@bastani/atomic 0.9.13 → 0.9.14-alpha.2

package/dist/builtin/workflows/builtin/open-claude-design.ts

@@ -2,16 +2,17 @@
  * Builtin workflow: open-claude-design
  *
  * Adapts Atomic SDK's Claude Design workflow to the local workflow SDK:
- * combined discovery/init, design-system/reference research, generation, bounded
- * refinement, export, and final display run through ctx.task()/ctx.parallel().
+ * combined discovery/init, design-system/reference research, one generation,
+ * one live review session, export, and final display run through
+ * ctx.task()/ctx.parallel().
  *
  * Every stage prompt invokes the specific impeccable sub-skill that maps to
  * its role (see https://github.com/pbakaus/impeccable/tree/main/site/content/skills):
  *
  *   onboarding     → impeccable `document` / `extract` / `audit`
  *   import         → impeccable `extract`
- *   generate-N     → impeccable `craft` / `polish` (HTML preview)
- *   user-feedback  → impeccable `live` (browser review + user notes)
+ *   generate-1     → impeccable `craft` (HTML preview)
+ *   live review    → impeccable `live` (unbounded browser review session)
  *   exporter       → impeccable `document` (rich HTML spec)
  *   final-display  → opens/surfaces the exported HTML spec
  */
@@ -20,13 +21,14 @@ import { Type } from "typebox";
 import { workflow } from "../src/authoring/workflow.js";
 import { withSteeringPropagationContext } from "./steering-context.js";
 import { runOpenClaudeDesignWorkflow } from "./open-claude-design-runner.js";
-import {
-  DEFAULT_MAX_REFINEMENTS,
-} from "./open-claude-design-utils.js";
 
 export default workflow({
   name: "open-claude-design",
-  description: "AI-powered design workflow: combined discovery/init → design-system/reference research → curated reference discovery → HTML generation → live-driven refinement → rich HTML handoff. The discovery stage asks what to build, the output type, and which references to emulate, then runs impeccable init for PRODUCT.md/DESIGN.md (references take precedence over project context). The user iteratively reviews the generated HTML.",
+  description: "AI-powered design workflow: combined discovery/init → design-system/reference research → curated reference discovery → HTML generation → one live review session → rich HTML handoff. The discovery stage asks what to build, the output type, and which references to emulate, then runs impeccable init for PRODUCT.md/DESIGN.md (references take precedence over project context). The user reviews the generated HTML in one live session.",
+  // Disabled: this workflow is driven by the user reviewing generated HTML,
+  // so the parent chat is already the thing holding it to its goal. A periodic
+  // alignment steer would interrupt that review rather than inform it.
+  heartbeatIntervalMinutes: 0,
   inputs: {
     prompt: Type.String({
       description: "What to design (for example, a dashboard, page, component, or prototype). The discovery stage refines this into a confirmed brief and asks for the output type and references.",
@@ -36,18 +38,12 @@ export default workflow({
       description:
         "Discover beautiful, current reference designs from notable design websites (Awwwards, recent.design, Dribbble, Monet, Motionsites) and feed them to generation. Set false to skip the network/browser reference pass.",
     }),
-    max_refinements: Type.Number({
-      default: DEFAULT_MAX_REFINEMENTS,
-      description: `Maximum generate/user-feedback loop iterations (default ${DEFAULT_MAX_REFINEMENTS}).`,
-    }),
   },
   outputs: {
     output_type: Type.Optional(Type.String({ description: "Kind of design artifact produced." })),
     design_system: Type.Optional(Type.String({ description: "Design system source used for generation: the project-derived design system." })),
-    artifact: Type.Optional(Type.String({ description: "Latest final design summary from the approved preview artifact." })),
+    artifact: Type.Optional(Type.String({ description: "Latest final design summary from the final preview artifact." })),
     handoff: Type.Optional(Type.String({ description: "Final rich HTML spec and implementation handoff summary." })),
-    approved_for_export: Type.Optional(Type.Boolean({ description: "Whether refinement completed before export." })),
-    refinements_completed: Type.Optional(Type.Number({ description: "Number of refinement iterations completed." })),
     import_context: Type.Optional(Type.String({ description: "Reference-import context used during generation." })),
     run_id: Type.Optional(Type.String({ description: "Per-run design workflow artifact identifier." })),
     artifact_dir: Type.Optional(Type.String({ description: "Directory containing preview and spec artifacts." })),

