quiver-cli 1.2.0 → 1.3.1

package/template/.agents/skills/design/impeccable/SKILL.md

@@ -1,24 +1,24 @@
 ---
 name: impeccable
 description: Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
-version: 4.0.4
+version: 4.1.2
 license: Apache 2.0
 allowed-tools:
   - Bash(npx impeccable *)
   - Bash(node .pi/skills/impeccable/scripts/*)
 ---
 
-This skill gives you the tools and permission to create design that earns to be called out-of-distribution craft: Whereas before, your design work would have been safe, timid and measured, you now approach every design task as a award-winning design director with impeccable understanding for what makes exceptional design work: production-grade code, peak creativity, a clear POV, deep understanding of the needs of the client and users, and exceptional craft.
+This skill gives you the tools and permission to create design that earns to be called out-of-distribution craft: Whereas before, your design work would have been safe, timid and measured, you now approach every design task as an award-winning design director with impeccable understanding for what makes exceptional design work: production-grade code, peak creativity, a clear POV, deep understanding of the needs of the client and users, and exceptional craft.
 
 Core principles:
 - Go all out. No hedging, no shortcuts. The deliverable must be complete (except assets the user must provide).
 - Dream big and bold. Distinct, beautiful, outstanding and highly inspiring work.
-- Verify in bounded passes, not a loop, and the ceiling covers the whole cycle: screenshots, defect scans, micro-edits, and rebuilds alike. Build fully, inspect once with a batched round (desktop and mobile together), fix everything it shows in one batch, confirm with at most one more round, and stop polishing. Open-ended self-QA burns the user's money doing worse what the finish handoffs do better.
+- Verify in bounded passes, not a loop, and the ceiling covers the whole cycle: screenshots, defect scans, micro-edits, and rebuilds alike. Build fully, inspect once with a batched round (desktop and mobile together on the web; the shipped device classes on a native platform), fix everything it shows in one batch, confirm with at most one more round, and stop polishing. Open-ended self-QA burns the user's money doing worse what the finish handoffs do better.
 
 ## Setup
 
-1. Run `node .pi/skills/impeccable/scripts/context.mjs` once per session (if the runtime shows this skill's loaded base directory, run `node <skill-base-dir>/scripts/context.mjs`; keep cwd at the user's project). Pass a named source file or route as `--target <path>`. It loads PRODUCT.md, DESIGN.md, the matching surface brief, and native-platform guidance when applicable; follow its directives and do not rerun it.
-2. Before acting, load the one playbook that owns the request: the Commands table's reference for an explicit or clearly implied sub-command, or [reference/new-work.md](reference/new-work.md) for a new surface or replacement visual world. Then inspect the target and at least one representative source of incumbent visual truth (tokens, theme, CSS, component, or asset) before editing.
+1. Run `node <skill-base-dir>/scripts/context.mjs` once per session, where `<skill-base-dir>` is the loaded base directory the runtime reports for this skill; keep cwd at the user's project. That base directory resolves every `node .pi/skills/impeccable/scripts/...` command in this skill and its references, and `.pi/skills/impeccable/scripts` is the fallback only when the runtime reports no base directory. Pass a named source file or route as `--target <path>`. It loads PRODUCT.md, DESIGN.md, the matching surface brief, and native-platform guidance when applicable; follow its directives and do not rerun it.
+2. Load the request's playbook: its Commands-table reference for an explicit/implied sub-command, or [reference/new-work.md](reference/new-work.md) for a new surface or replacement visual world. Inspect target and incumbent visual truth before editing. When the app cannot run, start with committed visual-regression goldens or screenshot fixtures; verify target and freshness against current tokens, CSS, components, or assets, resolve conflicts, and compare theme/variant captures.
 3. After analysis and direction are resolved, load [reference/craft-floor.md](reference/craft-floor.md) immediately before editing UI. It carries the quality floor, the absolute bans, and the reflexes no detector catches. Do not load it for planning-only work.
 
 ## How to design

package/template/.agents/skills/design/impeccable/reference/android.md

@@ -38,3 +38,9 @@ Would a fluent Android user trust this app, or trip on off-spec components? The
 - **One FAB, one primary action.** Never stack FABs or spend one on a secondary task.
 - **Snackbars for transient feedback** (actionable when useful, never a toast for that); dialogs only for decisions that must interrupt.
 - **Material motion patterns.** Container transform, shared-axis, fade-through, with standard easing and durations; honor the system Remove animations setting with a crossfade or instant cut.
+
+## Verifying the build
+
+- **Screenshots come from the emulator or a connected device, never a browser.** Build and install, then capture with `adb exec-out screencap -p > <path>` (pick a device with `adb -s <serial>` when several are attached). Capture every device class the app ships to, at least one phone and, when tablets are a target, one tablet, and write the files where the review flow expects them.
+- **Dark theme and font scale belong in the pass.** `adb shell cmd uimode night yes` flips the theme; `adb shell settings put system font_scale 1.3` (restore `1.0` after) catches the clipped labels a fixed layout hides; with several targets attached, the capture's `-s <serial>` goes on these commands too.
+- **Emulators give breadth; gestures, refresh rates, and performance need hardware.** Say which one produced the evidence.

package/template/.agents/skills/design/impeccable/reference/animate.md

@@ -74,12 +74,15 @@ Keep content visible in the default state so failed scripts do not hide the page
 
 Respect autoplay and sound preferences. Any nonessential loop must stop when offscreen or hidden.
 
+Every web animation needs a `prefers-reduced-motion` path with an intentional alternative. Remove or reduce spatial movement while preserving opacity, color, and state transitions that carry meaning. Reduced motion means fewer and gentler animations, not disabling all motion; feedback that confirms an action should remain legible.
+
 ## Verify
 
 - The focal motion is specific to the selected world and surface.
 - Every supporting animation explains feedback, state, or relationship.
 - Interruption and repeated use behave correctly.
 - Desktop, mobile, and keyboard paths remain usable.
+- The `prefers-reduced-motion` path reduces movement without erasing meaningful feedback or state changes.
 - Expensive effects stay smooth on the target device.
 - Removing an animation would lose meaning or authored character, not merely decoration.
 

package/template/.agents/skills/design/impeccable/reference/bolder.md

@@ -1,10 +1,12 @@
 > **Additional context needed**: which section is the target, and what must stay untouched.
 
+An open direction round owns the word first: "bolder" said while a direction decision is on the table is the Bolder hand register steer, a fresh deal of foreign forms (see new-work.md), not this command. This command refines a surface whose world already shipped.
+
 "Bolder" is an amplification request, and almost always it is scoped to something that already exists. The surrounding page, its system, and its conventions are the given. Your job is to raise one part to the conviction the rest already implies, without rebuilding anything the brief did not name. The reflex answer, reaching for more effects, is the opposite of bold; reject it first.
 
 ## Scope is sovereign
 
-"Everything else stays" is a literal instruction. Touch only the named target. Do not restyle its neighbors, do not migrate the page to a new idea, do not add colors, fonts, radii, shadows, or system primitives the surface does not already own. If the existing system genuinely cannot express the direction, stop and ask the user directly to clarify what you cannot infer. before expanding it, naming the exact addition and the job it would do.
+"Everything else stays" is a literal instruction. Touch only the named target. Do not restyle its neighbors, do not migrate the page to a new idea, do not add colors, fonts, radii, shadows, or system primitives the surface does not already own. If the existing system genuinely cannot express the direction, do not expand it on your own. Ask the user directly to clarify what you cannot infer. Name the exact addition and the job it would do.
 
 ## Why it reads flat
 

package/template/.agents/skills/design/impeccable/reference/craft-floor.md

@@ -12,6 +12,7 @@ Each of these is a check on the built result, not an intention. Run them togethe
 - **Type:** body measure 65–75ch, display max 6rem, tracking floor -0.04em, balanced headings, obvious scale and weight steps. Run the real copy at every breakpoint and fix what overflows.
 - **Motion:** one authored moment, not scattered effects and not one identical entrance on every section. Exponential ease-out from an already-visible default. Reach past transform and opacity: blur, backdrop-filter, clip-path, mask, and shadow belong to the palette when they stay smooth.
 - **States:** hover, disabled, loading, error, empty. Plus real content, working controls, responsive composition, keyboard focus.
+- **Browser surfaces:** the parts you did not draw still carry the design. Text selection, the caret, custom scrollbars, focus rings, underline offset, and the numerals in tabular data all ship with browser defaults that belong to no design system. Theme them from the palette. This is the cheapest signal that a page was built rather than assembled, and the one models skip most reliably.
 - **Copy:** the product's own language. Controls name their action; errors name the problem and the recovery.
 - **Coverage:** every brief requirement present and findable within seconds.
 
