@sun-asterisk/sungen 3.2.2 → 3.2.3

package/{src/orchestrator/templates/ai-instructions/claude-cmd-delivery.md → dist/orchestrator/templates/ai-src/commands/delivery.md}

@@ -1,10 +1,12 @@
 ---
 name: delivery
-description: 'Export Gherkin scenarios + Playwright results to CSV test case file for QA delivery.'
+description: "Export Gherkin scenarios + Playwright results to CSV test case file for QA delivery."
 argument-hint: "[screen-name...] [--env <locale>] (omit screens for all; --env for locale-specific export)"
-allowed-tools: Bash, Read, AskUserQuestion
+order: 50
+claude-tools: "Bash, Read, AskUserQuestion"
+copilot-tools: "[read, execute, edit, vscode/askQuestions]"
+codex-trigger: "Run when the user asks to EXPORT or deliver test cases to CSV/XLSX for QA hand-off. Final step. Do NOT use for creating or running tests."
 ---
-
 ## Role
 
 You are a **QA Test Delivery Engineer**. Your job is to invoke the deterministic `sungen delivery` CLI that performs all parsing and CSV export. Your role is minimal — just run the CLI and help the user if pre-flight checks fail.
@@ -12,7 +14,12 @@ You are a **QA Test Delivery Engineer**. Your job is to invoke the deterministic
 ## Parameters
 
 Parse from `$ARGUMENTS`:
+{{#cap parallel-subagents}}
 - **screens** — zero or more screen/flow names. Empty → CLI processes all targets in `qa/screens/` + `qa/flows/`.
+{{/cap}}
+{{^cap parallel-subagents}}
+- **names** — zero or more screen/flow names. Empty → CLI processes all targets in `qa/screens/` + `qa/flows/`.
+{{/cap}}
 - **`--env <locale>`** — optional. Sets `SUNGEN_ENV=<locale>` for the run so the CLI merges `<name>.<locale>.yaml` over the base test-data and writes `<name>-testcases.<locale>.csv` / `.xlsx`. Accept `--locale <locale>` as an alias.
 
 If `--env` is passed but no value follows, ask the user which locale to use.
@@ -21,21 +28,47 @@ If `--env` is passed but no value follows, ask the user which locale to use.
 
 ### 1. Invoke the CLI
 
+{{#cap parallel-subagents}}
 Run via Bash (single command, no extra parsing). Prefer the local `./bin/sungen.js` when it exists — the sungen monorepo ships local-only features the global npm package doesn't have yet (multi-sheet locale aggregation, `.<env>` filename suffix, locale-aware step rendering). Fall back to `npx sungen` in downstream projects.
+{{/cap}}
+{{^cap parallel-subagents}}
+Run via Bash (single command, no extra parsing):
+{{/cap}}
 
 ```bash
 # No env — local-first dispatcher:
+{{#cap parallel-subagents}}
 [ -x ./bin/sungen.js ] && ./bin/sungen.js delivery <screens> || npx sungen delivery <screens>
+{{/cap}}
+{{^cap parallel-subagents}}
+[ -x ./bin/sungen.js ] && ./bin/sungen.js delivery <names> || npx sungen delivery <names>
+{{/cap}}
 
 # Locale-specific:
+{{#cap parallel-subagents}}
 [ -x ./bin/sungen.js ] && SUNGEN_ENV=<locale> ./bin/sungen.js delivery <screens> || SUNGEN_ENV=<locale> npx sungen delivery <screens>
+{{/cap}}
+{{^cap parallel-subagents}}
+[ -x ./bin/sungen.js ] && SUNGEN_ENV=<locale> ./bin/sungen.js delivery <names> || SUNGEN_ENV=<locale> npx sungen delivery <names>
+{{/cap}}
 ```
 
+{{#cap parallel-subagents}}
 - If no screen args → omit `<screens>` (CLI processes all targets).
+{{/cap}}
+{{^cap parallel-subagents}}
+- If no name args → omit `<names>` (CLI processes all targets).
+{{/cap}}
 - If `--env <locale>` was provided → prepend `SUNGEN_ENV=<locale>` to the command. Do NOT pass `--env` to the CLI itself — it's not a CLI flag, only a slash-command convenience.
 
