@sun-asterisk/sungen 2.7.0-beta.1 → 3.0.0-beta.72

package/dist/orchestrator/templates/ai-instructions/claude-cmd-review.md

@@ -1,45 +1,42 @@
 ---
 name: review
-description: 'Review test cases for a Sungen screen — validate syntax, score coverage, check viewpoint quality.'
+description: 'Independent quality checkpoint for test cases — runs the harness (audit gate + reviewer + script-check) from a fresh context and presents one unified scorecard. Use for manually/prompt-authored or hand-edited testcases, before delivery, or in CI.'
 argument-hint: [screen-name]
-allowed-tools: Read, Grep, Glob, Edit, Write, AskUserQuestion
+allowed-tools: Read, Grep, Glob, Bash, Edit, Write, AskUserQuestion
 ---
 
 ## Role
 
-You are a **Senior QA Reviewer**. You evaluate Gherkin test cases using the `sungen-tc-review`, `sungen-viewpoint`, and `sungen-gherkin-syntax` skills.
+You are an **independent QA Reviewer** running in a **fresh context** — you did not author these tests. You do **not** invent a parallel score; you run the **harness** and present its signals as a human scorecard. Skills: `sungen-tc-review` (presentation rubric), `sungen-viewpoint`, `sungen-gherkin-syntax`.
 
-## Parameters
+## When this matters (positioning)
 
-Parse **name** from `$ARGUMENTS`. If missing, ask the user.
-
-**Auto-detect context**: check if `qa/flows/<name>/` exists → flow mode (base path: `qa/flows/<name>/`). Else check `qa/screens/<name>/` → screen mode (base path: `qa/screens/<name>/`).
+`/sungen:create-test` already runs the harness gate + repair while generating, so you do **not** need to review right after it. Run `/sungen:review` when the harness did **not** run, or when you need an independent sign-off:
+- Test cases **written by hand or by a free-form prompt** (bypassing create-test).
+- A `.feature` that was **hand-edited** after generation.
+- **Before `/sungen:delivery`** — an independent quality + integrity gate before client hand-off.
+- In **CI** — fail the build on a failing gate or spec drift.
 
 ## Steps
 
-1. **Enumerate feature files** — glob `<base>/<name>/features/*.feature`. A screen may have one main file (`<name>.feature`) plus sub-features (`<name>-<sub>.feature` like `awards-modal.feature`); a flow has a single `<name>.feature`. If zero `.feature` files found → `/sungen:create-test` first.
-2. **Review every feature file** — for each `<basename>.feature` discovered in step 1:
-   - Read `<basename>.feature` and the matching `test-data/<basename>.yaml`.
-   - Apply the `sungen-tc-review` skill — score the **7-dimension rubric (100 pts)**: Structure & Format (15), Coverage (30), Assertion Quality (20), Test Data (10), Security & Permission (10), Automation Readiness (10), Maintainability (5). **For flows**, also apply the flow-specific checks (Layer A7 "Tags & Flow"). Use `sungen-viewpoint` for pattern checklists.
-   - Apply the **Unverified Selectors check** — if `<base>/<name>/selectors/<basename>.yaml` exists, count lines matching `@needs-live-verify`. Include in the per-file report as a non-scoring metric. Does NOT affect the score or the PASS threshold.
-3. **Aggregated output** — present scores in a per-feature table, then a screen-level rollup:
+1. **Enumerate feature files** — glob `<base>/<name>/features/*.feature` (main + any sub-features). If none → `/sungen:create-test` first.
+2. **Run the harness (source of truth) — do NOT re-score with a separate rubric:**
+   - `sungen audit --screen <name>` (Bash) → gate status, business-weighted score, findings, gaps (coverage / assertion-depth / balance / duplicate / traceability).
+   - **`sungen-reviewer`** sub-agent (Task tool, `subagent_type: sungen-reviewer`) → semantic verdict the gate can't see (do steps prove the title, observable Then, @manual justified). Copilot/no-sub-agents: apply the `sungen-reviewer` criteria inline.
+   - `sungen script-check --screen <name>` (Bash) → is the generated spec a 1:1 of the Gherkin (only if a spec exists; flags hand-edit / stale drift).
+3. **Unified scorecard** — present ONE report per feature, anchored on the harness signals (the `sungen-tc-review` 7 dimensions are a *presentation layer* over these, not a competing score):
 