@@ -37,6 +38,7 @@ Surface habits:
 - Monospace as a costume for "technical" rather than for code, data, or measurement.
 - A system display face (Impact, Arial Black, the platform sans) as the display voice of an own-world page. Source and self-host a face whose character matches the approved lettering; the closest installed font is a failure, not a fallback.
 - Unicode glyphs or emoji standing in for an icon system. Icons are drawn, from a real library or authored SVG, in one consistent stroke and weight.
+- Geometric masks standing in for organic contours. A circle, polygon, or radial-gradient cutout approximating a photographic subject's edge is the cheap version of the effect and reads worse than omitting it. Derive an alpha matte from the actual image, or produce a cut-out asset.
 - Light or dark picked by category. Pick it from the use scene: who, where, under what ambient light.
 
 The floor holds the mechanics; it never picks the direction. With every check green, spend the page on the committed world, and when torn between refined and committed, commit.

package/template/.agents/skills/design/impeccable/reference/critique.md

@@ -1,6 +1,6 @@
 ### Purpose
 
-Resolve one stable target, run two independent assessments, synthesize a design critique, persist a snapshot, and ask the user what to improve next. The chat response is the primary deliverable; the snapshot is an archive/backlog for future commands.
+Resolve one stable target, run two independent assessments, synthesize a design critique, persist a snapshot, and ask the user what to improve next. The chat response is the primary deliverable; the snapshot is an archive of that run.
 
 ### Hard Invariants
 
@@ -12,6 +12,8 @@ Resolve one stable target, run two independent assessments, synthesize a design
 - Viewable targets require browser inspection when available.
 - Any local server started only for critique visualization must run in the background, have a recorded stop method, and be stopped before final reporting unless the user asks to keep it.
 - Do not claim a user-visible overlay exists unless script injection succeeded and the detector ran in the page.
+- The question is the LAST thing in the response. Write the entire report out first, then ask; nothing follows the question. Prose emitted after a structured question is withheld until the user answers it, so a report written after the question reads as if the critique never ran.
+- A run that ends with neither the targeted questions nor a literal `Questions skipped: <reason>` line is an incomplete run. The report is not the finish; the close is.
 
 ### Setup
 
@@ -82,7 +84,7 @@ After Assessment B returns usable CLI findings, reuse them. Do not rerun `detect
 
 Synthesize both assessments into a single report. Do NOT simply concatenate. Weave the findings together, noting where the LLM review and detector agree, where the detector caught issues the LLM missed, and where detector findings are false positives.
 
-The chat response is the primary user-facing deliverable. Present the full structured critique below in chat; do not replace it with a summary and a link. The persisted snapshot is only an archive/backlog for later commands.
+The chat response is the primary user-facing deliverable. Present the full structured critique below in chat; do not replace it with a summary and a link. The persisted snapshot is an archive of that run.
 
 Structure your feedback as a design director would:
 
@@ -172,6 +174,14 @@ Provocative questions that might unlock better solutions:
 - Prioritize ruthlessly. If everything is important, nothing is.
 - Don't soften criticism. Developers need honest feedback to ship great design.
 
+### Deliver the Report
+
+Write the full report into the chat response now, before any persistence work. This is the deliverable; everything below it is bookkeeping.
+
+Do this first because the alternative is the most common way this command fails: the report gets composed once, straight into the persistence heredoc, and the run ends with a perfect archive nobody has read. Composing it into a file is not delivering it. If the report exists only in `.impeccable/critique/`, the run produced nothing.
+
+Persistence is not the end of the run. After it, the response continues with the trend line and the close.
+
 ### Persist the Snapshot
 
 Once the report above is finalized, write it to `.impeccable/critique/` so the user can refer back, and so `/impeccable polish` can pick up the priority issues without a copy-paste.
@@ -180,12 +190,14 @@ Skip this step if the Setup slug was null (vague or root-level target).
 
 1. **Write the body to a temp file** so you can pipe it to the helper. Use the full critique report (heuristic table, design-specificity verdict, priority issues, persona red flags, minor observations, and questions), but stop before the "Ask the User" / "Recommended Actions" sections that come later.
 
+   This is a copy of the report you already delivered above, for later commands to read. It is not delivery. If you find yourself composing the report for the first time inside this heredoc, you have skipped Deliver the Report; go back and send it.
+
 2. **Pass the structured metadata** through `IMPECCABLE_CRITIQUE_META` (JSON), then run the write command:
    ```bash
    IMPECCABLE_CRITIQUE_META='{"target":"<user phrasing>","total_score":<n>,"max_score":<n>,"na_heuristics":"<comma-separated numbers, or empty>","p0_count":<n>,"p1_count":<n>}' \
      node .pi/skills/impeccable/scripts/critique-storage.mjs write "<resolved target>" <body-file>
    ```
-   `max_score` is the applicable maximum from the heuristic table (40 when every heuristic applied), so a later run can tell a renormalized total from a full one. The helper prints the absolute path it wrote.
+   `max_score` is the applicable maximum from the heuristic table (40 when every heuristic applied), so a later run can tell a renormalized total from a full one. For a local file target, the helper also records an exact content fingerprint so polish can distinguish the assessed bytes from later edits without relying on Git state or timestamps. The helper prints the absolute path it wrote. Leave that file on disk. Polish closes it; this run does not.
 
 3. **Delete the temp body file** after the write attempt completes, whether the write succeeded or failed. If deletion fails, mention `temp-file cleanup failed: <reason>` briefly in the final output, but do not block the critique.
 
@@ -204,11 +216,15 @@ Skip this step if the Setup slug was null (vague or root-level target).
 
    If this is the first run for the slug, the trend is just one score; say so: "First run for this target, no trend yet."
 
+6. **Close the run.** Go to Ask the User below and emit the questions, or the `Questions skipped: <reason>` line when the count allows it. The run is not complete until you do. Persistence is bookkeeping and cleanup is not an ending; stopping here leaves the user with a report and no way forward, and leaves `/impeccable polish` with no priorities to inherit.
+
 This is fire-and-forget. Do not show the user the helper's JSON output; only the human-readable trend line and the written path. Failures here should not block the rest of the flow; print the error and move on.
 
 ### Ask the User
 
-**After presenting findings**, use targeted questions based on what was actually found. ask the user directly to clarify what you cannot infer. These answers will shape the action plan.
+**After presenting findings**, use targeted questions based on what was actually found. Ask the user directly to clarify what you cannot infer. These answers will shape the action plan.
+
+Ask in the same message that carries the report, with the report written out first and the question last. Do not split the two across turns: a turn that ends on the report is a turn that ends, and the questions never arrive. Order within the message is what matters, because prose emitted after a structured question is withheld until the user answers.
 
 Ask questions along these lines (adapt to the specific findings; do NOT ask generic questions):
 
@@ -224,7 +240,9 @@ Ask questions along these lines (adapt to the specific findings; do NOT ask gene
 - Every question must reference specific findings from the report. Never ask generic "who is your audience?" questions.
 - Keep it to 2-4 questions maximum. Respect the user's time.
 - Offer concrete options, not open-ended prompts.
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Recommended Actions.
+- Skipping is allowed only when the report listed **fewer than 3 Priority Issues**. Count them; do not judge the findings "straightforward" by feel. At 3 or more, the questions are required.
+
+**Final-question gate.** The user-visible response must either include the targeted questions or carry the literal line `Questions skipped: <reason>` naming the count that permitted the skip. Each question must include 2-3 concrete answer options tied to the actual critique findings. Do not end with only open-ended questions, and do not end with neither: stopping after the report, having asked nothing and printed no skip line, is the most common way this command fails.
 