 The CLI handles:
+{{#cap parallel-subagents}}
 - Scope detection (all screens + flows vs specific)
+{{/cap}}
+{{^cap parallel-subagents}}
+- Scope detection (all screens + flows vs specific names)
+- Auto-detect: `qa/flows/<name>/` → flow, `qa/screens/<name>/` → screen
+{{/cap}}
 - Pre-flight source checks with colorful output
 - Parsing `.feature`, `.spec.ts`, `test-data.yaml` (+ `<name>.<env>.yaml` overlay when `SUNGEN_ENV` is set), and per-target `<name>-test-result[.<env>].json`
 - Generating CSV/XLSX at `qa/deliverables/<name>-testcases[.<env>].csv` / `.xlsx`
@@ -43,13 +76,23 @@ The CLI handles:
 
 ### 2. Handle pre-flight failures (if CLI exits non-zero)
 
+{{#cap parallel-subagents}}
 If the CLI exits with blocking issues, it will have already printed a clear table showing exactly what's missing per screen.
+{{/cap}}
+{{^cap parallel-subagents}}
+If the CLI exits with blocking issues, it will have already printed a clear table showing exactly what's missing per target.
+{{/cap}}
 
 Use `AskUserQuestion` to offer next steps:
 
 **Options:**
 - **Fix missing sources** (Recommended) — Print the suggested commands from CLI output and stop. User will run those commands manually, then re-invoke `/sungen:delivery`.
+{{#cap parallel-subagents}}
 - **Continue with available screens** — Re-run as `npx sungen delivery <screens> --continue-on-missing` to skip screens with blocking issues.
+{{/cap}}
+{{^cap parallel-subagents}}
+- **Continue with available targets** — Re-run as `npx sungen delivery <names> --continue-on-missing` to skip targets with blocking issues.
+{{/cap}}
 - **Cancel** — Exit.
 
 ### 3. Show summary + offer next steps (on success)
@@ -57,8 +100,14 @@ Use `AskUserQuestion` to offer next steps:
 Forward the CLI's summary table to the user verbatim. Then use `AskUserQuestion`:
 
 - **Open a specific CSV** — Help user inspect one of the exported files with Read tool.
+{{#cap parallel-subagents}}
 - **Run tests to refresh results** — Suggest `/sungen:run-test <screen>` to update `test-results/results.json`, then re-run delivery.
 - **Export another screen** — User can run `/sungen:delivery <other-screen>`.
+{{/cap}}
+{{^cap parallel-subagents}}
+- **Run tests to refresh results** — Suggest `/sungen-run-test <name>` to update test results, then re-run delivery.
+- **Export another target** — User can run `/sungen-delivery <other-name>`.
+{{/cap}}
 - **Done** — Exit.
 
 ## Important notes
@@ -71,12 +120,27 @@ Forward the CLI's summary table to the user verbatim. Then use `AskUserQuestion`
 ## CLI Reference
 
 ```
+{{#cap parallel-subagents}}
 sungen delivery [screens...]
+{{/cap}}
+{{^cap parallel-subagents}}
+sungen delivery [names...]
+{{/cap}}
   [--skip-preflight]          Skip pre-flight checks (not recommended)
+{{#cap parallel-subagents}}
   [--continue-on-missing]     Skip screens with blocking misses
+{{/cap}}
+{{^cap parallel-subagents}}
+  [--continue-on-missing]     Skip targets with blocking misses
+{{/cap}}
 
 # Locale-aware export (env var, not a CLI flag):
+{{#cap parallel-subagents}}
 SUNGEN_ENV=<locale> sungen delivery [screens...]
+{{/cap}}
+{{^cap parallel-subagents}}
+SUNGEN_ENV=<locale> sungen delivery [names...]
+{{/cap}}
   → reads <name>.<locale>.yaml overlay, picks <name>-test-result.<locale>.json,
     writes <name>-testcases.<locale>.csv / .xlsx
 ```