    ```
-   Feature              Total  Verdict       Unverified
-   ─────────────────────────────────────────────────────
-   home.feature           88   PASS          0
-   home-modal.feature     64   CONDITIONAL   2
-   ─────────────────────────────────────────────────────
-   Screen rollup (mean)   76   PASS
+   Feature        Gate   Score   Reviewer        Spec 1:1     Verdict
+   ───────────────────────────────────────────────────────────────────
+   home.feature   PASS   8.4/10  2 minor issues  in-sync      PASS
    ```
-
-   - **>= 70**: PASS that file.
-   - **50–69**: CONDITIONAL — fix before execution.
-   - **< 50**: FAIL — revise & re-review.
-   - "Unverified" = count of `@needs-live-verify` selectors (non-scoring). Show the full per-file report (dimension breakdown, recommendations, top issues) **only for files that are CONDITIONAL or FAIL**, or when the user asks for the deep report.
-4. If any file is CONDITIONAL or FAIL and user confirms → update that file's test cases following `sungen-gherkin-syntax` and `sungen-tc-generation` skills, then re-review **only those files** (skip already-passing ones to save time).
-5. After all files PASS (or user decides to proceed), use `AskUserQuestion` to offer next steps:
-
-- **`/sungen:run-test <name>`** — Generate selectors, compile, and run tests for **every feature** in this screen (Recommended)
-- **`/sungen:create-test <name>`** — Add more test cases before running
-- **Done for now** — I'll come back later
+   - **Gate PASS + reviewer clean + spec in-sync** → PASS.
+   - **Gate FAIL or reviewer NEEDS-REPAIR or drift** → CONDITIONAL/FAIL — show the findings + reviewer issues + fixes.
+   - The score is the **audit business-weighted score** adjusted down by unresolved reviewer issues — never a parallel number that contradicts the gate.
+4. **Repair (on confirm)** — if CONDITIONAL/FAIL, apply the audit findings + reviewer fixes (use `remember`/`see all` for cross-screen/filter per `sungen-harness-audit`), then re-run step 2 for the affected file. If a drift was found, `sungen generate` to resync the spec (never hand-edit it).
+5. **Trace + next steps** — run `sungen trace --screen <name>` to show the **human-loop focus** (@manual scenarios to verify). Then `AskUserQuestion`:
+   - **`/sungen:run-test <name>`** — generate selectors, compile, run (if not yet run) **(Recommended)**
+   - **`/sungen:delivery <name>`** — export the deliverable (review passed)
+   - **`/sungen:create-test <name>`** — add more coverage
+   - **Done for now**

package/dist/orchestrator/templates/ai-instructions/claude-cmd-run-test.md

@@ -45,7 +45,7 @@ Skip this pre-flight when `--env` matches the base locale (no overlay needed in
             one browser_snapshot → cross-verify every [Reference] label vs snapshot name →
             generate selectors.yaml (verified entries; explicit YAML for any label≠DOM-name mismatch)
      NO  → spec_figma.md exists in requirements/?
-             YES → provisional flow (sungen-figma-source + sungen-selector-fix skills):
+             YES → provisional flow (sungen-capture mode figma-pat + sungen-selector-fix skills):
                    1. Read filtered Figma node data from spec_figma.md (## Components + ## Text Inventory)
                    2. Apply selector priority from sungen-selector-fix § Step 3 (testid > role+name > label > placeholder > text > locator CSS last)
                    3. Write selectors.yaml — every provisional entry gets this comment on the line above:
@@ -83,6 +83,9 @@ Skip this pre-flight when `--env` matches the base locale (no overlay needed in
 6. **Phase 2 — Priority Wave**: Run all `@high` scenarios. Fix only failures from this wave. Max 2 attempts. Shared selectors fixed here cascade to later phases.
 7. **Phase 3 — Full Run**: Run all tests. Fix only **new** failures (elements unique to `@normal`/`@low`). Max 1 attempt. Don't loop on low-priority failures.
 8. **Phase 4 — Regression**: One final full run. Report results. No more fix loops.
+9. **Integrity check & trace (always run after the final run).**
+   - `sungen script-check --screen <name>` — verify the generated spec is a **1:1** of the Gherkin (every non-@manual scenario ↔ one `test()`, no drift). If it reports **DRIFT** (spec hand-edited or stale), re-run `sungen generate --screen <name>` so the spec matches the feature, then re-run — **never hand-edit the generated spec** (auto-fix must edit `selectors.yaml`, not the `.spec.ts`).
+   - `sungen ledger record --screen <name> --step run --ms <elapsed>` (record this run), then `sungen trace --screen <name>` — show the process map + bottlenecks + **HUMAN-LOOP FOCUS** (the @manual scenarios the QA must verify) to the user.
 
 ## Playwright command guidelines
 

package/dist/orchestrator/templates/ai-instructions/claude-config.md

@@ -16,10 +16,7 @@ You generate 3 files for sungen — a Gherkin compiler that produces Playwright
 | `sungen-selector-keys` | YAML key generation from `[Reference]` names, suffixes, lookup priority |
 | `sungen-selector-fix` | Selector generation from live page, auto-fix strategy |
 | `sungen-delivery` | Export Gherkin + Playwright results → CSV test case deliverable |
-| `sungen-capture-figma` | Fetch design context + PNG from a Figma frame URL via Figma Dev Mode MCP |
-| `sungen-capture-local` | Load existing UI assets (screenshots, mockups, Figma exports) from `requirements/ui/` |
-| `sungen-capture-live` | Capture a live running page via Playwright MCP (snapshot + screenshot) |
-| `sungen-figma-source` | Figma URL → spec_figma.md + ui/*.png + provisional selectors |
+| `sungen-capture` | Acquire visual/design context — one skill, 4 modes: figma-mcp (Dev Mode MCP), figma-pat (URL → spec_figma.md), live (Playwright MCP scan), local (images in `requirements/ui/`) |
 | `sungen-locale` | Bootstrap i18n — audit selectors, detect locale switch mechanism, generate test-data overlay |
 
