@vegastack/skills 0.4.0 → 0.6.0

package/skill/architect/references/web.md

@@ -0,0 +1,152 @@
+# Web — frontend, design system, backend/API taste
+
+## Project layout
+
+- Top-level `server/` (or `packages/*` server code) holds DB, services, integrations — it
+  is sacred: never imported from client code, enforced with `server-only` + a boundary
+  check. The app router lives in `src/app/`; features are self-contained modules under
+  `src/features/<domain>/` (components/hooks per feature); shared pieces in
+  `src/{components,hooks,lib,store,messages}/`. Pages stay thin — they compose features.
+- The house convention scopes agent instructions per directory (a short CLAUDE.md/AGENTS.md
+  at each boundary-bearing directory) — follow it where a project already does this.
+
+## Frontend architecture
+
+- Server state → RSC + TanStack Query; URL state → nuqs; ephemeral UI state → Zustand.
+  Remote/tenant data is never persisted client-side (IndexedDB/local-first was evaluated and
+  rejected for multi-tenant SaaS on governance grounds — a confirmed single-tenant/offline
+  product is the only exception, and that's a decision to ask for, not assume).
+- Next config: `output: 'standalone'`, `cacheComponents: true` (PPR flags no longer exist).
+  Query key factories live in non-`'use client'` `.keys.ts` modules so RSC pages can prefetch.
+- Server Components by default; `'use client'` only at the lowest leaf that needs it.
+  `/server` (or `packages/*` server code) is never imported from client code — `server-only`
+  plus a boundary check, not convention.
+- Request interception: on OpenNext/Cloudflare, `proxy.ts`/Node middleware does NOT work
+  as of 2026-08 (open adapter issues — see infra.md); use what the adapter actually
+  supports and re-check its docs per feature. Either way interception is never the auth
+  boundary (see security.md).
+- Internal navigation uses `next/link`; bare `<a>` only for true external links/downloads.
+- Never TypeScript `any` — `unknown` and narrow.
+- Dependencies: prefer the native/browser API when it covers the need
+  (`Intl.RelativeTimeFormat` over date-fns); self-implement simple behavior (a tween, a diff
+  view) by composing design-system primitives before adding a library; any non-trivial new
+  dependency needs a stated justification and approval. **Why:** self-contained code has no
+  supply-chain, licensing, or upgrade surface, and MK rejects "library because library".
+
+## Design system (consuming `@vegastack/design` / `@vegastack/ui`)
+
+- First-time setup in a fresh project (npm install, Tailwind wiring, provider, registry
+  auth) is a separate, already-built skill — `vegastack-consume` — use it; don't
+  re-derive the wiring here.
+- Consume through the package barrel, never deep imports; never edit shipped component files.
+  A missing component or variant is an upstream request MK decides — the recommended
+  interim pattern is a local presentational composition in the app (inferred — confirm on
+  first use); don't fork the system.
+- Semantic tokens only: no inline `style={}`, no arbitrary values (`bg-[#123]`, `h-[13px]`),
+  no raw palette classes (`bg-neutral-900`), not even for opacity. Dynamic values go through
+  CSS custom properties.
+- Visual language: borders-only cards, flat surfaces (shadows only for true overlays); accent
+  color rationed to the primary action and real selected/active state — never hover, roughly
+  ≤10 accent elements a page. Focus stays visible always (WCAG 2.2 AA floor) — the house
+  mechanism is a darker border or native outline, never a `ring-*` utility. Control heights
+  on the 28/32/40 scale = `h-7`/`h-8`/`h-10` (no off-scale `h-9`); radius: `rounded-md`
+  controls, `rounded-sm` menu items, `rounded-lg` containers, `rounded-full` pills — never
+  `rounded-xl` on cards/dialogs. Touch-target minimum is genuinely unresolved (24px WCAG AA
+  vs 44px mobile-HIG both appear in the record) — ask MK when it matters.
+- Typography: product code caps at `font-semibold` and uses it sparingly (inside the design
+  system package itself the cap is `font-medium`); headings `font-lora`; numbers, versions,
+  costs, and card digits always `font-mono`; uppercase only in mono at ≤14px. Fonts are
+  self-hosted via `next/font` — never a Google Fonts CDN request.
+- Icons: Lucide only. Toasts: sonner, never native/OS prompts. 4px spacing scale.
+- Motion: subtle and minimal — no button hover/press animations, no `transition-all`; motion
+  is for state feedback (success/error) and structural changes. `prefers-reduced-motion`
+  disables animation entirely (instant, not softened).
+- No decorative filler: no gratuitous badges, eyebrow text, or "3 of 3" counters — MK cuts
+  these on sight as AI-generated design tells.
+- Light AND dark theme on every shipped surface (internal-only tools may opt out, stated
+  up front).
+
+## UI completeness bar (every real surface, before it's "done")
+
+- Full state matrix: loading skeleton shaped like the real content · empty state with
+  guidance · error routed to the specific failure (401/403, 404, 410, 429, generic — never
+  swallowed into `{}`) · success feedback. Optimistic updates where a mutation changes
+  visible state; the UI reflects backend mutations without a manual refresh.
+- Forms: Enter submits; spinner replaces the button icon (not beside it); first field
+  auto-focused; all fields disabled while the primary action runs; state resets on error or
+  navigation.