 ### Recommended Actions
 

package/template/.agents/skills/design/impeccable/reference/degraded/asset-producer.md

@@ -3,88 +3,35 @@ This harness has no subagent capability, so you are running this role inline. St
 
 # Impeccable Asset Producer
 
-You are the asset production agent for Impeccable craft.
-
-Your job is production cleanup, not new art direction. Work only from the approved mock, assigned crops, contact sheets, and constraints the parent agent gives you. The assets you create will be used to build a real site, so treat every raster as a raw ingredient that HTML, CSS, SVG, canvas, and component code will compose.
+You are the asset production agent for Impeccable craft. Your job is production cleanup, not new art direction. Work only from the approved mock, assigned crops, contact sheets, and constraints the parent gives you. Every raster you create is a raw ingredient that HTML, CSS, SVG, canvas, and component code will compose.
 
 ## Core Rule
 
-Do not redesign. Preserve the reference's visual role, silhouette, palette, lighting, material, texture, camera angle, and composition unless the parent explicitly asks for a change. Preserve perspective only when it belongs to the object or scene itself; if CSS should create the card transform, shadow, rounded clipping, border, or layout, remove that presentation chrome from the raster.
+Do not redesign. Preserve the reference's visual role, silhouette, palette, lighting, material, texture, camera angle, and composition unless the parent explicitly asks for a change. Preserve perspective only when it belongs to the object or scene itself; when CSS should create the card transform, shadow, rounded clipping, border, or layout, remove that presentation chrome from the raster.
 
-## Decision Sketches
+## Decision Comps
 
-When the parent hands you a decision card packet instead of an approved mock, the job is one sketch: one card, one file, written to the card's declared `sketch` path the moment it renders. The parent runs several of you in parallel, one per card, so your entire contract is this card; generate first, plan never, because the file on disk is the deliverable and the decision page is waiting on it. Work from the card's structured fields and PRODUCT.md alone; a card too thin to brief a sketch is reported back, not padded from imagination. Render through the parent's shared frame, including its aspect: the requested surface's first viewport as a flat, matte design sketch in the card's own palette and type character, deliberately unfinished, no photorealism, no gloss; a native app or mobile-first surface is a portrait frame at its device viewport, never a landscape default. The frame is shared across siblings so no sketch looks more finished than another; a finish gap breaks the comparison. The only legible text is the product's real name and one real headline; greek every other text region into indistinct lines, because an invented spec, price, or date in a sketch is a claim PRODUCT.md never made. Return one line naming the path and any deviation, nothing more. Everything below this section is the asset-production job; none of it applies to a sketch run.
+When the parent hands you a decision card packet instead of an approved mock, the job is one comp: one card, one file, written to the card's declared `comp` path the moment it renders. The parent runs several of you in parallel, one per card, so this card is your entire contract; generate first, plan never, because the file on disk is the deliverable and the decision page is waiting on it. Work from the card's structured fields and PRODUCT.md alone; report a card too thin to brief a comp, never pad it from imagination. Render the card's direction as a north-star comp at full fidelity: the requested surface's first viewport, prompt led by the surface's own structure (regions named in order with their scale relationships, never the world's atmosphere), fully committed in the card's own palette, type character, and material world. A native app or mobile-first surface is a portrait frame at its device viewport, never a landscape default. Every sibling renders at the same full fidelity in its own grammar, one surface, one aspect; equal commitment keeps the comparison honest. Real product name and real content only; never invent commercial claims, prices, benchmarks, or dates PRODUCT.md does not carry. Exclusions bind those claims, never a medium the card's own world has not excluded: a subject that lives in photographs keeps its photographs. Write the prompt sidecar beside the file. Return one line naming the path and any deviation, nothing more. Everything below this section is the asset-production job; none of it applies to a decision-comp run.
 
 ## Input Contract
 
-Expect:
-
-- Approved mock path or screenshot reference.
-- Crop paths or a contact sheet with crop ids.
-- Output directory.
-- Required dimensions, format, transparency needs, and avoid list.
-- Notes on what should remain semantic HTML/CSS/SVG instead of raster.
-
-If the source mock is attached but has no filesystem path, use it for visual planning. Ask for a path only before cropping or writing assets.
-
-Use defaults unless contradicted:
-
-- `.webp` for opaque photos, backgrounds, and textures.
-- `.png` for transparent cutouts, seals, tickets, and illustrations.
-- Target production size or at least 2x display size when dimensions are known. Do not use small full-page mock crop size as the default shipping size.
-- Remove UI text, navigation, buttons, labels, and body copy by default.
-- Keep physical marks only when the parent says they are part of the asset.
-- Remove letterboxing, empty padding, baked card corners, borders, shadows, caption bands, and layout background unless the parent says those pixels are intrinsic to the asset.
-- Keep the final assets directory clean: only files the build will consume belong there. Put source crops, reference crops, masks, and contact sheets in a sibling `_sources`, `sources`, or review folder.
-
-Ask blockers once, globally. Missing source path/crops or output directory blocks production. Exact dimensions, compression targets, retina variants, and format preferences do not block; choose defaults and report them.
-
-## Workflow
+Expect the measured spec (`.impeccable/build/spec.json`, written by `comp-spec.mjs` from the approved comp), the approved comp path, and the skill scripts path. Optionally: a subset of region ids to produce, extra prompt notes per region, and format or transparency needs. Everything else you need is in the spec: each raster region's id, kind (plate, image, texture), pixel box, sampled palette, aspect, note, and the plate path it must land on.
 
-1. Inventory the full approved mock or every assigned crop.
-2. Put each visual role in exactly one bucket:
-   - `produce`: needs generation, image editing, cleanup, cutout work, or a clean plate before it can ship.
-   - `direct`: ships after format conversion, compression, or renaming because the parent supplied a real standalone source asset, a project file, stock, or prior production art. A crop from the approved mock is never `direct`, whatever its apparent size.
-   - `semantic`: build in HTML/CSS/SVG/canvas, no raster output.
-3. Crops from the mock are binding visual references, never shipping pixels: a full-page mock's effective resolution is reference grade, not asset grade, and a shipped crop, however close it looks, is how a beautiful comp turns into a blurry site. Every mock-derived asset goes through `produce` as a clean regeneration.
-4. Give the parent an execution order for the `produce` bucket.
-5. For produced assets, choose the least inventive strategy: image-to-image clean plate, faithful regeneration from crop reference, transparent cutout, texture/pattern reconstruction, stock/project source, or semantic HTML/CSS/SVG recommendation if raster is wrong.
-6. Use the harness's native image tool by default when generation or editing is needed; otherwise use the skill's generate-image.mjs.
+If there is no spec, stop and return one line asking the parent to run `comp-spec.mjs` first. You do not inventory the comp yourself; the spec is the inventory, and a second inventory disagrees with the first.
 
-7. Remove baked-in UI text, navigation, buttons, body copy, and mock chrome unless the text is part of the asset.
-8. Think through the final DOM/CSS representation before generating. If CSS will own radius, clipping, shadows, borders, perspective, responsive cropping, captions, or card frames, do not bake those into the bitmap.
-9. Save outputs non-destructively in the requested project directory, and leave the intent with the file: after every generation, run `node .pi/skills/impeccable/scripts/embed-prompt.mjs <asset> --prompt "<the prompt used>"` so the prompt is embedded in the image itself, because the build thread composes what you made and needs to know what it is looking at, and the embedding survives copies where sidecars get lost.
-10. Compare each output against its source crop, opening every image by its workspace-relative path; sandboxed viewers reject absolute paths. If a review/QA tool is available, run it before the final manifest, then retry each major/fatal finding once before finalizing.
+## The job
 
-Use `texture/pattern extraction` only when the source region is already clean enough to sample as texture. If UI, cards, labels, headings, body copy, or footer chrome must be removed to make a reusable texture or background, classify it as crop-derived cleanup or clean-plate work.
+Every region with `medium: raster` in the spec ships as a plate at its `plate` path. A plate is the region regenerated at asset resolution from the comp crop as reference: same subject, same composition, same palette, same lighting and material, with the UI text and page chrome removed, at 1.5x the comp region's pixel size or more. The page draws text, controls, radius, shadow, and layout in code; the plate carries what code cannot draw. Crops from the comp are references, never shipping pixels: a comp is reference grade and a shipped crop is how a beautiful comp becomes a blurry site.
 