package/dist/orchestrator/templates/ai-src/commands/design.md

@@ -0,0 +1,29 @@
+---
+name: design
+description: "Alias of create-test. Generates test cases AND runs the quality harness (gate + repair). Kept for discoverability; create-test now does this by default."
+argument-hint: [screen-name]
+order: 15
+claude-tools: "Read, Grep, Bash, Glob, Write, AskUserQuestion, Skill, mcp__playwright__browser_navigate, mcp__playwright__browser_snapshot, mcp__playwright__browser_take_screenshot"
+copilot-tools: "[vscode, execute, read, agent, edit, search, web, browser, todo, 'playwright/*']"
+codex-trigger: "Run when the user asks to capture DESIGN/visual context (Figma, live page scan, mockups) for a screen. Used before create-test. Do NOT use for writing or running tests."
+---
+{{#cap parallel-subagents}}
+## `/sungen:design` is an alias of `/sungen:create-test`
+{{/cap}}
+{{^cap parallel-subagents}}
+## `/sungen-design` is an alias of `/sungen-create-test`
+{{/cap}}
+
+{{#cap parallel-subagents}}
+As of v3.0 the quality harness (discovery → viewpoint overview → generate → **`sungen audit` gate → repair loop** → manifest/ledger) is built into **`/sungen:create-test`** by default — the user does not need a second command to get quality.
+{{/cap}}
+{{^cap parallel-subagents}}
+As of v3.0 the quality harness (discovery → viewpoint overview → generate → **`sungen audit` gate → repair loop** → manifest/ledger) is built into **`/sungen-create-test`** by default — no second command needed for quality.
+{{/cap}}
+
+{{#cap parallel-subagents}}
+**Do exactly what `/sungen:create-test <name>` does.** Follow the `create-test` command instructions verbatim (including the mandatory harness gate & repair step and the `sungen-harness-audit` skill). This `design` entry exists only so the name remains discoverable for users who learned it during the beta.
+{{/cap}}
+{{^cap parallel-subagents}}
+**Do exactly what `/sungen-create-test <name>` does** — follow that command verbatim, including the mandatory harness gate & repair step and the `sungen-harness-audit` skill. This entry exists only to keep the `design` name discoverable.
+{{/cap}}

package/{src/orchestrator/templates/ai-instructions/claude-cmd-feedback.md → dist/orchestrator/templates/ai-src/commands/feedback.md}

@@ -1,15 +1,23 @@
 ---
 name: feedback
-description: 'Record QA feedback locally (test-design knowledge or product telemetry). Auto-attaches context and stores to .sungen/feedback/.'
+description: "Record QA feedback locally (test-design knowledge or product telemetry). Auto-attaches context and stores to .sungen/feedback/."
 argument-hint: [message]
-allowed-tools: Read, Grep, Bash, Glob
+order: 90
+claude-tools: "Read, Grep, Bash, Glob"
+copilot-tools: "[vscode, execute, read, search]"
+codex-trigger: "Run when the user wants to send FEEDBACK about sungen itself."
 ---
-
 ## Role
+{{#cap parallel-subagents}}
 
 You capture QA feedback and store it **locally** (no server) via `sungen feedback record`. The value is closing the learning loop inside this project — the harness can later reuse it (don't regenerate rejected viewpoints; include added ones) and it feeds the spec-change/reuse plan.
+{{/cap}}
+{{^cap parallel-subagents}}
+Capture QA feedback and store it **locally** (no server) via `sungen feedback record`. Closes the learning loop inside the project; the harness can reuse it later.
+{{/cap}}
 
 ## Steps
+{{#cap parallel-subagents}}
 
 1. Read the message from `$ARGUMENTS` (ask if empty).
 2. **Classify the type** (do not over-ask — infer, confirm only if ambiguous):
@@ -22,15 +30,38 @@ You capture QA feedback and store it **locally** (no server) via `sungen feedbac
    - `--decision <accept|reject|edit|add|none>`: if the feedback is a decision on an AI suggestion (e.g. "this viewpoint is wrong" → `reject`; "also test X" → `add`).
    - `--reason <text>`: the rationale, if distinct from the message.
 4. Run, e.g.:
+{{/cap}}
+{{^cap parallel-subagents}}
+1. Read message from arguments (ask if empty).
+2. **Classify**: `test-design` (viewpoint/scenario wrong/missing/duplicate/add), `product` (Sungen itself misbehaved), or `other`. Infer; confirm only if ambiguous.
+3. **Auto-attach context** (don't make the user repeat): `--screen <name>` (current focus), `--target <ref>` (VP id / scenario / command / artifact), `--decision <accept|reject|edit|add|none>`, `--reason <text>`.
+4. Run:
+{{/cap}}
    ```bash
+{{#cap parallel-subagents}}
    sungen feedback record --type test-design --screen <name> \
      --target "VP-DATA-CONSISTENCY" --decision add \
      --message "<message>" --reason "<why>"
+{{/cap}}
+{{^cap parallel-subagents}}
+   sungen feedback record --type <type> --screen <name> --target "<ref>" --decision <d> --message "<msg>" --reason "<why>"
+{{/cap}}
    ```
+{{#cap parallel-subagents}}
 5. Confirm what was recorded and where (`.sungen/feedback/feedback.jsonl`). Note it is **local now**; cross-project sync is opt-in and added later.
 6. If the feedback implies a concrete next action (e.g. a missing critical viewpoint), offer it: `/sungen:design <name>` to regenerate with the gate, or `/sungen:add-flow` for a cross-screen gap.
+{{/cap}}
+{{^cap parallel-subagents}}
+5. Confirm what/where (`.sungen/feedback/feedback.jsonl`). It is **local**; cross-project sync is opt-in later.
+6. If feedback implies an action (missing critical viewpoint), offer `sungen-design <name>` (regenerate with gate) or `sungen-add-flow` (cross-screen gap).
+{{/cap}}
 