+- Responsive: no horizontal scroll at any width; computed layout math, never hardcoded pixel
+  offsets; truncation driven by available space, not character counts; iOS inputs must not
+  zoom on focus; the mobile keyboard must never occlude the active input.
+- Systemic fixes: a defect found in one component (scroll leaking through an overlay, missing
+  cursor, wrong token) is fixed across the whole family in one sweep, with evidence.
+- Perceived speed is the named pattern "instant shell": the layout shell renders
+  immediately (RSC + `cacheComponents`), every data region streams in behind a skeleton
+  shaped like its content — never a blank page or a full-page spinner.
+- Long lists (>~50 rows) virtualize with `@tanstack/react-virtual` (the approved package —
+  still state the justification when adding it).
+- Cloning/rebranding a reference site: strip every trace of the source tool's provenance
+  (class names, external asset domains, meta) so the result is fully self-contained, and
+  verify parity by clicking through as a real user — screenshot diffing alone doesn't count.
+
+## SEO and metadata (every public-facing app)
+
+- Every route exports `metadata`/`generateMetadata` — not just the root layout. Public
+  apps ship `sitemap.ts` and `robots.ts`; `llms.txt` is generated at build time, never
+  hand-maintained. OG images follow the house convention (generated, mono for
+  names/numbers). i18n uses next-intl `localePrefix: 'as-needed'` (stack.md) so default-
+  locale URLs stay clean. **Why:** MK has demanded "100% SEO" coverage on shipped sites
+  twice — treat it as a completeness bar, not an enhancement.
+
+## Testing (web/backend — test where it pays off)
+
+- Unit-test services and pure logic (Vitest); component/a11y tests run in Vitest browser
+  mode with the Playwright provider (real Chromium — jsdom's ARIA/layout gaps produce
+  false a11y results and are not trusted).
+- E2E is a walking skeleton: one real happy path (boot → auth → core mutation → verify)
+  plus targeted adversarial invariants — not a blanket suite. DB-gated tests are authored
+  even when execution is blocked, and gated behind an env flag (`RUN_DB_TESTS=1` pattern);
+  E2E doubles implement real ports, never a parallel mock pathway.
+- Every confirmed bug gets a regression test; no coverage-percentage targets — "100%"
+  means audit completeness, never a coverage metric. VRT/demo content is deterministic
+  (no `Date.now()`/`Math.random()`).
+
+## Backend / API design
+
+- Contract-first: zod schemas are the single source → OpenAPI 3.1 under `/api/v1`, camelCase,
+  cursor pagination on every list, RFC 9457 problem-details errors with a stable error-code
+  catalog. One contract serves web, Flutter, MCP, and public consumers.
+- Every route: auth before parse, through the shared route-handler wrapper — no route-local
+  zod, no raw `request.json()`. Sanitize responses: secrets and credential references never
+  leave the server. Enforce with a CI ratchet (unwrapped routes fail the build), not review.
+- Return what the view renders, not everything — no mega-responses. Select columns explicitly.
+- Body limits stream: count bytes as they arrive and abort at the limit; never buffer the
+  whole body first.
+- Webhooks over polling; the database is the source of truth. Once provider state lands in
+  Postgres via webhook, don't re-poll the provider — and don't build intermediary "waiting"
+  pages; redirect on success and let the rest arrive in the background.
+- Money paths (Stripe): isolated intake (own worker or route), idempotency keys on every
+  mutation, event dedupe, append-only ledgers as the single cost source of truth, audit
+  events written in the same transaction as the business change. Pricing/quoting math is
+  deterministic code with server-enforced invariants — AI drafts and judges; deterministic
+  code calculates and enforces (a proven client-project pattern; treat as the strong
+  default for money paths).
+- Centralize the boring: one ID helper (never raw `crypto.randomUUID` scattered), one logger
+  (never `console.log`; request/org context auto-injected; never log secrets or PII beyond
+  user IDs), one typed fail-hard zod env parser validated at startup — no
+  `DISABLE_AUTH`-style escape hatches, no plaintext fallbacks.
+- Dead endpoints get deleted, not deprecated-and-kept. (Exception: a versioned `/api/v1`
+  contract consumed by a shipped mobile app outlives web deploy cycles — app-store install
+  lag means mobile clients keep the old contract alive; see mobile.md.)
+- Outbound webhooks to customers (when a product offers them): a defined event catalog,
+  Standard Webhooks-style signing with rotatable secrets, delivery via the transactional
+  outbox → queue with retries/backoff, auto-disable an endpoint after N consecutive
+  failures, and a replay surface. Never fire webhooks inline from request handlers.
+- Platform-native mentions over plain text: when the data allows it, resolve and mention
+  the real entity (Slack user @mentions, Notion Person fields) instead of rendering names
+  as text — the recurring "don't just fix, improve" integration principle.
+- Wizard/checkout flow-state persistence (Zustand + sessionStorage vs server-side draft)
+  is not yet a settled house rule — ask MK when building one.
+- Rate-limited responses return 429 with a `Retry-After` header.
+- Timestamps stored UTC (`timestamptz`), rendered in the user's timezone; durations as
+  integer milliseconds; money in integer minor units.