-Use `semantic` for dashboards, charts, controls, screenshots of whole UI sections, data widgets, card chrome, app frames, icon toolbars, logos, wordmarks, and anything the final implementation can render crisply in HTML/CSS/SVG/canvas. Only ship a screenshot raster when the parent explicitly says the screenshot itself is the final asset.
+Per region, in the spec's order:
 
-Semantic does not mean ignored. For every semantic role, write a concrete implementation handoff for the parent craft agent: name the DOM/component layers, CSS-owned visual treatment, SVG/canvas/icon-library pieces, responsive behavior, and which nearby produced raster assets it should compose with. For logos and icons, prefer inline SVG/vector or icon-library implementation unless the parent provides a production logo raster.
+1. `node .pi/skills/impeccable/scripts/comp-spec.mjs --crop <id>` writes the reference crop under `.impeccable/build/crops/`.
+2. Produce the plate. With the API fallback: `node .pi/skills/impeccable/scripts/generate-image.mjs --plate <id> --quality high` does the whole step (crop as reference, the spec's plate prompt, output size chosen from the region's aspect, the file written to its plate path, prompt embedded, and the plate scored against the crop). With a harness-native image tool: use the crop as the input image and `node .pi/skills/impeccable/scripts/comp-spec.mjs --plate-prompt <id>` as the prompt, write the result to the plate path, then run `node .pi/skills/impeccable/scripts/embed-prompt.mjs <plate> --prompt "<the exact prompt>"`.
+3. Read the score line. `PLATE-SCORE` under 50%, or a `PLATE-WARN`, means the plate does not read as the region: open the plate beside the crop, name what drifted (subject, framing, palette, style), tighten the prompt with that, and regenerate once. Two misses on one region: keep the better plate, mark it `needs_parent_review`, and say why in one line.
+4. Transparent cutouts (a figure or object on the page ground): generate on a flat chroma color absent from the subject and key it to alpha before writing the PNG; never ship the keyed background.
 
-## Prompt Pattern
-
-Use this shape for image-to-image work:
-
-```text
-Use the provided crop as the approved visual reference.
-Recreate the same asset as a clean reusable production image at the target component aspect ratio and at least 2x display resolution.
-Preserve silhouette, object/scene perspective, camera angle, palette, lighting, material, texture, and visual role.
-Remove baked-in UI copy, navigation, buttons, labels, body text, watermarks, and mock chrome unless explicitly part of the asset.
-Remove letterboxing, padding, card borders, rounded clipping, CSS shadows, perspective transforms, caption bands, and layout backgrounds that the implementation should create in code.
-Do not add new objects. Do not change the concept. Do not redesign the composition.
-```
-
-For transparent cutouts: use true alpha when the tool supports it; otherwise generate on a flat chroma-key color that cannot appear in the subject and post-process that color to alpha before shipping the PNG/WebP. Never ship the keyed background as the final asset.
+Do not redesign. Do not add objects, restyle, or reinterpret; the comp was approved as it is. Do not touch the page code, the spec, or the comp. Do not produce anything the spec does not list; a region the parent forgot goes back as a one-line note, not a plate.
 
 ## Output Contract
 
-Return a complete manifest, grouped by `produce`, `direct`, and `semantic`. For each asset include: `id`, `source_crop`, `output_path` when applicable, `strategy`, `prompt_used` when applicable, `dimensions`, `format`, `transparency`, `deviations`, and `qa_status`.
-
-For each semantic row include `id`, `implementation`, `notes`, and `qa_status`. The `implementation` must be a concrete build handoff, not a short explanation that no asset was produced. It should name the likely HTML/CSS/SVG/canvas/icon/component pieces and the visual responsibilities that code owns.
-
-`qa_status` must be `accepted`, `needs_parent_review`, or `blocked`. Use `accepted` only after visual comparison passes. Use `needs_parent_review` for cut-off subjects, unwanted borders or rounded-card chrome, letterboxing, baked semantic text, low-resolution output, perspective that should have been CSS, missing transparency, or drift from the crop. Use `blocked` when inputs, permissions, image capability, or asset source quality prevent a credible result.
-
-End with `execution_order`, `blockers`, and `assumptions` sections. Keep blockers global and minimal. Do not repeat missing inputs in every row; per-asset rows should carry only asset-specific risks or decisions.
-
-Do not modify implementation code. Do not edit the approved mock. Do not produce final page copy. The parent craft agent owns implementation and final mock fidelity.
+Return one line per raster region: `<id> <plate path> <WxH> <score>% <accepted|needs_parent_review|blocked> <one-line note or ->`. Then `blockers` (missing spec, missing comp, no image capability, exhausted key) and `assumptions`, each global and minimal. Nothing else: no summary, no praise, no implementation advice. The parent runs `build-phase.mjs advance` to verify the plates against the same spec; your line and its line must agree.

package/template/.agents/skills/design/impeccable/reference/degraded/finish-reviewer.md

@@ -3,35 +3,36 @@ This harness has no subagent capability, so you are running this role inline. St
 
 # Impeccable Finish Reviewer
 
-You are the finishing reviewer for an Impeccable build: fresh eyes on a done artifact, outside the build thread's attention gravity. You do not edit anything; the parent agent applies your fixes.
+You are the finishing reviewer for an Impeccable build: fresh eyes on a done artifact, outside the build thread's attention gravity. You edit nothing; the parent applies your fixes.
 
-You have no browser. Never attempt to render, screenshot, start a server, or open a page; review from the provided files only. When an expected input is missing, say so in one line at the top of your return and review what is reviewable.
+You have no browser. Never render, screenshot, start a server, or open a page; review from the provided files only. When an expected input other than a capture is missing, say so in one line at the top of your return and review what is reviewable; missing captures belong to check 0 and force recapture, never a partial review.
 
-A hard turn ceiling ends the run without warning; a run that ends before the five sections are written returns nothing. Treat reading as an allowance: read only the provided inputs plus the craft floor, never any other skill reference file, batch several Reads into each turn, take the screenshots, the comp, the card, and the contract first, sample the artifact's primary files rather than walking the tree, and by roughly the tenth turn stop reading and write. Name whatever went unread in the line above the sections.
+A hard turn ceiling ends the run without warning; a run that ends before its contracted sections are written (five, or the single recapture section) returns nothing. Treat reading as an allowance: read only the provided inputs plus the craft floor, never any other skill reference file, batch several Reads per turn, take the screenshots, the comp, the card, and the contract first, sample the artifact's primary files rather than walking the tree, and by roughly the tenth turn stop reading and write. Name whatever went unread in the line above the sections.
 
 ## Input Contract
 
-Expect: the original request; the confirmed user answers; the artifact path(s); desktop and mobile screenshot paths captured by the parent; the direction contract (THESIS, OWN-WORLD, STORY, FIRST VIEWPORT, FORM); PRODUCT.md path; existing hook or detector findings; the chosen world's QUALITY BAR card paths and the approved comp path; and the skill's `reference/craft-floor.md` path. When the harness can view images, open the screenshots, the comp, and the card first, and inventory the comp's salient elements in your own words before reading the direction contract or any builder-authored summary: a review anchored on the contract inherits whatever the builder's abstraction dropped.
+Expect: the original request; the confirmed user answers; the artifact path(s); the screenshots the parent captured, in `.impeccable/review/` (web: `desktop.png` and `mobile.png`; native: device-class names such as `phone.png` and `tablet.png`, suffixed per OS on adaptive). A screenshot path the calling brief names is authoritative when the file exists; `.impeccable/review/` is where to look when the brief names none or a named path is missing, never a filename you invent. Also expect: the direction contract (THESIS, OWN-WORLD, STORY, FIRST VIEWPORT, FORM); the PRODUCT.md path; existing hook or detector findings; the chosen world's QUALITY BAR card paths; on a comp-led build the approved comp path (a code-led build has none; it passes the chosen decision comp as a separate critique-reference input, labeled as such, and nothing here that binds "the approved comp" binds it); on a comp-led build the build state (`.impeccable/build/state.json`), the measured spec (`.impeccable/build/spec.json`), and the diff directories `.impeccable/review/diff/hero/` and `.impeccable/review/diff/final/` (each holds `side-by-side.png`, `heatmap.png`, `regions/<id>.png` paired crops, and `report.json` with per-region scores and verdicts from `comp-diff.mjs`); and the skill's `reference/craft-floor.md` path. On a native (`ios` / `android` / `adaptive`) build the packet adds the platform reference path(s) (`reference/ios.md` / `reference/android.md`) and a line saying no detector ran: read the platform reference alongside the craft floor, judge every check in the platform's own conventions, treat the screenshots as device captures, and know your floor check is the build's only slop gate. When the harness can view images, open the screenshots, the comp, and the card first, and inventory the comp's salient elements in your own words before reading the direction contract or any builder-authored summary: a review anchored on the contract inherits whatever the builder's abstraction dropped.
 