 ## Workflow (7 AI commands)

package/dist/orchestrator/templates/ai-instructions/claude-skill-capture-mode-figma-mcp.md

@@ -0,0 +1,82 @@
+# Capture mode: figma-mcp
+
+Pull **structured design data** (layout, typography, colors, component tree, design tokens) and a **PNG screenshot** from a Figma frame URL via the **Figma Dev Mode MCP**, so `sungen-tc-generation` can author Gherkin + test-data before a live domain exists. Use when the project is pre-launch or Figma is the source of truth and the live build lags the design.
+
+## Prerequisites
+
+- **Figma MCP server** (`https://mcp.figma.com/mcp`, HTTP transport) connected in `.mcp.json` — `sungen init` scaffolds this. On first use, Claude Code opens a browser for Figma OAuth. Official tools: `get_design_context`, `get_variable_defs`, `get_screenshot`.
+- Figma account signed in with access to the file. **Dev/Full seats** get per-minute rate limits; **Starter/View seats** get monthly tool-call limits.
+- A Figma URL with both **fileKey** and **nodeId**.
+
+If the MCP is not connected, **do not fail silently** — tell the user:
+> "Figma MCP not detected. Run `sungen init` to scaffold the config, or manually add `figma` with `url: https://mcp.figma.com/mcp` to `.mcp.json`. Then sign in when Claude Code prompts."
+
+Then stop.
+
+## Steps
+
+### 1. Resolve Figma URL
+
+Prefer in this order:
+1. `Figma URL` field in `requirements/spec.md` (Overview section)
+2. If empty/missing → `AskUserQuestion`: *"Paste the Figma frame URL"* (free text)
+
+Accept any of these shapes:
+```
+https://www.figma.com/file/<fileKey>/<title>?node-id=<nodeId>
+https://www.figma.com/design/<fileKey>/<title>?node-id=<nodeId>
+https://www.figma.com/proto/<fileKey>/<title>?node-id=<nodeId>
+```
+Parse: `fileKey` = segment after `/file/`, `/design/`, or `/proto/`; `nodeId` = the `node-id` query param (pass `-` or `:` through as-is). If `node-id` is missing, ask the user to select a frame in Figma and copy the **frame URL** (not the file root).
+
+### 2. Fetch design context
+
+Call **both** in parallel:
+```
+get_design_context({ fileKey, nodeId })
+get_variable_defs({ fileKey, nodeId })
+```
+`get_design_context` → layout, typography, colors, component structure, spacing. `get_variable_defs` → named design tokens.
+
+### 3. Fetch screenshot
+
+```
+get_screenshot({ fileKey, nodeId })
+```
+Save the PNG to `requirements/ui/figma-<sanitized-nodeId>.png` (replace `:` and `-` with `_`, e.g. `42-15` → `figma-42_15.png`).
+
+### 4. Write metadata dump
+
+Combine design context + variables into `requirements/ui/figma-meta.md`:
+```markdown
+# Figma Capture — <nodeId>
+**Source:** <full Figma URL>
+**Captured:** <ISO date>
+## Components
+<component names + variants>
+## Typography
+<font families, sizes, weights, line heights>
+## Colors
+<color tokens + raw hex>
+## Spacing & Layout
+<spacing tokens, auto-layout specs>
+## Text Content
+<visible text strings — used by tc-generation to populate test-data>
+```
+Consumed by `sungen-tc-generation` as a secondary source alongside `spec.md`.
+
+### 5. Report back
+
+> Captured Figma frame `<nodeId>`: Components N · Text strings M · Design tokens K · Screenshot `requirements/ui/figma-<nodeId>.png` · Metadata `requirements/ui/figma-meta.md`
+
+Then hand back to the calling command.
+
+## Error handling
+
+| Error | Action |
+|---|---|
+| MCP tool not available | Print setup instructions, stop, do not fall back silently |
+| `fileKey` missing from URL | Ask user to paste a valid frame URL |
+| `nodeId` missing from URL | Ask user to right-click a frame in Figma → *Copy link to selection* |
+| `get_design_context` 403 | Ask user to check Dev Mode seat on that file |
+| `get_screenshot` returns no image | Continue with metadata only; warn no PNG was captured |

package/dist/orchestrator/templates/ai-instructions/{github-skill-sungen-figma-source.md → claude-skill-capture-mode-figma-pat.md}

@@ -1,18 +1,6 @@
----
-name: sungen-figma-source
-description: 'Figma URL → spec_figma.md envelope + LLM-synthesized narrative from cached raw node JSON. Auto-loaded when --figma flag present or spec_figma.md exists.'
-user-invocable: false
----
+# Capture mode: figma-pat
 
-## When This Skill Loads
-
-Auto-load triggers (any one is sufficient):
-
-- Any sungen AI command invoked with `--figma` flag
-- `requirements/spec_figma.md` exists in the screen directory
-- User mentions a Figma URL or says "generate from Figma"
-
----
+Figma URL → `spec_figma.md` envelope + LLM-synthesized narrative from cached raw node JSON. This mode is the active one when any of these is true: a sungen command was invoked with `--figma`, `requirements/spec_figma.md` exists, or the user says "generate from Figma".
 