package/skill/architect/refresh/REFRESH.md

@@ -0,0 +1,29 @@
+# Freshness contract — architect
+
+Most of this skill is durable taste and recorded decisions; it does not go stale on its
+own. Exactly one file decays with the platform landscape: `references/pinned-facts.md`
+(plus the version claims embedded in `references/stack.md` and `references/mobile.md`).
+
+## Mechanism
+
+1. **Weekly scheduled agent (primary).** A scheduled Claude Code/Codex job re-verifies
+   each pinned fact against its stated source URL and opens ONE pull request quoting
+   evidence for anything that changed (fact text, version, date, source). The diffing
+   judgment lives in the agent run, not in maintained scripts. The PR is human-reviewed —
+   never auto-merged.
+2. **Refresh-on-use (safety net, written into SKILL.md).** When a recommendation leans on
+   a pinned fact older than 60 days, the consuming agent re-verifies that one fact first
+   and says so. Never bulk-refresh in-session.
+3. **Registry baseline (`sources.json`).** The repo-shared refresh runner
+   (`tooling/refresh/refresh-evidence.mjs`) keeps checksum baselines for the critical
+   source pages so CI can detect upstream drift deterministically between weekly runs.
+
+## Rules
+
+- Critical sources (Hyperdrive supported versions, Better Auth docs, eve/Workflow SDK
+  deploy constraints) get `critical: true` — drift there warrants a prompt PR, not a
+  batch.
+- Every edited fact keeps the pattern: fact → why it changes a decision → source URL →
+  verified date. The file carries one blanket verified-date for facts checked together;
+  a fact re-verified alone gets its own inline date, superseding the blanket one.
+- A fact that stops being decision-changing is deleted, not kept for completeness.