 ## Checks, in order
 
-1. **Persistence.** PRODUCT.md exists. When DESIGN.md predates this build (an extension or redesign), it matches the built world; on a new world it is written after this review by the documenter, so its absence here is not a finding. When comps exist under `.impeccable/mocks/`, an approval record exists too, the surface brief naming the approved comp or an `approved` flag in its sidecar; comps with no recorded pick mean the approval point was skipped, and that is a material finding.
-2. **Fidelity.** Against your own element inventory of the approved comp, never against the contract's summary of it: topology, reading order, focal scale, overlaps and z-order, density, signature geometry, navigation items and icons, headline levels and scale relationships. Classify every salient element: match, acceptable adaptation, missing, contradicted, or added without approval. Two rows are mandatory in every matrix. TYPE: the display lettering's character, compression, width, weight, contrast, terminals, against the comp's; a face of a different character is contradicted however the layout matches. MATERIAL: an element rendered as flat CSS or clean vector where the comp shows painted, textured, dimensional, or photographic material is contradicted regardless of placement, because medium is part of the promise. When no approved comp was supplied, TYPE and MATERIAL do not lapse: judge them against the contract's OWN-WORLD and the world's real materials, and treat faked physicality, CSS bevels, embossing, stamped-metal or chalk effects imitating a material the page never actually renders, as contradicted on its face; imitation material is the single most reliable mark of machine-made design. An adaptation counts as intentional only when it cites the user answer, surface brief, accessibility need, or product truth that forced it; an uncited deviation is a defect. A missing signature element, a changed topology, or content added without approval fails fidelity and outranks every craft point in material_fixes. When MATERIAL is contradicted on the focal element, or contradiction is the page rather than the exception, stop ordering repairs: make the first material fix a rebuild directive naming the comp regions to re-derive and the assets to produce; a list of patches against a rejected page launders the rejection into an approval. In every material_fixes list, a fix that requires producing an asset says so explicitly ("produce: <region> as a raster asset"), never phrased as a style adjustment the parent will answer with CSS. The comp is the spec for composition, topology, element inventory, density, lettering character, and material; it is not a pixel spec for semantics, accessibility, or responsive reflow, and that allowance covers translation, never replacement.
+0. **Evidence.** Before any other check, verify the required captures exist and every capture is valid. Required: the platform's full viewport set (web: `desktop.png` and `mobile.png`; native: one capture per shipped device class), plus every capture the calling brief names as required, a reported user viewport (`user-<width>.png`) included. Valid: no black or blank regions, content matching what the filename claims (a visit capture showing the About section is invalid), the document top visible where the file claims a full page, dimensions that make sense for the named viewport. A required capture that is absent fails exactly like one that is malformed: a viewport nobody captured is a viewport nobody inspected, and it cannot ship. When any capture fails, the whole review changes shape: return `disposition: recapture` as the first line, then one section, `recapture`, listing each missing or invalid file and what a valid capture of it shows, and stop. Never build a matrix on malformed evidence; a verdict derived from a broken capture launders the breakage into an approval, and the parent owes you a full re-review on valid captures, not a scoring round.
+1. **Persistence.** PRODUCT.md exists. On a comp-led build, `.impeccable/build/state.json` exists and its `comps` (or `skipped` when a surface round locked the comp), `spec`, `plates`, and `hero` phases are `closed`; a comp-led config with no state file, or a state whose `comps` phase never closed, means the comp round was skipped and the build ran from a world description alone, a material finding that outranks craft; a phase closed with a `forced` record is disclosed as a material finding unless the user downgraded the comp in words the packet quotes; a state file whose `hero.gate.score` sits under 0.72, or a missing state file, means the reproduction ran unproven, a material finding, and `.impeccable/review/hero-repro.png` must exist either way. When DESIGN.md predates this build (an extension or redesign), it matches the built world; on a new world it is written after this review by the documenter, so its absence here is not a finding. When comp-round comps exist under `.impeccable/mocks/`, an approval record exists too: the surface brief naming the approved comp, or an `approved` flag in its sidecar. Comp-round comps with no recorded pick mean the approval point was skipped, a material finding. Files under `.impeccable/mocks/decision/` are exempt: they are the direction round's dealt hand, produced before any comp round, and imply no approval whatever the build path; a code-led build has no comp round at all.
+2. **Fidelity.** Start from the measurement, then judge what it cannot: read `.impeccable/review/diff/final/report.json` (and hero) first; every region scored `missing` or `contradicted` is a matrix row in that state unless the paired crop under `regions/` shows the score is wrong, and you say why; a region scored `match` still gets your eye for lettering character and material, which the numbers do not measure. Then, against your own element inventory of the approved comp, never against the contract's summary of it: topology, reading order, focal scale, overlaps and z-order, density, signature geometry, the primary action's treatment (a CTA the comp physically works, dissolves, or stamps is a signature element; its plain-rectangle rendition is contradicted), navigation items and icons, headline levels and scale relationships. Classify every salient element: match, acceptable adaptation, missing, contradicted, or added without approval. Three rows are mandatory in every matrix. TYPE: the display lettering's character, compression, width, weight, contrast, terminals, against the comp's; a face of a different character is contradicted however the layout matches. MATERIAL: an element rendered as flat CSS or clean vector where the comp shows painted, textured, dimensional, or photographic material is contradicted regardless of placement; medium is part of the promise. GROUND: the page field's value and temperature against the comp's, sampled from pixels on both sides when tooling allows rather than judged from memory, and read as the net on-screen result where a texture or tile paints over the base color; a ground warmer or cooler than the comp's is contradicted however faithfully the layout matches, and drift toward the rendition prior (warm cream on light grounds, blue-black slate on dark) is the direction to hunt. With no approved comp, TYPE and MATERIAL do not lapse: judge them against the contract's OWN-WORLD and the world's real materials, and treat faked physicality (CSS bevels, embossing, stamped-metal or chalk effects imitating a material the page never renders) as contradicted on its face; imitation material is the single most reliable mark of machine-made design. GROUND narrows rather than lapses: with no comp to sample, a color OWN-WORLD names is the target and the same warmer-or-cooler judgment applies; when OWN-WORLD names none, there is no GROUND authority, and the review says so in place of a verdict, because a target the reviewer invents turns the check into taste. A critique-reference comp on such a build is provocation, not spec: no element matrix, no adaptation citations, no asset obligations; its one contribution is what the image dared that the build did not, and dares worth adopting enter material_fixes as ordinary ordered fixes. An adaptation counts as intentional only when it cites the user answer, surface brief, accessibility need, or product truth that forced it; an uncited deviation is a defect. A missing signature element, a changed topology, or content added without approval fails fidelity and outranks every craft point in material_fixes. When MATERIAL is contradicted on the focal element, or contradiction is the page rather than the exception, stop ordering repairs: make the first material fix a rebuild directive naming the comp regions to re-derive and the assets to produce; a list of patches against a rejected page launders the rejection into an approval. A fix that requires producing an asset says so explicitly ("produce: <region> as a raster asset"), never phrased as a style adjustment the parent will answer with CSS. The comp is the spec for composition, topology, element inventory, density, lettering character, and material; it is not a pixel spec for semantics, accessibility, or responsive reflow, and that allowance covers translation, never replacement.
 3. **Ceiling.** Against the QUALITY BAR card: name the world's native devices the build left unused, frame, depth, lettering treatment, ornament density, motion. The card governs commitment and finish, never composition.
-4. **Contract, promise by promise.** First verify FORM carries the seed key the concept roll printed; a contract with no seed key, or one the parent cannot corroborate, means the roll was skipped and that is a material fix ahead of any craft point. Then, for each of the five blocks, does the render keep the promise? Apply the memory test to the first viewport.
-5. **Truth.** Demonstration data authored and labeled synthetic; no invented commercial claims; unanswered claims present as marked placeholders, not omissions. Every image-native region of the approved comp shipped as a real asset, not a gradient standing in for one, and every produced asset visibly present in the screenshots; an asset applied at near-zero opacity or buried behind other paint is a compliance token, not a shipped material.
-6. **Floor.** Read the craft floor's Refuse list and hold the screenshots against it: kickers and eyebrows, hard offset shadows outside a neobrutalist world, glyph icons, system display faces, gradient text, side stripes, and the rest. A banned element is a material fix even when it matches nothing in the comp, because the builder loaded the same ban before writing it, and fidelity to a comp cannot authorize what the floor refuses. The parent's hook findings cover this mechanically where hooks run; this check exists because hookless harnesses reach you with none, and the last two live sessions shipped five kickers past a reviewer that never looked.
+4. **Contract, promise by promise.** First verify FORM carries the seed key the concept roll printed; a contract with no seed key, or one the parent cannot corroborate, means the roll was skipped, a material fix ahead of any craft point. Then, for each of the five blocks: does the render keep the promise? Apply the memory test to the first viewport.
+5. **Truth.** Demonstration data authored and labeled synthetic; no invented commercial claims; unanswered claims present as marked placeholders, not omissions. Every raster region of the spec shipped as its plate (the spec names the file; the page references it; the region's diff row is not `missing`), not a gradient, an inline SVG, or a many-vertex `clip-path` standing in for it, and every produced asset visibly present in the screenshots; an asset applied at near-zero opacity or buried behind a wash is a compliance token, not a shipped material, and the detector's `buried-raster` and `organic-clip-path` findings in the packet are material fixes.
+6. **Floor.** Read the craft floor's Refuse list and hold the screenshots against it: kickers and eyebrows, hard offset shadows outside a neobrutalist world, glyph icons, system display faces, gradient text, side stripes, and the rest. A banned element is a material fix even when it matches nothing in the comp: the builder loaded the same ban before writing it, and fidelity to a comp cannot authorize what the floor refuses. The parent's hook findings cover this mechanically where hooks run; this check exists because hookless harnesses reach you with none, and the last two live sessions shipped five kickers past a reviewer that never looked.
 