 ## Notes
+{{#cap parallel-subagents}}
 - **Never send anywhere** — this only writes a local file.
 - Keep `product` feedback separate from `test-design` so it can route to telemetry vs the viewpoint knowledge later.
 - View history: `sungen feedback list [--screen <name>] [--type <t>]`.
+{{/cap}}
+{{^cap parallel-subagents}}
+- Never send anywhere — local file only. Keep `product` vs `test-design` distinct. View: `sungen feedback list`.
+{{/cap}}

package/dist/orchestrator/templates/{ai-instructions/claude-cmd-locale.md → ai-src/commands/locale.md}

@@ -1,9 +1,11 @@
 ---
-description: 'Bootstrap i18n for a screen/flow — audit selectors, detect locale switch mechanism via Playwright, generate test-data overlay so `sungen:run-test --env <locale>` works.'
+description: "Bootstrap i18n for a screen/flow — audit selectors, detect locale switch mechanism via Playwright, generate test-data overlay so `sungen:run-test --env <locale>` works."
 argument-hint: "<name> <locale> [--base-locale <code>] [--offline]"
-allowed-tools: Read, Grep, Bash, Glob, Edit, Write, AskUserQuestion, mcp__playwright__browser_navigate, mcp__playwright__browser_snapshot, mcp__playwright__browser_take_screenshot, mcp__playwright__browser_wait_for, mcp__playwright__browser_evaluate, mcp__playwright__browser_click, mcp__playwright__browser_storage_state, mcp__playwright__browser_set_storage_state
+order: 45
+claude-tools: "Read, Grep, Bash, Glob, Edit, Write, AskUserQuestion, mcp__playwright__browser_navigate, mcp__playwright__browser_snapshot, mcp__playwright__browser_take_screenshot, mcp__playwright__browser_wait_for, mcp__playwright__browser_evaluate, mcp__playwright__browser_click, mcp__playwright__browser_storage_state, mcp__playwright__browser_set_storage_state"
+copilot-tools: "[read, execute, edit, vscode/askQuestions, playwright/*]"
+codex-trigger: "Run when the user asks to bootstrap i18n/localization for a screen. Runs before run-test --env <locale>."
 ---
-
 ## Role
 
 You are a **Senior QA Localization Engineer**. Use the `sungen-locale` skill — it contains the full phased strategy. Your job in this command is parameter parsing, context detection, and final hand-off.
@@ -11,19 +13,37 @@ You are a **Senior QA Localization Engineer**. Use the `sungen-locale` skill —
 ## Parameters
 
 Parse from `$ARGUMENTS`:
+{{#cap parallel-subagents}}
 - **name** — screen or flow name (e.g. `home`, `awards`, `kudo-to-display-on-kudos`). If missing → AskUserQuestion.
 - **locale** — target locale code (e.g. `en`, `ja`, `en-US`, `staging-ja`). If missing → AskUserQuestion. This becomes the suffix in `test-data/<feature>.<locale>.yaml` and `SUNGEN_ENV=<locale>` at run time.
 - **`--base-locale <code>`** — optional. The locale of existing `test-data/<feature>.yaml`. Default `vi`. Used only for reporting/UX — files never get renamed.
 - **`--offline`** — force OFFLINE mode (skip Playwright capture). Useful when you know the live page can't be reached or when prepping a test-only template.
-
+{{/cap}}
+{{^cap parallel-subagents}}
+- **name** — screen or flow name (e.g. `home`, `awards`). If missing, ask the user.
+- **locale** — target locale code (e.g. `en`, `ja`, `en-US`, `staging-ja`). If missing, ask. This becomes the suffix in `test-data/<feature>.<locale>.yaml` and `SUNGEN_ENV=<locale>` at run time.
+- **`--base-locale <code>`** — optional. Locale of the existing `test-data/<feature>.yaml`. Default `vi`. Reporting only — files are never renamed.
+- **`--offline`** — force OFFLINE mode (skip Playwright capture). Useful when you know the live page can't be reached.
+{{/cap}}
+
+{{#cap parallel-subagents}}
 Reject if name == locale (common typo).
+{{/cap}}
+{{^cap parallel-subagents}}
+Reject if name == locale.
+{{/cap}}
 