package/skill/architect/refresh/sources.json

@@ -0,0 +1,244 @@
+{
+  "schemaVersion": 1,
+  "policy": {
+    "criticalTopics": [
+      "hyperdrive-postgres",
+      "better-auth",
+      "eve-deploy"
+    ],
+    "defaultChecksumScope": "html-text-v1",
+    "offline": "Use cached metadata only; fail closed when a critical entry is missing or older than thresholdDays.",
+    "drift": "Any drift requires reading the changed page and a human-reviewed PR updating references/pinned-facts.md (and version claims in references/stack.md / references/mobile.md); never auto-apply.",
+    "copyright": "Store claim metadata, URLs, hashes, and concise excerpts only; never archive third-party documentation corpora.",
+    "cadence": "weekly scheduled-agent refresh; thresholdDays must be >= 14 (2x cadence) so a single missed run never breaches a threshold"
+  },
+  "sources": [
+    {
+      "id": "CF-HYPERDRIVE-VERSIONS",
+      "service": "Cloudflare Hyperdrive supported databases",
+      "kind": "official-docs",
+      "stability": "vendor-docs",
+      "thresholdDays": 14,
+      "critical": true,
+      "urls": {
+        "primary": "https://developers.cloudflare.com/hyperdrive/reference/supported-databases-and-features/"
+      },
+      "versionDetection": {
+        "type": "manual-review"
+      },
+      "topics": [
+        "hyperdrive-postgres"
+      ],
+      "affected": [
+        "references/pinned-facts.md",
+        "references/stack.md",
+        "references/data.md"
+      ],
+      "checksum": "fda2870b95deffce48dca7f3df3707325b1bc4a2d58a17708ee9220bfba5eba1",
+      "retrievedAt": "2026-08-12T14:33:11.062Z"
+    },
+    {
+      "id": "CF-R2-PRICING",
+      "service": "Cloudflare R2 pricing",
+      "kind": "official-docs",
+      "stability": "vendor-docs",
+      "thresholdDays": 30,
+      "critical": false,
+      "urls": {
+        "primary": "https://developers.cloudflare.com/r2/pricing/"
+      },
+      "versionDetection": {
+        "type": "manual-review"
+      },
+      "topics": [
+        "r2-economics"
+      ],
+      "affected": [
+        "references/pinned-facts.md",
+        "references/stack.md"
+      ],
+      "checksum": "bd5e8d26f7bbf2f92182ad4ac1a59ae9b1d90695120062adaf54c281bd88e81f",
+      "retrievedAt": "2026-08-12T14:33:11.062Z"
+    },
+    {
+      "id": "CF-WORKFLOWS-PRICING",
+      "service": "Cloudflare Workflows limits and pricing",
+      "kind": "official-docs",
+      "stability": "vendor-docs",
+      "thresholdDays": 30,
+      "critical": false,
+      "urls": {
+        "primary": "https://developers.cloudflare.com/workflows/reference/limits/"
+      },
+      "versionDetection": {
+        "type": "manual-review"
+      },
+      "topics": [
+        "workflows"
+      ],
+      "affected": [
+        "references/pinned-facts.md",
+        "references/ai-agents.md"
+      ],
+      "checksum": "64e10ca4ced4edc042d12a9a24f2e165ea71cb9481c30ac5f067f2f6c9218cda",
+      "retrievedAt": "2026-08-12T14:33:11.062Z"
+    },
+    {
+      "id": "BETTER-AUTH-DOCS",
+      "service": "Better Auth documentation",
+      "kind": "official-docs",
+      "stability": "vendor-docs",
+      "thresholdDays": 14,
+      "critical": true,
+      "urls": {
+        "primary": "https://better-auth.com/docs/plugins/organization"
+      },
+      "versionDetection": {
+        "type": "npm",
+        "package": "better-auth"
+      },
+      "topics": [
+        "better-auth"
+      ],
+      "affected": [
+        "references/pinned-facts.md",
+        "references/security.md",
+        "references/stack.md"
+      ],
+      "currentVersion": "1.6.27",
+      "versionCheckedAt": "2026-08-12T14:33:11.062Z",
+      "checksum": "30edf1b6658a473a00005153a3eafc07de5c3decd6b8f09fc6c32f3a21c4db1c",
+      "retrievedAt": "2026-08-12T14:33:11.062Z"
+    },
+    {
+      "id": "EVE-DOCS",
+      "service": "Vercel eve agent framework",
+      "kind": "official-docs",
+      "stability": "beta",
+      "thresholdDays": 14,
+      "critical": true,
+      "urls": {
+        "primary": "https://vercel.com/docs/eve"
+      },
+      "versionDetection": {
+        "type": "npm",
+        "package": "eve"
+      },
+      "topics": [
+        "eve-deploy"
+      ],
+      "affected": [
+        "references/pinned-facts.md",
+        "references/ai-agents.md",
+        "references/stack.md"
+      ],
+      "currentVersion": "0.33.2",
+      "versionCheckedAt": "2026-08-12T14:33:11.062Z",
+      "checksum": "a777f9da0cb3966a9c7cc06a3c12be34b2928800b370e966e8b6e0f5a5622915",
+      "retrievedAt": "2026-08-12T14:33:11.062Z"
+    },
+    {
+      "id": "WORKFLOW-SDK-POSTGRES",
+      "service": "Workflow SDK Postgres world deployment constraints",
+      "kind": "official-docs",
+      "stability": "vendor-docs",
+      "thresholdDays": 14,
+      "critical": true,
+      "urls": {
+        "primary": "https://workflow-sdk.dev/worlds/postgres"
+      },
+      "versionDetection": {
+        "type": "npm",
+        "package": "@workflow/world-postgres"
+      },
+      "topics": [
+        "eve-deploy"
+      ],
+      "affected": [
+        "references/pinned-facts.md",
+        "references/ai-agents.md"
+      ],
+      "currentVersion": "4.3.3",
+      "versionCheckedAt": "2026-08-12T14:33:11.062Z",
+      "checksum": "3eca56b5ec9668638d4e00b290c157383dfe8ceaaa334de13bb6244b32fa6839",
+      "retrievedAt": "2026-08-12T14:33:11.062Z"
+    },
+    {
+      "id": "NEXTJS-BLOG",
+      "service": "Next.js release blog",
+      "kind": "official-docs",
+      "stability": "vendor-docs",
+      "thresholdDays": 30,
+      "critical": false,
+      "urls": {
+        "primary": "https://nextjs.org/blog"
+      },
+      "versionDetection": {
+        "type": "npm",
+        "package": "next"
+      },
+      "topics": [
+        "nextjs"
+      ],
+      "affected": [
+        "references/pinned-facts.md",
+        "references/web.md",
+        "references/stack.md"
+      ],
+      "currentVersion": "16.3.0",
+      "versionCheckedAt": "2026-08-12T14:33:11.062Z",
+      "checksum": "9d5d2503e2e8aa7ed1c3f0cb972c78e64b2e3aae5f3ad264bb0a79bd179708f0",
+      "retrievedAt": "2026-08-12T14:33:11.062Z"
+    },
+    {
+      "id": "PG-BOSS-NPM",
+      "service": "pg-boss job queue",
+      "kind": "package-registry",
+      "stability": "stable",
+      "thresholdDays": 30,
+      "critical": false,
+      "urls": {
+        "primary": "https://registry.npmjs.org/pg-boss/latest"
+      },
+      "versionDetection": {
+        "type": "npm",
+        "package": "pg-boss"
+      },
+      "topics": [
+        "jobs"
+      ],
+      "affected": [
+        "references/pinned-facts.md",
+        "references/ai-agents.md"
+      ],
+      "currentVersion": "12.27.0",
+      "versionCheckedAt": "2026-08-12T14:33:11.062Z",
+      "checksumScope": "http-body",
+      "checksum": "abf4bc2795e2df03181a21dfd29c7b9234c933a9dcafa72b4583d590cad609da",
+      "retrievedAt": "2026-08-12T14:33:41.513Z"
+    },
+    {
+      "id": "FLUTTER-RELEASES",
+      "service": "Flutter release notes",
+      "kind": "official-docs",
+      "stability": "vendor-docs",
+      "thresholdDays": 30,
+      "critical": false,
+      "urls": {
+        "primary": "https://docs.flutter.dev/release/release-notes"
+      },
+      "versionDetection": {
+        "type": "manual-review"
+      },
+      "topics": [
+        "flutter"
+      ],
+      "affected": [
+        "references/pinned-facts.md",
+        "references/mobile.md"
+      ],
+      "checksum": "94f9df6f67615ee05d826995f9709309c5453d0d8e4be11232ca5d463929ed2b",
+      "retrievedAt": "2026-08-12T14:33:11.062Z"
+    }
+  ]
+}