 ## Prerequisites
 
@@ -22,8 +10,6 @@ Auto-load triggers (any one is sufficient):
 
 **Never paste the PAT into any transcript, spec file, or commit.**
 
----
-
 ## Two-Layer Architecture
 
 `spec_figma.md` has two layers separated by the `<!-- SYNTHESIS-BELOW -->` marker:
@@ -31,34 +17,27 @@ Auto-load triggers (any one is sufficient):
 | Layer | Producer | Overwrite Rule |
 |---|---|---|
 | **Envelope** (above marker) | sungen CLI | Regenerated each `sungen figma` run — deterministic |
-| **Narrative** (below marker) | This skill (LLM) | Replaced on re-synthesis — everything from marker to EOF |
+| **Narrative** (below marker) | This mode (LLM) | Replaced on re-synthesis — everything from marker to EOF |
 
 The envelope contains: YAML frontmatter, Frame metadata, Screenshots. The narrative is synthesized by YOU from the cached raw Figma node JSON.
 
----
-
 ## Inputs You Read
 
 The scaffolder persists a raw (unfiltered) Figma node tree to:
-
 ```
 .sungen/figma-cache/<fileKey>/<versionId>/<nodeId>-raw.json
 ```
-
 Read this file + the envelope frontmatter of `requirements/spec_figma.md` + any PNGs under `requirements/ui/`. You MUST NOT call the Figma REST API directly — the PAT is not available to you.
 
----
-
 ## Synthesis Task
 
-Append 7 narrative sections below `<!-- SYNTHESIS-BELOW -->`. Each section is inferred from the raw node tree (names, types, `characters`, layout bounds, auto-layout direction, componentProperties):
+Append 7 narrative sections below `<!-- SYNTHESIS-BELOW -->`. Each is inferred from the raw node tree (names, types, `characters`, layout bounds, auto-layout direction, componentProperties):
 
 ### 1. Purpose
 One paragraph. What screen is this? Primary user goal? Infer from frame name + top-level text + dominant CTA.
 
 ### 2. ASCII Layout
-Rough spatial sketch using box characters. Reflect top-bottom / left-right ordering from absoluteBoundingBox. Keep under ~20 lines. Example:
-
+Rough spatial sketch using box characters. Reflect top-bottom / left-right ordering from absoluteBoundingBox. Keep under ~20 lines:
 ```
 ┌──────────────────────────────────────┐
 │ [Logo]                     [Sign In] │
@@ -72,55 +51,46 @@ Rough spatial sketch using box characters. Reflect top-bottom / left-right order
 ```
 
 ### 3. Regions
-Bulleted list of the major layout regions (header, sidebar, main, footer, modal, etc.) with a one-line purpose each. Use auto-layout frames as region hints.
+Bulleted list of major layout regions (header, sidebar, main, footer, modal…) with a one-line purpose each. Use auto-layout frames as region hints.
 
 ### 4. Actions
-Every interactive element the user can trigger. Derive from nodes whose name/type suggests a button, link, icon-button, menu-item, toggle, etc. Format:
-
+Every interactive element the user can trigger (button, link, icon-button, menu-item, toggle…):
 ```
 - **<Action name>** — <what it does> (source: <node name>)
 ```
 
 ### 5. Form Fields
-Every input the user can fill. Include label, type (text/email/password/select/checkbox/radio/textarea/date), required hint if inferable, and placeholder.
-
+Every input. Include label, type (text/email/password/select/checkbox/radio/textarea/date), required hint if inferable, placeholder:
 ```
 | Label | Type | Required | Placeholder |
 |---|---|---|---|
 ```
-
-Omit entirely (write `_none_`) if no inputs exist.
+Omit (write `_none_`) if no inputs exist.
 
 ### 6. Data Columns
-If the screen shows a table, list, or card grid — enumerate the columns/fields displayed per row. Otherwise write `_none_`.
+If the screen shows a table/list/card grid — enumerate the columns/fields per row. Otherwise `_none_`.
 
 ### 7. Navigation
-Outgoing links, tab bars, breadcrumbs, back buttons — anything that moves the user to another screen. Include both explicit navigation components and implicit CTAs that navigate.
-
----
+Outgoing links, tab bars, breadcrumbs, back buttons — anything that moves to another screen. Include explicit nav components and implicit CTAs that navigate.
 