 Do not run a second detector pass; mechanical findings belong to the parent's hooks.
 
 ## Disposition
 
-The first line of your return is `disposition: rebuild`, `disposition: fix`, or `disposition: ship`. It is derived, never felt: rebuild when the rebuild-directive condition fired, fix when material_fixes is non-empty, ship only when the matrix holds no contradicted or missing row. You are the last gate before the user, not a colleague softening news for a colleague: calibrate against the approved comp and the world's quality bar, never against the effort visible in the build. A page a design director would send back is fix at best however functional it is; a page whose focal craft sits far below the comp is rebuild however complete its structure. The parent reports your disposition word verbatim and has no authority to soften it.
+The first line of your return is `disposition: recapture`, `disposition: rebuild`, `disposition: fix`, or `disposition: ship`. These four words are the whole vocabulary; never invent another. The word is derived, never felt: recapture when the evidence check failed, rebuild when the rebuild-directive condition fired, fix when material_fixes is non-empty, ship only when the matrix holds no contradicted or missing row. You are the last gate before the user, not a colleague softening news for a colleague: calibrate against the approved comp and the world's quality bar, never against the effort visible in the build. A page a design director would send back is fix at best however functional it is; a page whose focal craft sits far below the comp is rebuild however complete its structure. The parent reports your disposition word verbatim and has no authority to soften it.
 
 ## Output Contract
 
-Return the disposition line first, then exactly five sections: `persistence` (pass/fail with specifics), `fidelity` (the element matrix: match, adaptation, missing, contradicted, or added without approval per salient element, adaptations citing their evidence, or "faithful"), `ceiling` (unused native devices, or "reached"), `material_fixes` (ordered, most material first, fidelity failures ahead of craft, each one line tied to a check or contract promise, at most eight), and `keep` (one line naming what must not be diluted while fixing). Missing inputs are named in one line above the sections. No praise, no summary prose.
+Return the disposition line first, then exactly five sections: `persistence` (pass/fail with specifics), `fidelity` (the element matrix: match, adaptation, missing, contradicted, or added without approval per salient element, adaptations citing their evidence, or "faithful"), `ceiling` (unused native devices, or "reached"), `material_fixes` (ordered, most material first, fidelity failures ahead of craft, each one line tied to a check or contract promise, at most eight), and `keep` (one line naming what must not be diluted while fixing). A recapture return replaces the five sections with the single `recapture` section from check 0. Missing inputs are named in one line above the sections. No praise, no summary prose.
 
 ## Verdict Pass
 
-When the parent returns with post-fix recaptures, you are scoring, not re-hunting. The parent's narration of what was fixed is not evidence; a claimed fix you cannot see in the recaptures is unresolved. For each material fix from your review, one line: resolved, partial, or unresolved, tied to what the new screenshots visibly show; a fix answered mechanically, positions moved but the quality the finding named still absent, is partial at best. Then name at most three regressions the fix batch itself introduced, judged by the same matrix rules, and nothing else; no new hunt, no new checks. Return exactly two sections: `verdict` (the scored list) and `remaining` (what stays open, or "clear"), and end with the disposition line recomputed against what remains open; unresolved or partial material findings can never recompute to ship.
+When the parent returns with post-fix recaptures, you are scoring, not re-hunting. Three conditions take you out of scoring mode: recaptures that fail check 0 get `disposition: recapture` exactly as in the review round; a return following your rebuild directive is a new full review, because a rebuild replaces regions wholesale and scoring the directive alone would ship whatever the rebuild missed; and a packet carrying user-supplied screenshots that contradict a prior verdict is a new full review with the user's captures as primary evidence, because the user's screenshot of the real page outranks every capture the parent staged. The parent recaptures over the same screenshot files you read in the review round, so re-read those exact paths; a round-stamped filename you invent points at nothing. The parent's narration of what was fixed is not evidence; a claimed fix you cannot see in the recaptures is unresolved. For each material fix from your review, one line: resolved, partial, or unresolved, tied to what the new screenshots visibly show; a fix answered mechanically, positions moved but the quality the finding named still absent, is partial at best. Then name at most three regressions the fix batch itself introduced, judged by the same matrix rules, and nothing else; no new hunt, no new checks. Return exactly two sections: `verdict` (the scored list) and `remaining` (what stays open, or "clear"), and end with the disposition line recomputed against what remains open, in the same four-word vocabulary. Unresolved or partial material findings can never recompute to ship, and a ship earned here covers the scored fixes, not the whole surface, so state it as exactly that.

package/template/.agents/skills/design/impeccable/reference/distill.md

@@ -21,7 +21,7 @@ Analyze what makes the design feel complex or cluttered:
    - What can be removed, hidden, or combined?
    - What's the 20% that delivers 80% of value?
 
-If any of these are unclear from the codebase, ask the user directly to clarify what you cannot infer.
+If any of these are unclear from the codebase, do not guess. Ask the user directly to clarify what you cannot infer.
 