package/skill/skill-maintainer/references/release-ops.md

@@ -4,26 +4,22 @@ Condensed operational playbook. The authoritative policies live at the repo root
 
 ## Semver for skill content
 
-Consumers depend on rule IDs and rule strength, not an API surface.
+Content is advisory prose and decision tables — no rule IDs, no machine-extracted rule format.
 
 | Bump | Content change |
 |---|---|
-| MAJOR | Removing or renaming a rule ID (IDs are stable and permanent — never renumber or reuse). Changing a `MUST`/`MUST NOT` so it permits something previously forbidden. Removing or renaming a skill. |
-| MINOR | New rules or rule IDs. New references or reference sections. New skill. Loosening ceremony without weakening a `MUST`. Tightening a `SHOULD` to a `MUST`. |
-| PATCH | Factual refreshes: version pins, vendor mechanism names, URLs, registry checksums. Typos and non-normative wording. Test/fixture-only changes. |
+| MAJOR | Removing or renaming a skill. A breaking change to a per-project profile format (e.g. `.vegastack/arch.md`) that invalidates existing committed profiles. |
+| MINOR | New reference file or reference section. New or changed recorded decision (e.g. a new "use/not/why" row, a new red line). New skill. |
+| PATCH | Factual refreshes: pinned-fact updates, version pins, vendor mechanism names, URLs, registry checksums. Wording clarifications that don't change the recorded decision. Test/fixture-only changes. |
 
 Installer/CLI changes follow ordinary semver on the same package version; a release takes the highest bump either side requires.
 
-## Two version identities — never conflate
+## One version identity
 
-| Identity | Lives in | Governs |
-|---|---|---|
-| Package version | `packages/cli/package.json` (changesets) | npm releases of installer + content snapshot |
-| Foundation version | profile schema const, `profile-tool.mjs` default, `foundation-compatibility.json` | the profile/schema contract deployed `.vegastack/architecture` profiles validate against |
-
-- Bumping the **package** (even MAJOR) must never invalidate a deployed profile — profiles bind to the foundation version.
-- Bumping the **foundation** version is a content-contract event: it requires a compatibility entry describing how existing baselines are treated, and at minimum a MINOR package release.
-- Each identity has one source of truth; never introduce additional copies of either number.
+There is a single source of truth: the **package version** (`packages/cli/package.json`,
+changesets-managed) — the npm release identity for the installer and every bundled skill's
+content snapshot. No skill tracks a separate content-contract version, and no per-project
+profile carries a schema version to validate against.
 