 ## Synthesis Workflow
 
 1. Read `requirements/spec_figma.md` — note `file_key`, `node_id`, `figma_version_id` from frontmatter
 2. Read `.sungen/figma-cache/<file_key>/<figma_version_id>/<safe_node_id>-raw.json` (colons in node_id become underscores)
-3. Traverse the tree. Collect: names, types, `characters`, `componentProperties`, `absoluteBoundingBox`
+3. Traverse the tree. Collect names, types, `characters`, `componentProperties`, `absoluteBoundingBox`
 4. Produce the 7 sections above
 5. **Locate the insertion point** in `spec_figma.md`:
    - **If `<!-- SYNTHESIS-BELOW -->` is present** → replace everything from the marker (inclusive) to EOF with: the marker line, a blank line, then the 7 sections.
-   - **If the marker is NOT present** (older `spec_figma.md` pre-envelope-refactor, or hand-edited file) → locate the last non-empty line of the envelope (usually the end of `## Screenshots`), append a blank line, then write the marker, another blank line, then the 7 sections. Do NOT delete any existing envelope content.
+   - **If the marker is NOT present** (older file or hand-edited) → locate the last non-empty line of the envelope (usually the end of `## Screenshots`), append a blank line, then the marker, another blank line, then the 7 sections. Do NOT delete any envelope content.
    - **If the file is missing entirely** → advise the user to re-run `sungen add --screen <screen> --figma <url> --refresh` to regenerate the envelope first. Do not fabricate one.
 6. Preserve the envelope (frontmatter + Frame + Screenshots) byte-for-byte. Never touch content above the marker.
 
----
-
 ## Re-synthesis
 
 - If the envelope's `figma_version_id` changed → envelope is fresh; re-run synthesis
-- If only the narrative is stale (user wants a rewrite) → truncate from marker to EOF and regenerate
+- If only the narrative is stale → truncate from marker to EOF and regenerate
 - Never edit content ABOVE the marker — that is the scaffolder's territory
 
----
-
 ## Selector Heuristics (for downstream `run-test`)
 
 During `run-test` Phase 0, provisional selectors can be seeded from the raw JSON:
@@ -135,15 +105,11 @@ During `run-test` Phase 0, provisional selectors can be seeded from the raw JSON
 | Node name ends `Icon` | `role: img` + `name: "<accessible name>"` |
 
 Every provisional entry MUST carry:
-
 ```
 # @needs-live-verify source=figma node_id=<id>
 ```
-
 Provisional selectors feed `selectors.yaml` as candidates. `run-test` Phase 0 verifies them against the live page and overwrites incorrect entries.
 
----
-
 ## Security
 
 - Never include the PAT in `spec_figma.md`, selectors, test data, or any committed file

package/dist/orchestrator/templates/ai-instructions/claude-skill-capture-mode-live.md

@@ -0,0 +1,60 @@
+# Capture mode: live
+
+Navigate a running application, take **one accessibility snapshot** and **one screenshot**, and save them as visual context for test generation. Use when the app is live (dev, staging, or production with read-only access) and you want tests grounded in the actual rendered UI. Handles auth gracefully: if the page redirects to login, ask the user to sign in manually rather than injecting cookies.
+
+## Prerequisites
+
+- Playwright MCP connected.
+- Dev/staging server reachable (or a public URL).
+- `playwright.config.ts` exists at the project root (for `baseURL` fallback).
+
+## Steps
+
+### 1. Resolve target URL
+
+1. `Live URL` field in `requirements/spec.md` (Overview section)
+2. `baseURL` from `playwright.config.ts` + `URL Path` from `spec.md`
+3. Neither → `AskUserQuestion`: *"Paste the full URL for the page to scan"*
+
+### 2. Navigate
+
+`browser_navigate` to the resolved URL.
+
+### 3. Handle auth redirect
+
+If the page redirects to a login route (URL contains `/login`, `/signin`, `/auth`, or content indicates a login screen):
+1. Tell the user which login URL they landed on.
+2. `AskUserQuestion`:
+   - **I'll log in manually** — wait for confirmation, then re-navigate to the target URL
+   - **Skip live scan** — switch to mode `local`
+   - **Cancel**
+3. **Never** inject cookies or localStorage via `browser_evaluate` / `browser_run_code`. Auth belongs to the user.
+
+### 4. Snapshot
+
+Take **ONE** `browser_snapshot`. This accessibility tree is the primary AI context — roles, names, text, structure that tc-generation uses to identify sections and fields.
+
+### 5. Screenshot (recommended)
+
+Take **ONE** `browser_take_screenshot` with `fullPage: true`. Save to `requirements/ui/live-<timestamp>.png`, where `<timestamp>` is `YYYYMMDD-HHMM` local time (e.g. `live-20260421-1430.png`).
+
+### 6a. Verify unauthenticated redirect target (flow capture only)
+
+When capturing for a **flow** with security scenarios (e.g. "unauthenticated user cannot access X"):
+1. Open a **fresh incognito/unauthenticated** context (no storage state).
+2. `browser_navigate` to the protected route.
+3. Record the **actual redirect URL** — do NOT assume `/login`; it may be `/register`, `/`, etc.
+4. Report the redirect target: *"Unauthenticated access to `/dashboard` redirects to `/register`"*.
+5. The caller must use the **actual redirect URL** in Gherkin assertions, never an assumed one.
+
+Skip if the flow has no security scenarios or the user says to skip.
+
+### 6. Detect discrepancies vs spec
+
+If `spec.md` exists, cross-check the snapshot against spec sections: fields in spec but not in snapshot → *missing in UI*; elements in snapshot but not in spec → *missing in spec*. Report findings but **do not** auto-edit `spec.md`.
+
+### 7. Report back
+
+> Captured live page `<URL>`: Snapshot N interactive elements · Screenshot `requirements/ui/live-<timestamp>.png` · Discrepancies vs spec: <count or "none">
+
+Hand back to the calling command. Scans **exactly one** page per invocation.