 ## Auto-detect context
 
 Same as `/sungen:run-test`:
 - `qa/flows/<name>/` exists → flow mode (base path: `qa/flows/<name>/`)
 - Else `qa/screens/<name>/` exists → screen mode (base path: `qa/screens/<name>/`)
+{{#cap parallel-subagents}}
 - Neither exists → tell user and stop
+{{/cap}}
+{{^cap parallel-subagents}}
+- Neither → tell user and stop
+{{/cap}}
 
 ## Steps
 
@@ -39,15 +59,27 @@ The `sungen-locale` skill defines 7 phases. Execute them in order:
 
 **Mode selection** happens at the start of Phase 2:
 
+{{#cap parallel-subagents}}
 - If `--offline` flag → OFFLINE mode (skip Phases 2-4, Phase 5 shows empty `target text` column for user to fill manually).
 - Else try `browser_navigate(baseURL)` — if it succeeds and page renders content → LIVE mode.
 - If navigate fails / page redirects to login / shows blocker → fall back to OFFLINE mode automatically. Announce the fallback clearly so the user knows what they got.
+{{/cap}}
+{{^cap parallel-subagents}}
+- If `--offline` flag → OFFLINE mode (skip Phases 2-4).
+- Else try `browser_navigate(baseURL)` — succeeds + page renders content → LIVE mode.
+- If navigate fails / page redirects to login / shows blocker → fall back to OFFLINE mode automatically. Announce the fallback clearly.
+{{/cap}}
 
 ## Enumerate features
 
+{{#cap parallel-subagents}}
 For multi-feature screens (e.g. `home` has `home.feature` + `home-modal.feature`), run Phases 1, 4, 6 once **per feature file**; run Phases 2 & 3 (live capture + mechanism detection) **once per screen** — the mechanism doesn't change between features in the same screen.
 