 ## Release flow (tag-driven)
 
@@ -44,7 +40,7 @@ Contributors do not bump versions in PRs; releases are maintainer-driven.
 
 ## Rename a skill
 
-Derived from the stable-ID logic in content-versioning (skill names are consumer-facing identifiers like rule IDs):
+Skill names are consumer-facing identifiers — treat a rename as a stable-ID break:
 
 1. Rename the directory and the frontmatter `name` in the same commit — they must always stay equal.
 2. Update every wiring point in the same PR: the packaging allowlist in `packages/cli/scripts/sync-skill.mjs`, the root README skills table row, and any cross-skill or docs links.
@@ -60,4 +56,4 @@ Derived from the stable-ID logic in content-versioning (skill names are consumer
 
 ## Refresh branches
 
-Branches named `refresh/**` are reserved for the automated freshness loop and are CI-restricted to `skills/*/refresh/` and `skills/*/references/foundation-compatibility.json`. Human content changes go on normal branches. Never hand-edit checksums/versions/timestamps anywhere — CI re-fetches claimed baselines, so hand-edited values cannot merge.
+Branches named `refresh/**` are reserved for the automated freshness loop and are CI-restricted to `skills/*/refresh/`. Human content changes go on normal branches. Never hand-edit checksums/versions/timestamps anywhere — CI re-fetches claimed baselines, so hand-edited values cannot merge.

package/skill/skill-maintainer/refresh/REFRESH.md

@@ -10,13 +10,13 @@ Instructions for the scheduled refresh agent (and any human running a manual ref
 
 ## How to refresh
 
-The deterministic runner is repo-shared and hosted in arch-guardian for now. Run from the repo root:
+The deterministic runner is repo-shared, hosted at `tooling/refresh/`. Run from the repo root:
 
 1. **Deterministic pass first** (no LLM judgment):
-   `node skills/arch-guardian/scripts/refresh-evidence.mjs --registry skills/skill-maintainer/refresh/sources.json`
+   `node tooling/refresh/refresh-evidence.mjs --registry skills/skill-maintainer/refresh/sources.json`
    drift/stale/unavailable results are the work-list. Exit 1 with a critical entry means fail-closed: the run must not be silently skipped. All four sources here are critical.
 2. **Accept verified changes** in the same code path:
-   `node skills/arch-guardian/scripts/refresh-evidence.mjs --registry skills/skill-maintainer/refresh/sources.json --accept-baselines`
+   `node tooling/refresh/refresh-evidence.mjs --registry skills/skill-maintainer/refresh/sources.json --accept-baselines`
    This writes registry, cache, and drift report together — never hand-edit checksums, versions, or timestamps; they must always come from a run. Baselines are runner-seeded; when a new source is added or a verified change is accepted, this accept-baselines invocation is the only sanctioned way to update them.
 3. **Semantic verification** for every source the deterministic pass flagged: read the changed page (fetch the registry URL), decide whether any `<!-- source: X -->` marked sentence in `references/standards.md` (or the mirrored SKILL.md hard-limits row) is now wrong, and propose the minimal edit. Unlike version-pin registries, checksum drift here is presumed meaningful until a human reads the diff — these pages define the standards themselves. Editorial churn may be accepted silently only after that read.
 4. **One standing refresh PR**, branch `refresh/weekly`, force-updated on every run (never stacked duplicates; the weekly workflow .github/workflows/refresh.yml maintains it). PR body lists: each changed source, old→new checksum, links to the evidence, and which marked sentences changed and why. A maintainer review is mandatory before merge.