package/dist/orchestrator/templates/ai-instructions/claude-skill-capture-mode-local.md

@@ -0,0 +1,38 @@
+# Capture mode: local
+
+Use **pre-existing images** in `requirements/ui/` as visual context. No network, no MCP, no live site — works for any design tool (Figma export, Sketch, Penpot, Zeplin, hand-drawn, staging screenshots). This is the **baseline fallback**: if the live domain is down and Figma MCP isn't configured, this always works as long as the user drops images in the folder.
+
+## Steps
+
+### 1. List available images
+
+Glob `requirements/ui/*.{png,jpg,jpeg,webp,gif}` and report count + filenames. Filter out metadata files (e.g. `figma-meta.md` written by mode figma-mcp) — those are read by `tc-generation` separately, not treated as images here.
+
+### 2. Handle empty folder
+
+If no images found:
+1. Tell the user the folder is empty, with the full path so they can open it in Finder.
+2. `AskUserQuestion`:
+   - **I'll drop images now** — wait for confirmation, then re-glob
+   - **Switch to Figma** — switch to mode `figma-mcp`
+   - **Switch to live page scan** — switch to mode `live`
+   - **Cancel** — abort create-test
+3. If "drop images now", wait for confirmation (e.g. "done") then re-run step 1.
+
+### 3. Read images for context
+
+Use the `Read` tool on each image — Claude Code reads PNG/JPG/WebP directly as visual context. For large sets (>10 images), ask which are primary and which are states/variants to avoid loading too much at once.
+
+### 4. Summarize
+
+> Loaded N image(s) from `requirements/ui/`:
+> - `<filename-1>` — <one-line description of what's visible>
+> - `<filename-2>` — <one-line description>
+
+Hand back to the calling command.
+
+## File naming hints for users
+
+Nudge users toward consistent filenames (don't enforce):
+- `<section>-default.png` / `-error.png` / `-loading.png` / `-empty.png` — section states
+- `full-page.png` / `viewport.png` — whole screen (auto-generated by `sungen add --capture`)

package/dist/orchestrator/templates/ai-instructions/claude-skill-capture.md

@@ -0,0 +1,35 @@
+---
+name: sungen-capture
+description: 'Acquire visual/design context for test generation from one of four sources (modes): figma-mcp, figma-pat, live, local. Auto-loaded by create-test/add-screen when a visual source is needed, or when --figma flag / spec_figma.md is present. Router skill — read only the mode file you need.'
+user-invocable: false
+---
+
+## Purpose
+
+Bring **visual + design context** into test generation so `sungen-tc-generation` can author Gherkin + test-data grounded in the real UI. This is a **router**: pick exactly **one mode** for the run, then read only that mode's file. Do **not** read all four.
+
+This skill never generates Gherkin or `selectors.yaml` — it only acquires context and reports back to the calling command.
+
+## Pick the mode
+
+| Mode | Read | Use when | Needs |
+|---|---|---|---|
+| **figma-mcp** | `mode-figma-mcp.md` | Pre-launch / Figma is source of truth, **Figma Dev Mode MCP** connected | Figma MCP + frame URL |
+| **figma-pat** | `mode-figma-pat.md` | `--figma` flag was used, or `requirements/spec_figma.md` exists (synthesize narrative from cached raw node JSON) | `sungen figma auth` PAT |
+| **live** | `mode-live.md` | App is running (dev/staging/prod read-only) and you want the actual rendered UI | Playwright MCP + reachable URL |
+| **local** | `mode-local.md` | Images already dropped in `requirements/ui/` (any design tool, screenshots, mockups) — baseline fallback, no network | nothing |
+
+### How the mode is chosen (when the caller didn't specify)
+
+1. `requirements/spec_figma.md` exists → **figma-pat** (PAT flow already ran during `add-screen`).
+2. `requirements/ui/` has images → **local**.
+3. Neither → ask the user which source (figma-mcp / live / local), then load that one mode file.
+
+Modes are **mutually exclusive per run**, but the user can run `create-test` again with a different mode to layer context. All modes write to `requirements/ui/` and report back.
+
+## What this skill (any mode) does NOT do
+
+- Does not generate Gherkin — that's `sungen-tc-generation`.
+- Does not write `selectors.yaml` — that's `/sungen:run-test`.
+- Does not inject auth/cookies — the user logs in manually (see `live`).
+- Does not crawl or generate images.

package/dist/orchestrator/templates/ai-instructions/claude-skill-harness-audit.md

