (Step D evaluator); the fidelity of the *implemented* result is verified downstream via `/e2e-review` Phase 4 (auto-run by `/new`, or manual `/e2e-review CARD-ID` outside the pipeline).
+
+## [4.78.1] - 2026-06-29
+
+**`/ds-new` + `/ds-edit` now close the closed-loop (the `DS_MIRROR_STALE` nudge).** The mirror advisory — check #6 of the Post-Intervention Coherence Check, which nudges `/design-sync publish` when the in-repo registry has moved ahead of its Claude Design satellite — was cited by **every** UI-touching surface (`code-reviewer`, `ui-design`, `/design-review`, `/new` implement, `/prd` ui-design-phase, the `ds-drift` backstop) **except the two skills whose whole job is to create/modify a canonical element**: `/ds-new` and `/ds-edit`. So creating a primitive with `/ds-new` on a satellite-bound project never reminded the user to publish it — the one event that most directly makes the mirror stale was the one that skipped the nudge. This release adds the citation to both skills' step-8 coherence report.
+
+**PATCH** — doc-only completion of an existing advisory check; no new capability, no agent, **no `baldart.config.yml` key** (the check rides on the already-present `features.has_design_system` + the satellite-bound gate). The definition stays the single SSOT in `design-system-protocol.md` § Post-Intervention Coherence Check check #6 — the skills **cite, never redefine** it. Skipped when no satellite is bound (the vast majority of consumers → no-op); never blocks creation/edit.
+
+### Changed
+
+- **`/ds-new`** (`framework/.claude/skills/ds-new/SKILL.md`) — step 8 coherence report now surfaces `DS_MIRROR_STALE` (advisory, non-blocking) nudging `/design-sync publish` when a Claude Design satellite is bound (`.baldart/design-sync.json` has a `project_id`); added a `See Also` pointer to `/design-sync`.
+- **`/ds-edit`** (`framework/.claude/skills/ds-edit/SKILL.md`) — same step-8 mirror advisory, with the breaking-edit note that satellite drift is the same class as the migration; added the `/design-sync` `See Also` pointer.
+
 ## [4.78.0] - 2026-06-29
 
 **Route-independent per-card mockup fidelity + graphics fast-lane.** On a `/new` run a desktop "Edit product" page shipped as **1 column** against a **2-column** mockup, marked DONE: the fidelity gate never ran on a rendered page because the auth-gated route returned 500 under the empty-Supabase demo lane, the views were "soft-skipped", and the verdict came back `ACCEPTED (harness limit)` — **a skip masked as a pass**. Two adversarial passes found this is not one bug but two distinct holes hitting two cards, plus the fact that the fidelity check depended on rendering a live, data-bearing route at all. This release inverts the priority: per-card UI fidelity is verified **route-independently, before proceeding** — a code-structural diff first, an isolated render as confirmation — and an un-runnable required check now **blocks instead of silently passing**. Bets validated against 2026 best practice (structural TED + perceptual diff as complementary dimensions; MLLM-as-judge reliable at comparison, weak at absolute scoring → fidelity gates, quality stays advisory).

package/VERSION

@@ -1 +1 @@
-4.78.0
+4.78.2

package/framework/.claude/skills/ds-edit/SKILL.md

@@ -144,6 +144,13 @@ Each step is a delegation. Read the cited SSOT; do not paraphrase it.
 8. **Coherence report (never silent).** Emit the protocol's "Registry coherence
    check: N findings" block: spec updated (incl. HEAD), INDEX/policy reconciled,
    tokens reconciled, breaking change documented + migration noted.
+   **Mirror (advisory, non-blocking):** modifying a canonical component or token
+   moves the registry ahead of its Claude Design satellite — so when a satellite is
+   bound (`.baldart/design-sync.json` has a `project_id`), also surface
+   `DS_MIRROR_STALE` (check #6, `design-system-protocol.md` — cite, do not redefine)
+   nudging `/design-sync publish`. For a **breaking** edit the satellite drift is
+   the same class as the migration — note both. Skipped when no satellite is bound;
+   never blocks the edit.
 