package/skill-integrity.json

@@ -1,58 +1,34 @@
 {
   "schemaVersion": 2,
   "skills": {
-    "arch-guardian": {
+    "architect": {
       "files": {
-        "SKILL.md": "46eb5d40506c3e7b2f9d15a3cbfa189acb690ba55e7af924d463e003ae8eeb70",
-        "agents/openai.yaml": "9553ddb318a4b7f0d610343f28fc8af636fc4b24832a00e818c3b824449b0a59",
-        "assets/adr-template.md": "db813ef4621a76e1101b3a19fc944de60a38591b423d9a9ad6c8f0b1db38120c",
-        "assets/answers-example.json": "eed87446717032c60015232674272689bd68a7c8f5f43ff166aeaa0f649b7a9f",
-        "assets/architecture-profile.json": "70d78d81f2c65f7aa37d9ea7b7a5f0518961037262ae2db6da8e6c1f24757ee8",
-        "assets/architecture-profile.schema.json": "bcf370b882ef6e605abf530c8245d599471e8aa54f0ef42fc99b5119550b8905",
-        "assets/deployment-review-template.md": "e9be2feb153138d936f9ebd5763c3be10597cee639616f86cc082c498fd60cd2",
-        "assets/service-design-template.md": "670798e3bf26a76d593294ff60763e1a6a35866fa84ea74345406b05b4b0b61b",
-        "assets/threat-model-template.md": "ffcf22e3fc81c803d976ac6c41cbac4fb0f552d81653b89a5b587a46b59d9aed",
-        "references/advisory-report.md": "bfc0dc8e985e33312ed0617705b359457eaea7b6056307e94ea293d167992dd4",
-        "references/architecture/agent-product.md": "3b8039ef9ca6aa30fc8781475e005d7bbb9d8d415705a6e8c79b4a602ee1ed5e",
-        "references/architecture/ai-cost.md": "9cb300e5718c15d5e6c29d22293b4ca80340e73d2b77267fbc529016c6262dd2",
-        "references/architecture/ai-data-boundaries.md": "0d756d0132d05e0e45dcd1b582e6c4bfe04a9043ab8df64d9a88fb086d8b29ff",
-        "references/architecture/ai-evals.md": "9b9698acd8b73c17ea301569b6c57bbdede304cfec7fa6f7d6d4af017a64fa6c",
-        "references/architecture/connectors-sandbox.md": "c12248cb0eddf51143e6f14c71541042d676b405bf274271bb69148c621ab41f",
-        "references/architecture/data-memory.md": "3d2ccbcd90a00dddda7096877c874d4fa7b61b96e2e4061c3c82b40bd990cf19",
-        "references/architecture/delivery-operations.md": "82fafe5f0f157f7a870ff6c9aad64564ab121ac049446318fcf9c1b7f4517f36",
-        "references/architecture/durable-execution.md": "4dd1c7d69e41fb0abf7f469c8eadd1695b15c502e0219108c76d8aea06f9ffe6",
-        "references/architecture/flutter.md": "f024292b89b4667c65993bba906fb16afd278824f205f0e39c96a58384c6f423",
-        "references/architecture/foundation.md": "19536e03fdbb8720e263600a298b11e980cf6c24a724f8692db83b04302b39f1",
-        "references/architecture/hosting-reliability.md": "c69b00a354d78e2a7b2845cddc0d8a642911bc009efefa141075d1d774756142",
-        "references/architecture/identity-tenancy.md": "5fb2e5d74ae24ad2efe3ba01c06b8fcc16ba1dce1b9c531b7d955352af38d4c2",
-        "references/architecture/model-lifecycle.md": "eacdeade0fa88caaca11de9a9e69f0db8a9ecfc8b472070afb7158f5e30f6ba2",
-        "references/architecture/models-observability.md": "5501655b71d85e9653e5a8c276e481e2765b2a0c67c5bc23759f869529278b94",
-        "references/architecture/realtime-channels.md": "a95738c431f3f4c8c42c153a0b940897bae8d679ed0c2dfced3cb1c4c9c67ca5",
-        "references/architecture/security-privacy.md": "28d8d1a6347df95807d274829b2fbbd852c07a74d52d7e0be18d208b559504ea",
-        "references/architecture/topology-monorepo.md": "fdad26c8eaa32b977139e6f70c90a3954332a1fa6dd6e8d98bc9fb7c5a613117",
-        "references/architecture/web.md": "560957d179f9372ff01e3e216fdc8ad1cbee290ac95f42094d04da4af08a4c0a",
-        "references/foundation-compatibility.json": "dfbf106631ebd229d683b18855e126cdc4684a252038123b25d002724571ac14",
-        "references/golden-patterns.md": "0b00ece15e0ae20450d5c20409e7be34bab0d9b47c1614fb48cef780ca66605b",