@@ -0,0 +1,84 @@
+---
+name: sungen-harness-audit
+description: 'How to read `sungen audit` output and repair test-design findings. Auto-loaded by the design orchestrator.'
+user-invocable: false
+---
+
+## What `sungen audit` measures
+
+`sungen audit --screen <name>` runs deterministic sensors over `features/<name>.feature` + `requirements/test-viewpoint.md` and writes `.sungen/reports/<name>-audit.json`. It is the **gate** the orchestrator repairs against. Run with `--json` to parse it.
+
+### Report shape (key fields)
+```jsonc
+{
+  "score": { "overall": 3.9, "coverage": 0.4, "businessDepth": 0.18, "balance": 0.5, "traceability": 0.7 },
+  "gateStatus": "PASS" | "FAIL",
+  "gate": { "pageType": "ecommerce-list", "themesCovered": 2, "themesTotal": 5,
+            "gaps": [ { "theme": "cart-correctness", "keywords": [...] } ] },
+  "depth": { "businessCriticalShallow": 9, "businessCriticalTotal": 11,
+             "shallowBusinessCritical": [ { "name": "...", "category": "PRODUCT" } ] },
+  "balance": { "imbalanced": true, "coreCount": 11, "secondaryCount": 22, "byBucket": {...} },
+  "duplicates": { "clusters": [ { "sameDataLikely": false, "scenarios": [...] } ] },
+  "trace": { "mappedRatio": 0.4, "note": "..." },
+  "findings": [ "GATE: ...", "DEPTH: ...", "BALANCE: ...", "TRACE: ..." ]
+}
+```
+- **`overall` score is business-weighted** (coverage 0.4 + businessDepth 0.3 + balance 0.15 + traceability 0.15). It is intentionally strict on business value — a high count with shallow business coverage scores low. Don't optimize the count; optimize coverage + depth.
+- Exit code **2** when `gateStatus == FAIL` (usable in CI / loop).
+
+## Finding → repair mapping
+
+| Finding prefix | Meaning | Repair action |
+|---|---|---|
+| **GATE** | a critical theme for the page-type has no covering scenario | Generate scenarios for that theme. **If cross-screen** (cart-correctness, product-detail-consistency, filter-result-correctness, multi-item cart) → do NOT fake it on a single screen; plan a **flow** (`/sungen:add-flow`) and record the deferral. |
+| **DEPTH** | business-critical scenarios assert only visibility/navigation | Replace `Then User see [X] page/section` with **observable data assertions**: `Then User see [X] with {{value}}`, `Then User see [T] table match data:`. Capture real expected values into `test-data.yaml`. |
+| **BALANCE** | secondary viewpoints (UI/validation/security) outweigh business-core | **Stop expanding** secondary viewpoints; generate the missing business-core scenarios first. Do not add more subscription/UI variants while core is thin. |
+| **TRACE** | scenarios use ad-hoc `VP-<CAT>-NNN` codes not linked to the viewpoint-overview | Make each scenario map to a viewpoint-overview id (align category codes, or add a mapping comment). |
+| **UNIVERSAL** | a universal theme (error/empty-state, accessibility) is absent | Low priority — add if in scope; otherwise note as out-of-scope with reason. |
+
+## P5 steps for deep cross-screen / list coverage
+
+Use these when repairing GATE/DEPTH findings for the hard viewpoints (cart/detail/filter correctness). They need **runtime data mode** (the default).
+
+- **Capture a value to compare across screens** (product-detail-consistency, cart-correctness):
+  ```gherkin
+  When User remember [Product Name] text as {{selected_product_name}}
+  And User remember [Product Price] text as {{selected_product_price}}
+  And User click [View Product] link
+  Then User see [Detail Product Name] header with {{selected_product_name}}
+  And User see [Detail Product Price] text with {{selected_product_price}}
+  ```
+  `remember` stores the element's text/value at runtime; later `{{var}}` resolves to it. This proves the detail/cart shows the SAME product, not a random one.
+
+- **Assert every item in a result matches** (category/brand-filter-correctness):
+  ```gherkin
+  When User click [Women] link
+  And User click [Dress] link
+  Then User see all [Result Product Name] contain {{selected_category}}
+  ```
+  `see all [X] contain {{v}}` asserts EVERY matching element contains the value → "all displayed products belong to the selected category/brand", not just one.
+
+> Cross-screen flows (home → detail/cart): if the target screen is a separate screen, prefer a **flow** (`/sungen:add-flow`) so the journey is one test. On a single screen, keep the cross-screen assertion but tag `@manual` with a `# Deferred to a flow` comment.
+
+## Repair loop rules
+
+1. **Budget = 3 rounds.** Re-run `sungen audit` after each repair; track score delta.
+2. **Stop when** `gateStatus == PASS` AND `findings` empty — or budget exhausted.
+3. **Never fake a pass.** A shallow `see [Cart] page` does not satisfy `cart-correctness`. If a gap is genuinely cross-screen or needs capabilities the DSL lacks (e.g. capture an element value to compare elsewhere), **report it as a residual gap / flow item** instead of forcing a green gate.
+4. **EP/data families are OK.** A `duplicates` cluster with `sameDataLikely=false` is an intentional equivalence-partition family (e.g. many invalid-email cases) — keep it; only collapse `sameDataLikely=true` exact duplicates.
+
+## Discovery / fallback tree (when input is limited)
+
+```
+spec.md đủ tốt?      → YES: Spec-first
+  │ NO
+source code có?      → YES: Source-first (mine behavior từ code)
+  │ NO
+testcase cũ tương tự?→ YES: History-first
+  │ NO
+domain rủi ro+defect?→ YES: Defect-first
+  │ NO
+→ hỏi QA; QA chưa phản hồi → OUTPUT kèm ASSUMPTION LIST rõ ràng (không stall)
+```
+
+See `docs/orchestration-spec.md` for the full flow and `reports/sungen_refactor_spec.md` for the design rationale.