 ## Token edit path
 
@@ -183,3 +190,5 @@ symmetric to how a `NEW (governed)` standard routes to `/ds-new`. `/prd` owns th
 - `framework/agents/component-manifest-schema.md` — the HEAD schema + the
   regeneration contract (preserve agentic, regenerate deterministic).
 - `framework/templates/breaking-change-checklist.md` — for breaking edits.
+- `framework/.claude/skills/design-sync/SKILL.md` — `/design-sync publish` mirrors
+  the edit UP to the Claude Design satellite (the `DS_MIRROR_STALE` nudge).

package/framework/.claude/skills/ds-new/SKILL.md

@@ -139,6 +139,12 @@ Each step is a delegation. Read the cited SSOT; do not paraphrase it.
 8. **Coherence report (never silent).** Emit the protocol's "Registry coherence
    check: N findings" block (per § Post-Intervention Coherence Check): new spec
    shipped, INDEX entry added, tokens reconciled, closed-set respected.
+   **Mirror (advisory, non-blocking):** creating a canonical component or token is
+   exactly the event that moves the registry ahead of its Claude Design satellite —
+   so when a satellite is bound (`.baldart/design-sync.json` has a `project_id`),
+   also surface `DS_MIRROR_STALE` (check #6, `design-system-protocol.md` — cite, do
+   not redefine) nudging `/design-sync publish`. Skipped when no satellite is bound;
+   never blocks creation.
 
 ---
 
@@ -196,4 +202,6 @@ across the two.
   the serializer fills (the standardized doc shape).
 - `framework/.claude/skills/design-system-init/SKILL.md` — the bulk twin; shares
   the same scripts (`extract-manifest`/`extract-one`/`serialize-spec`).
+- `framework/.claude/skills/design-sync/SKILL.md` — `/design-sync publish` mirrors
+  the new element UP to the Claude Design satellite (the `DS_MIRROR_STALE` nudge).
 - `framework/docs/COMPONENT-MANIFEST-LAYER.md` — the layer overview.

package/framework/.claude/skills/ds-render/SKILL.md

@@ -71,6 +71,14 @@ Baseline `medium`. Honor an inline `effort=<level>` override.
    mechanism is the `mockup_source.level: "harness-render"` marker (see
    `e2e-review/SKILL.md` Phase 2 cascade) which Phase 4 skips and Phase 4b takes.
 
+> **Where route-level fidelity lives (nudge, not a gate).** This harness verifies a
+> primitive **in isolation** (quality only — it has no mockup ground-truth). The full
+> visual-**fidelity** check happens **downstream**, when the primitive is composed into
+> a real route: that is `/e2e-review` Phase 4 (auto-run by `/new`, or invoke
+> `/e2e-review CARD-ID` manually if you implement outside `/new`). Verifying an inert
+> primitive against a mockup here would be premature — it has nothing to be judged
+> against yet. So this is a pointer, never a blocking obligation.
+
 ## Hard prohibitions
 - NEVER feed a harness PNG to a fidelity diff (Phase 4) — quality (4b/4c) only.
 - NEVER build a framework-native preview-route or an auto-provider-shim — Storybook

package/framework/.claude/skills/ui-design/SKILL.md

@@ -246,6 +246,14 @@ prevent**: catching a duplicate primitive at the mockup stage costs minutes,
 catching it after implementation costs a refactor. The weekly `ds-drift`
 routine is a safety net, not a substitute for this check.
 
+**Downstream visual verification (nudge, not a gate).** The chosen design is
+verified visually **at the mockup stage** here (Step D evaluator). The fidelity
+of the *implemented* result against this design is verified **downstream**, when
+the design lands in a live route: that is `/e2e-review` Phase 4 — auto-run by
+`/new`, or invoke `/e2e-review CARD-ID` manually if you implement this design
+outside the `/new` pipeline. This is where route-level fidelity lives; it is a
+pointer, never a blocking obligation on this skill.
+
 ---
 
 ## Design Principles (quick reference)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "baldart",
-  "version": "4.78.0",
+  "version": "4.78.2",
   "description": "Claude Agent Framework - Reusable framework for coordinating AI agents and humans in software projects",
   "bin": {
     "baldart": "./bin/baldart.js"