-        "references/profile-governance.md": "b3ed0b4580c73fa0340c33267707ee9515071ac2b64bdc3dd56b8c558431a0b3",
-        "references/rule-model.json": "b9d4d13d152eecbb73a5add12c8ab9bb050e0f1001495c90c8b801d029b56598",
-        "references/workflows.md": "f54c284d831e14da00886fd186bc711bb8598fca4f2fc309f6caa197835e79ae",
-        "refresh/REFRESH.md": "db15a4304d0a3d3ab7f53722d30fb76609f1823cb2dc998f1807f092e79e008a",
-        "refresh/sources.json": "d35735620325c45693c8eddb5de5e7e1867cae19554e118b45867f8984250950",
-        "scripts/lib.mjs": "4ef4910518134eea7f89b6e397e5871f66a416429c75f59bf37e0864e4cf7ca0",
-        "scripts/profile-tool.mjs": "c13230b1c6a7bce9b91fb8a6a7d6eb84e9ef8855bf8b2a544e7bbfdc38e94877",
-        "scripts/refresh-evidence.mjs": "4759cedd15470247df23485b4c8d258e7e8f22cbceaac60f7e63cb42159af779",
-        "scripts/schema-validate.mjs": "329cca29ead284949107a5e0984588373522e9ef6624dffd18d4d207ef51fc99",
-        "scripts/validate-profile.mjs": "0b1f6b6d9e21267fd1ac545fd47fe46d9ecddc6a2efe67c5518e0845719a2b4d",
-        "scripts/verify-corpus.mjs": "d752efb00145afeaa7d2e758e10c5c11670253c1387326a52d6dda7fc67cda1c"
+        "SKILL.md": "70327518548075edd58f140710273df6dba6bd49327252a085b6881aae2f6663",
+        "agents/openai.yaml": "5bee46acf49a8c01856eec2a51a57aad95257c064302fca7f5e952016054b4e0",
+        "assets/adr-template.md": "72c84eebf90a7de8a6fc79c5165bada2683b38e86ccb1e3936e305f71be67d91",
+        "assets/arch-template.md": "a3dbfbd8b8f115e5cf3a922f26571ca469e0f4962d924e88bd9d8fd280b75d89",
+        "references/advisory.md": "ecba7d92cbf4dee9a6c9b7e0cb86f863748435be9fde4c0c8f493bcbc8e48249",
+        "references/ai-agents.md": "f39af3e8e6ea111157225c2786b428d66c944546898b08e45f12069633cf007e",
+        "references/data.md": "6c0384b53b66c914e39b4ca5f146cb50f1b91ca3ca5106e43b5cc2ce17bc59d5",
+        "references/infra.md": "cd56381da2d59fb2362fc162246269116cba92f796d0847cbac03e478b600add",
+        "references/mobile.md": "19932670613c064c979cf6d675c94213d3b12a5382d6fff4eacd58cb8b2a609c",
+        "references/pinned-facts.md": "07212409f708bd00ed69c77e98c61303ed1718514d907eb135c4c8ffe081196e",
+        "references/principles.md": "1d33c9f2912c04341c50398e30482c348d98a22ea218b06eca47b7aa247685b1",
+        "references/project-profile.md": "f3455643044260405ac47cdbeef5238e87a8ff9fbb285ce256a2aca9be9ff522",
+        "references/security.md": "4be060806c63c8c56559c293a818af581c2d7aec29f1830b57570dfda3c69d4a",
+        "references/stack.md": "b3aea9bb500b14c5bdb7576252e0af3be012d8c1f849d812c446e82ca2192af4",
+        "references/web.md": "df296df0a3c4fbbeda47f49ac96b4f0e9f4c5bba5dd68a428a3e390abd7f2261",
+        "refresh/REFRESH.md": "cdf7a06dd70f4b9483aa7a1db8c5e6c8e0a1f1724be22031d1aba1f609d69e22",
+        "refresh/sources.json": "38cf2a3fb13b5b4f3eec59d40d4faa4e5edcc0aecb66fbdd031aeefb92fecc01"
       }
     },
     "skill-maintainer": {
       "files": {
         "SKILL.md": "bbbf15a9900d9d2009ccfbe163cface9654c81a9a84777718348d97b30739aeb",
         "agents/openai.yaml": "0b89d4e6416cf20b448f5322f3d7433cfde333d2b4a05b42ed53db3759701fb4",
-        "references/release-ops.md": "2bde6c55cbe7674678e14b915fc5ebe565413aeb25c3d51a86e195af53004d01",
+        "references/release-ops.md": "a32c6dd6fff7b5c44d3d6dbcb32d7f3eb14f1ca61db85c0b31de032727952c3d",
         "references/standards.md": "3646d0dd0560a87b333f70febf670b093c89b35111132cdb641b763bf184b02f",
-        "refresh/REFRESH.md": "a9a86a979ef720cf2f316c76f05db0fd9beef591401b95ceb475474fe40bc936",
+        "refresh/REFRESH.md": "badbf807de2b2b38a7acb77d4e5a82ec7677afa1cb97abef34c429a81b855508",
         "refresh/sources.json": "cf38cdf8123a50ea7ef2d1466a87faa648c12e5bc90d9ee9b6ae45632e7d0800"
       }
     },