package/dist/orchestrator/templates/ai-instructions/claude-skill-tc-generation.md

@@ -7,7 +7,7 @@ user-invocable: false
 ## ⚠️ Gotchas — read before generating
 
 - `spec_figma.md` exists → read file only, **NEVER** call `mcp__figma__*`
-  → PAT auth flow already done by `sungen-figma-source`; re-calling fails or duplicates work.
+  → PAT auth flow already done by `sungen-capture` (mode figma-pat); re-calling fails or duplicates work.
 
 - `selectors.yaml` → do **NOT** generate — handled by `run-test`
   → Selectors need live DOM inspection via Playwright MCP, only `run-test` triggers it.
@@ -221,6 +221,45 @@ Security:         [S1 – admin only]
 
 **✅ Good** — see admin notice example above: `Display surfaces` lists every URL spec mentions as output, `Cross-surface rules` maps each admin action to its user-facing outcome, `Inclusive bounds` flags every `<=`/`>=` for BVA. Every item maps to a VP-ID in `Tier 1 output`.
 
+#### Critical business-viewpoint pre-gate — pass `sungen audit` on the FIRST pass
+
+> The harness gate FAILS (and forces repair rounds → wasted tokens) when a page-type's critical **business** viewpoints are missing or **shallow**. Generate them correctly the first time. A business-critical `Then` must assert **DATA**, never just `see [X] page/section/modal`.
+
+**By page-type, generate a DEEP scenario for each (before expanding UI/validation/subscription):**
+
+| Page-type | Must-cover viewpoints (each with a data assertion) |
+|---|---|
+| **e-commerce list / home** | list-data (card has image+name+price+add) · product-detail-consistency · cart-correctness · category-filter-correctness · **brand-filter-correctness (separate from category)** · add-to-cart success · nav-core |
+| **form** | required-validation · format/boundary · submit-success |
+| **auth** | valid-login · invalid-credential · access-control |
+
+**Required assertion shapes (use these, not bare visibility):**
+- Card info: assert at **card level** (image+name+price together), e.g. `User see all [Product Card] contain {{...}}` — not `see [Section]` (section-level passes even if one card lacks price).
+- Cross-screen consistency (detail/cart): **capture then compare** —
+  ```gherkin
+  When User remember [Product Name] text as {{selected_product_name}}
+  And User remember [Product Price] text as {{selected_product_price}}
+  And User click [View Product] link
+  Then User see [Detail Product Name] header with {{selected_product_name}}
+  And User see [Detail Product Price] text contains {{selected_product_price}}
+  ```
+  Cross-screen target → tag `@manual` + `# Deferred to a flow (home -> detail)`.
+- Filter result (category AND brand, separately): `Then User see all [Result Product Name] contain {{selected_category}}` — proves EVERY item belongs, not one.
+
+**Depth is a GATE dimension (harness-roadmap P1) — self-raise, never silently go shallow:**
+- For every data-correctness theme the catalog marks `depth.requires: data-assertion`, emit its `depth.template` shape by **default** — don't wait for the repair loop. `sungen audit` measures `businessDepth` (ratio of these scenarios that assert data) against an intent threshold (functional ≥ 0.70); below it the **gate FAILs**.
+- `depth.cross_screen: true` (cart / detail / filter / brand correctness) → write the deep capture/compare shape but tag `@manual` + `# Deferred to a flow (...)`. These are excluded from the ratio (they're correctly deferred), so they don't hurt depth.
+- **If the spec lacks the concrete value** a deep assertion needs (exact message, price, count): still write the deep shape with a `{{var}}` placeholder and leave a `# SPEC-GAP: <field> value not in spec` comment — do **not** downgrade to `see [X] section`. A visible gap is better than a silent shallow pass.
+- **Blind-Spot Memory:** before finishing, run `sungen blindspot list --prompt` (Bash) and make sure the suite satisfies each recorded pattern (e.g. "for any Add/Create action: check success + resulting data state + duplicate/double-submit"). These are gaps QA hit before — don't repeat them.
+
+**First-pass anti-patterns (these are exactly what the gate/reviewer reject — avoid them):**
+- Title↔steps mismatch: e.g. a "no-result state" scenario that clicks a query which **returns** products. Steps must create the condition the title claims.
+- Tautology `Then`: `click [Next Slide]` → `see [Carousel] section` (always visible, proves nothing). Assert the change (new slide title differs).
+- Business-critical scenario ending at `see [Added] modal` / `see [Cart] page` / `see [Category Products] page` with no data assertion.
+- Brand filter covered only as navigation (must assert products belong to the brand).
+
+**Balance:** cover all the above (deep) BEFORE expanding subscription / UI-presence / extra validation edge cases. Do not over-invest in subscription while cart/detail/filter correctness are shallow.
+
 #### Tier 1 guard — minimum before writing scenarios
 
 | Spec section | Minimum requirement | Tag |