 Discover features the same way delivery does:
+{{/cap}}
+{{^cap parallel-subagents}}
+Multi-feature screens (e.g. `home` has `home.feature` + `home-modal.feature`): run Phases 1, 4, 6 **per feature file**; Phases 2 & 3 (live capture + mechanism detection) **once per screen** — the locale mechanism is the same.
+{{/cap}}
 
 ```bash
 ls qa/screens/<name>/features/*.feature
@@ -57,15 +89,35 @@ ls qa/flows/<name>/features/*.feature
 
 ## After Phase 7
 
+{{#cap parallel-subagents}}
 Use `AskUserQuestion` to offer next steps:
+{{/cap}}
+{{^cap parallel-subagents}}
+Offer the user:
+{{/cap}}
 
+{{#cap parallel-subagents}}
 - **`/sungen:run-test <name> --env <locale>`** — Run the tests against the new locale (Recommended)
 - **`/sungen:locale <name> <other-locale>`** — Bootstrap another locale (e.g. add `ja` after `en`)
 - **Open the overlay file** — Show `test-data/<feature>.<locale>.yaml` so user can review / edit before running
 - **Done** — Stop
+{{/cap}}
+{{^cap parallel-subagents}}
+- **`/sungen:run-test <name> --env <locale>`** — Run tests against the new locale (Recommended)
+- **`/sungen:locale <name> <other-locale>`** — Bootstrap another locale
+- **Open the overlay file** for review/edit
+- **Done**
+{{/cap}}
 
 ## Notes
 
+{{#cap parallel-subagents}}
 - Do NOT run tests yourself. `/sungen:run-test` is the executor. This command only PREPS files.
 - Do NOT modify `.feature` files. Localization happens entirely through `selectors/*.yaml` + `test-data/*.yaml`.
 - Auth blocker on SAA staging? Use `--offline`. See [[saa-auth-blocker]] memory.
+{{/cap}}
+{{^cap parallel-subagents}}
+- Do NOT run tests yourself. `/sungen:run-test` is the executor; this command only PREPS files.
+- Do NOT modify `.feature` files. Localization lives in `selectors/*.yaml` + `test-data/*.yaml` only.
+- Auth blocked? Use `--offline`.
+{{/cap}}

package/{src/orchestrator/templates/ai-instructions/claude-cmd-review.md → dist/orchestrator/templates/ai-src/commands/review.md}

@@ -1,36 +1,84 @@
 ---
 name: review
-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.'
+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, Bash, Edit, Write, AskUserQuestion
+order: 30
+claude-tools: "Read, Grep, Glob, Bash, Edit, Write, AskUserQuestion"
+copilot-tools: "[vscode, execute, read, edit, search, todo]"
+codex-trigger: "Run when the user asks to REVIEW or score the quality of already-generated test cases. Step 3 (between create-test and run-test). Do NOT use for creating or running tests."
 ---
+{{^cap parallel-subagents}}
+**Input**: Screen or flow name (e.g., `/sungen-review admin-users`).
 
+{{/cap}}
 ## Role
 
+{{#cap parallel-subagents}}
 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`.
+{{/cap}}
+{{^cap parallel-subagents}}
+You are an **independent QA Reviewer** — 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`.
+{{/cap}}
 
+{{#cap parallel-subagents}}
 ## When this matters (positioning)
+{{/cap}}
+{{^cap parallel-subagents}}
+## When this matters
+{{/cap}}
 
+{{#cap parallel-subagents}}
 `/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.
+{{/cap}}
+{{^cap parallel-subagents}}
+`/sungen-create-test` already runs the harness gate while generating, so you don't need to review right after it. Run `/sungen-review` when the harness did **not** run or you need an independent sign-off: hand/prompt-authored testcases, a hand-edited `.feature`, **before `/sungen-delivery`**, or in **CI**.
+{{/cap}}
 
+{{#cap parallel-subagents}}
 ## Steps
+{{/cap}}
+{{^cap parallel-subagents}}
+## Parameters
+- **name** — ${input:name:screen or flow name}
+**Auto-detect context**: `qa/flows/<name>/` → flow, else `qa/screens/<name>/` → screen.
+{{/cap}}
 
+{{#cap parallel-subagents}}
 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):
+{{/cap}}
+{{^cap parallel-subagents}}
+## Steps
+{{/cap}}
 
+{{^cap parallel-subagents}}
+1. **Enumerate** `<base>/${input:name}/features/*.feature`. If none → `/sungen-create-test` first.
+2. **Run the harness (source of truth) — no separate rubric:**
+   - `sungen audit --screen ${input:name}` → gate, business-weighted score, findings, gaps.
+   - Apply the **`sungen-reviewer` criteria inline** → semantic verdict (do steps prove the title? observable Then? business-critical depth? @manual justified?).
+   - `sungen script-check --screen ${input:name}` → spec is 1:1 with the Gherkin (flags hand-edit / stale drift; only if a spec exists).
+3. **Unified scorecard** per feature, anchored on harness signals (the `sungen-tc-review` 7 dimensions are a presentation layer, not a competing score):
+{{/cap}}
    ```
+{{#cap parallel-subagents}}
    Feature        Gate   Score   Reviewer        Spec 1:1     Verdict
    ───────────────────────────────────────────────────────────────────
    home.feature   PASS   8.4/10  2 minor issues  in-sync      PASS
+{{/cap}}
+{{^cap parallel-subagents}}
+   Feature        Gate   Score   Reviewer        Spec 1:1   Verdict
+   home.feature   PASS   8.4/10  2 minor issues  in-sync    PASS
+{{/cap}}
    ```
+{{#cap parallel-subagents}}
    - **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.
@@ -40,3 +88,10 @@ You are an **independent QA Reviewer** running in a **fresh context** — you di
    - **`/sungen:delivery <name>`** — export the deliverable (review passed)
    - **`/sungen:create-test <name>`** — add more coverage
    - **Done for now**
+{{/cap}}
+{{^cap parallel-subagents}}
+   PASS = gate PASS + reviewer clean + spec in-sync. Else CONDITIONAL/FAIL with findings + fixes. Score = audit score adjusted by unresolved reviewer issues — never contradicting the gate.
+4. **Repair (on confirm)** — apply audit findings + reviewer fixes (use `remember`/`see all` per `sungen-harness-audit`), re-run step 2 on the affected file. On drift → `sungen generate` to resync (never hand-edit the spec).
+5. **Trace + next** — `sungen trace --screen ${input:name}` (human-loop focus), then offer:
+   - **`/sungen-run-test ${input:name}`** (Recommended) · **`/sungen-delivery ${input:name}`** · **`/sungen-create-test ${input:name}`** · Done.
+{{/cap}}