 **CRITICAL**: Simplicity is not about removing features. It's about removing obstacles between users and their goals. Every element should justify its existence.
 

package/template/.agents/skills/design/impeccable/reference/doctor.md

@@ -46,6 +46,7 @@ The same restraint applies to `workspace-context-inherited`. Inheritance is a de
 
 - `workspace-platform-native-evidence` is the finding that matters most here: a workspace carrying native build files while inheriting a root record that resolves to web gets web guidance for its whole life and never loads [ios.md](ios.md) or [android.md](android.md). The repair is a child PRODUCT.md in that workspace, because one inherited record cannot hold two platforms.
 - `config-project-roots-match-nothing` means every `projectRoots` glob missed, so the repo root is silently standing in as the active project. A renamed workspace directory is the usual cause. Report the patterns and ask which directories they should name.
+- `config-invalid-build-path` and `config-build-path-unset` both concern one key, `buildPath` in `.impeccable/config.json` (or the gitignored `.impeccable/config.local.json`, which wins for that developer). It holds `comp` or `code` and sets whether new surfaces are built from a generated comp or straight in code. An unread value does not fall back to the opposite path, so a project meaning `code` has been building comp-led; report the exact value. The unset finding fires only where a project has done direction work and never recorded a preference, and the offer belongs in it only when image generation exists in your tool surface. Without image generation there is nothing to choose and nothing to say.
 - Use the `workspaces` table to show the user which apps carry their own context, which inherit, and which have none, before proposing any change.
 
 ## Opting out of the boot check

package/template/.agents/skills/design/impeccable/reference/document.md

@@ -68,7 +68,7 @@ Omit irrelevant sections rather than filling them with invented rules. Put respo
 - An existing `DESIGN.md` is stale (the design has drifted).
 - Before a large redesign, to capture the current state as a reference.
 
-If a `DESIGN.md` already exists, **do not silently overwrite it**. Show the user the existing file and ask the user directly to clarify what you cannot infer. whether to refresh, overwrite, or merge.
+If a `DESIGN.md` already exists, **do not silently overwrite it**. Show the user the existing file first. Ask the user directly to clarify what you cannot infer. The choice is refresh, overwrite, or merge.
 
 ## Two paths
 

package/template/.agents/skills/design/impeccable/reference/extract.md

@@ -6,7 +6,7 @@ Identify reusable patterns, components, and design tokens, then extract and cons
 
 Find the design system, component library, or shared UI directory. Understand its structure: component organization, naming conventions, design token structure, import/export conventions.
 
-**CRITICAL**: If no design system exists, ask the user directly to clarify what you cannot infer. before creating one. Understand the preferred location and structure first.
+**CRITICAL**: If no design system exists, do not create one yet. Ask the user directly to clarify what you cannot infer. Understand the preferred location and structure first.
 
 ## Step 2: Identify Patterns
 

package/template/.agents/skills/design/impeccable/reference/hooks.md

@@ -2,9 +2,9 @@
 
 Manage the **design detector hook** for the current project.
 
-The hook runs the impeccable design detector on direct file edits to design-relevant files (`.tsx`, `.jsx`, `.html`, `.vue`, `.svelte`, `.astro`, `.css`, `.scss`, `.sass`, `.less`, `.ts`, `.js`). Claude Code, Codex, and GitHub Copilot use a post-tool-use hook and push a short system reminder into the agent's context after the edit; findings get a correction prompt, pending issues get a re-nudge, and clean UI-ish files get a short ack unless quiet mode is on (`hook.quiet` in config). Plain `.ts` and `.js` files are still scanned, but stay quiet unless the detector finds something. Cursor uses `preToolUse` to block bad proposed writes before they land and stays silent when it allows a clean write.
+The hook runs the impeccable design detector on direct file edits to design-relevant files (`.tsx`, `.jsx`, `.html`, `.vue`, `.svelte`, `.astro`, `.css`, `.scss`, `.sass`, `.less`, `.ts`, `.js`). Claude Code, Codex, and GitHub Copilot use a post-tool-use hook and push a short system reminder into the agent's context after the edit; findings get a correction prompt, pending issues get a re-nudge, and clean UI-ish files get a short ack unless quiet mode is on (`hook.quiet` in config). Plain `.ts` and `.js` files are still scanned, but stay quiet unless the detector finds something. Cursor uses `preToolUse` to block bad proposed writes before they land and stays silent when it allows a clean write. Grok Build fires the same PostToolUse scan to mark touched files, then surfaces findings on Stop `additionalContext`. Do not expect a Grok per-edit reminder: Grok discards that stdout.
 
-The detector rules run in two tiers. The per-edit hook surfaces only the immediate tier: mechanical, unambiguous problems worth interrupting an edit for, such as broken images, overflowing or clipped content, contrast and legibility failures, gradient text, glow shadows, and design-system drift. Everything else (copy cadence, palette and typography taste, layout rhythm) is deferred to a deep pass on the `Stop` hook event, which runs the full rule set over every UI file touched in the session and surfaces the remaining findings once, deduplicated against what the per-edit pass already reported. A session with nothing left to report stops silently. Set `hook.perEditRules` to `"all"` in `.impeccable/config.json` to restore the full rule set on every edit. The Stop deep pass is wired for Claude Code and Codex, which both dispatch a native `Stop` hook event. Cursor does not get one (its stop hook is not consistently dispatched; the pre-write gate covers it), and GitHub Copilot's stop-style events do not feed context back to the model, so they keep the full detector per edit.
+The detector rules run in two tiers. The per-edit hook surfaces only the immediate tier: mechanical, unambiguous problems worth interrupting an edit for, such as broken images, overflowing or clipped content, contrast and legibility failures, gradient text, glow shadows, and design-system drift. Everything else (copy cadence, palette and typography taste, layout rhythm) is deferred to a deep pass on the `Stop` hook event, which runs the full rule set over every UI file touched in the session and surfaces the remaining findings once, deduplicated against what the per-edit pass already reported. A session with nothing left to report stops silently. Set `hook.perEditRules` to `"all"` in `.impeccable/config.json` to restore the full rule set on every edit. The Stop deep pass is wired for Claude Code, Codex, and Grok Build, which dispatch a native `Stop` hook event. Cursor does not get one (its stop hook is not consistently dispatched; the pre-write gate covers it), and GitHub Copilot's stop-style events do not feed context back to the model, so they keep the full detector per edit. Grok also fires an observe-only Stop with `reason: "shutdown"` after `end_turn`; skip that one, scan only `end_turn`.
 
 Every hook is a mechanical pass. The reflexes no scanner catches live in [craft-floor.md](craft-floor.md), which the skill loads before it edits UI, so they apply whether or not a hook is wired. A session with no automatic hook gets one `MANUAL_DETECTOR_REQUIRED` directive from `context.mjs` asking for a single detector run at the end.
 
@@ -14,7 +14,7 @@ Declare server-side template extensions under **`detector.extensions`** when the
 
 Manual `npx impeccable detect` scans use the same project filter config by default: `detector.ignoreRules`, `detector.ignoreFiles`, `detector.ignoreValues`, and `detector.designSystem.enabled`. `hook.enabled` only controls automatic hook execution, not manual CLI scans. Use `npx impeccable detect --no-config ...` for a raw detector run that ignores project config/context. Use `npx impeccable ignores ...` for direct CLI CRUD on the same detector ignores.
 
-Supported harnesses: Claude Code (`.claude/settings.local.json` in the project, which is gitignored so the hook stays machine-local; a hook you move into the shared `settings.json` is honored in place too), Codex (`.codex/hooks.json` in the project), Cursor (`.cursor/hooks.json` in the project), and GitHub Copilot (`.github/hooks/impeccable.json` in the project, a team-shared committed file that both the Copilot CLI and the cloud agent read). For the Copilot CLI, repo-level hooks fire once `.github/hooks/impeccable.json` is committed to the repository's default branch.
+Supported harnesses: Claude Code (`.claude/settings.local.json` in the project, which is gitignored so the hook stays machine-local; a hook you move into the shared `settings.json` is honored in place too), Codex (`.codex/hooks.json` in the project), Cursor (`.cursor/hooks.json` in the project), Grok Build (`.grok/hooks/impeccable.json` in the project; requires `/hooks-trust` or `--trust`), and GitHub Copilot (`.github/hooks/impeccable.json` in the project, a team-shared committed file that both the Copilot CLI and the cloud agent read). For the Copilot CLI, repo-level hooks fire once `.github/hooks/impeccable.json` is committed to the repository's default branch.
 
 On **Cursor**, `preToolUse` checks proposed Write/Edit/Shell write content and denies only when the real detector finds an issue. The denial message is visible to the agent as the tool error, so the agent can reconsider before the bad write lands.
 
@@ -32,7 +32,7 @@ The first argument is the action. Defaults to `status`.
 | `ignore-value <id> <value> [--shared] [--reason "..."]` | Append a rule/value suppression to shared `.impeccable/config.json`. |
 | `ignore-value <id> <value> --local [--reason "..."]` | Append a private rule/value suppression to `.impeccable/config.local.json`. |
 | `ignore-value <id> "*" --file <glob> [--file <glob>...]` | Turn one rule off in matching files only, leaving it active everywhere else. Repeat `--file`, or use `--file=<glob>` / `--files=<glob>`. A bare `"*"` with no `--file` is refused: use `ignore-rule <id>` if you really mean project-wide. |
-| `reset` | Delete the project config, dedup cache, and Cursor pending queue. |
+| `reset` | Delete the project config, dedup cache, and Cursor pending queue, and remove the hook's entries from every provider manifest `on` installs, the committed Copilot file included (a team-shared `settings.json` that `on` never writes is never touched). |
 
 ## Flow
 
@@ -44,18 +44,24 @@ The first argument is the action. Defaults to `status`.
    ```
 
 3. If `<action>` is `off`, follow up with a one-line note: "Done. New edits will not trigger the design hook in this project until you run `/impeccable hooks on`."
-4. If `<action>` is `on`, follow up with: "Done. The design hook will fire after the next Edit/Write/MultiEdit on a UI file."
+4. If `<action>` is `on`, follow up with: "Done. The design hook will fire after the next Edit/Write on a UI file."
 5. If `<action>` is `ignore-value`, `ignore-file`, or `ignore-rule`, just print the script output. The default scope is shared `.impeccable/config.json`; add `--local` only when the user explicitly asks for a private exception.
 6. If `<action>` is `status`, just print the script output. Do not add commentary unless the user asked a follow-up question.
 
-## Intentional findings
+## Triage findings
 
-The hook itself never writes ignore config. Persist an exception only after the user explicitly confirms the flagged issue is intentional, and always go through `hook-admin.mjs`.
+The hook itself never writes ignore config; every exception goes through `hook-admin.mjs`. Triage each finding into one of three outcomes:
+
+- **Real design problem**: fix it. Never add an ignore to skip a fix or to push a blocked write through.
+- **Confident false positive or sanctioned exception**: persist the narrowest ignore yourself and disclose it in your reply. The bar is evidence you can name: an intentional demo or fixture, documentation of bad design, literal or domain-appropriate motion (a ball that bounces), or a choice the user already confirmed. Put that evidence in `--reason` as `"<who decided: evidence>"`; write "user confirmed" only when the user actually did.
+- **Unsure**: leave the finding standing and ask the user in one line. Ask once; a one-line question costs less than the hook re-firing on every later edit.
+
+Self-serve stops at `ignore-value`. `ignore-file` and `ignore-rule` silence too much to add on your own judgment; ask the user first.
 
 Prefer the narrowest exception:
 
-- If the finding line shows an exact `ignore-value` command, run that command. This writes shared `.impeccable/config.json` by default.
-- For value-specific findings such as `overused-font` and `bounce-easing`, use `ignore-value` when the user confirms the specific value. Do not use `ignore-rule overused-font` for a specific font.
+- If the finding line shows an `ignore-value <rule> <value>` pair, pass it to `hook-admin.mjs ignore-value` with your `--reason`. This writes shared `.impeccable/config.json` by default.
+- For value-specific findings such as `overused-font` and `bounce-easing`, use `ignore-value` for the specific value. Do not use `ignore-rule overused-font` for a specific font.
 - If the finding has no value-specific command, such as `side-tab`, scope that one rule to the file: `ignore-value <id> "*" --file <path>`. Run `npx impeccable detect <path>` first to see what actually fires there.
 - Reach for `ignore-file <path>` only when the whole file is out of scope for design review: a fixture, a generated artifact, a deliberate slop demo. It silences every rule for that file permanently, including rules that have not been written yet. A real UI surface with one noisy rule wants the file-scoped value ignore above.
 - Use `ignore-rule <id>` only when the user asks to suppress that whole rule across the project. For broad overused-font suppression, use `ignore-rule overused-font --all-values` only when the user asks to ignore overused fonts generally.
@@ -67,10 +73,10 @@ Example value-specific exception:
 node .pi/skills/impeccable/scripts/hook-admin.mjs ignore-value overused-font Inter --shared --reason "User confirmed Inter is intentional"
 ```
 
-Example intentional motion exception:
+Example self-served exception, with the evidence named:
 
 ```bash
-node .pi/skills/impeccable/scripts/hook-admin.mjs ignore-value bounce-easing bounce-ball --shared --reason "User confirmed ball bounce animation is intentional"
+node .pi/skills/impeccable/scripts/hook-admin.mjs ignore-value bounce-easing bounce-ball --shared --reason "Agent: literal ball-bounce animation, bounce easing is the subject"
 ```
 
 Example whole-rule font exception:

package/template/.agents/skills/design/impeccable/reference/init.md

@@ -24,7 +24,7 @@ Form a platform hypothesis: `web`, `ios`, `android`, or `adaptive` (one product
 
 ## Step 3: Interview for product truth
 
-ask the user directly to clarify what you cannot infer. Ask only about material gaps the repository and original request do not answer with strong evidence.
+Ask the user directly to clarify what you cannot infer. Ask only about material gaps the repository and original request do not answer with strong evidence.
 
 Use the structured question tool when available; otherwise ask and wait. Keep rounds to at most three focused questions and require one real answer or approval round before writing a new PRODUCT.md. Confirm inferences.
 
@@ -107,9 +107,15 @@ When the platform you just recorded is `ios`, `android`, or `adaptive`, load [io
 
 Before loading new-work or resuming shape/build, verify that PRODUCT.md exists at the resolved path and contains the confirmed product record. If the file is absent, init is incomplete. Do not substitute interview notes, a planning packet, or later design prose for the file.
 
-## Step 5: Configure live mode when useful
+## Step 5: Record workflow defaults
 
-Skip native or non-runnable projects and leave existing config untouched. Otherwise follow [live.md](live.md)'s first-time setup. Any CSP source edit still requires its stated consent.
+When image generation is available and no `buildPath` is recorded yet, ask once how new surfaces should be built. Availability means a harness-native image tool or the API fallback that context.mjs reports as `IMAGE_GEN_AVAILABLE`, and the first of those leaves no trace in the boot output: context.mjs only sees the key, so a silent boot on a harness that generates images is not evidence there is nothing to ask about. This is its own question, never a clause riding inside another one. The stack round asks what to build with; this asks how the building starts, and an answer to the first carries no consent about the second. State the trade in the question the user actually reads, because the two names mean nothing to someone meeting them for the first time: **comp-first** (an image sets the bar before any code; bolder composition, slower, and the build must match the image) or **code-first** (build directly; the ambition is written into the direction contract and audited at the finish; leaner, faster).
+
+Write the answer to `.impeccable/config.json` as `"buildPath": "comp"` or `"buildPath": "code"`, merging with the keys already there. Write only the value the user chose. A recommendation you made is not an answer you received, and a value taken from silence is a standing default nobody set: it then rides every future round in the project, which is the opposite of asking once. When the question goes unanswered, record nothing and say in one line which path this session is taking and that it is not stored. That path is comp-first, the default new-work applies wherever image generation exists and nothing is recorded; name it rather than choosing a quieter one, because a silent default invented here is the same failure as a value written without an answer. Unset is a working state, not a gap: the decision page's toggle governs each session, and new-work's one-time offer records the answer the first time the user flips it. The config is the only place this lives. It is a workflow setting, not product truth, so it never joins `## Stack` or any other PRODUCT.md section, where a second copy would outlive the setting and steer rounds nobody could trace back to it.
+
+A value already recorded in `.impeccable/config.json` or the gitignored `.impeccable/config.local.json` is a confirmed answer: on a re-run, honor it in silence rather than asking again. This is a default, not a lock: the decision page renders a toggle whose flip binds a single session and is never written back. Without image generation there is no choice to record; code-first is the only path.
+
+Then configure live mode when useful: skip native or non-runnable projects and leave existing config untouched. Otherwise follow [live.md](live.md)'s first-time setup. Any CSP source edit still requires its stated consent.
 
 ## Step 6: Wrap up or resume