package/dist/builtin/workflows/builtin/ralph-models.ts

@@ -9,10 +9,10 @@ import { reviewDecisionSchema } from "./ralph-core.js";
 //   decorrelate review errors from reviewer A.
 // - Dominated benchmark models stay out of the chains: claude-sonnet-5,
 //   claude-sonnet-4.6, gemini-3.1-pro, and gemini-3.5-flash.
-// - GLM-5.2 has only two real reasoning tiers — its thinkingLevelMap collapses
-//   minimal/low/medium/high to "high" and xhigh to "max" — so chains only use
-//   :high (budget tier, 36%/$2.84) or :xhigh (best tier, 44%/$3.92); the
-//   openrouter/z-ai mirror maps :xhigh exclusively, so it is always :xhigh.
+// - GLM-5.3 exposes reasoning without a thinkingLevelMap or reasoning-effort
+//   control, so chains use the catalog-supported :high tier explicitly rather
+//   than carrying the prior GLM generation's :xhigh/:max suffixes forward. OpenRouter has no
+//   GLM-5.3 catalog entry, so its unavailable fallback is intentionally omitted.
 
 export const promptEngineerModelConfig = {
     model: "anthropic/claude-opus-5:high",
@@ -31,9 +31,9 @@ export const promptEngineerModelConfig = {
       "openai/gpt-5.5:xhigh",
       "anthropic/claude-opus-4-8:high",
       "github-copilot/claude-opus-4.8:high",
-      "xai/grok-4.5:high",
-      "zai/glm-5.2:xhigh",
-      "zai-coding-cn/glm-5.2:xhigh",
+      "xai/grok-4.6:high",
+      "zai/glm-5.3:high",
+      "zai-coding-cn/glm-5.3:high",
       "openrouter/anthropic/claude-opus-5:high",
       "openrouter/anthropic/claude-fable-5:high",
       "openrouter/openai/gpt-5.6-sol:xhigh",
@@ -41,8 +41,7 @@ export const promptEngineerModelConfig = {
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-opus-4-8:high",
-      "openrouter/x-ai/grok-4.5",
-      "openrouter/z-ai/glm-5.2:xhigh"
+      "openrouter/x-ai/grok-4.6",
     ],
     excludedTools: ["ask_user_question"],
 };
@@ -64,9 +63,9 @@ export const researchModelConfig = {
       "openai/gpt-5.5:xhigh",
       "anthropic/claude-opus-4-8:high",
       "github-copilot/claude-opus-4.8:high",
-      "xai/grok-4.5:high",
-      "zai/glm-5.2:xhigh",
-      "zai-coding-cn/glm-5.2:xhigh",
+      "xai/grok-4.6:high",
+      "zai/glm-5.3:high",
+      "zai-coding-cn/glm-5.3:high",
       "openrouter/anthropic/claude-opus-5:high",
       "openrouter/openai/gpt-5.6-sol:xhigh",
       "openrouter/anthropic/claude-fable-5:high",
@@ -74,8 +73,7 @@ export const researchModelConfig = {
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-opus-4-8:high",
-      "openrouter/x-ai/grok-4.5",
-      "openrouter/z-ai/glm-5.2:xhigh"
+      "openrouter/x-ai/grok-4.6",
     ],
     excludedTools: ["ask_user_question"],
 };
@@ -97,9 +95,9 @@ export const orchestratorModelConfig = {
       "openai/gpt-5.5:xhigh",
       "anthropic/claude-opus-4-8:high",
       "github-copilot/claude-opus-4.8:high",
-      "xai/grok-4.5:high",
-      "zai/glm-5.2:xhigh",
-      "zai-coding-cn/glm-5.2:xhigh",
+      "xai/grok-4.6:high",
+      "zai/glm-5.3:high",
+      "zai-coding-cn/glm-5.3:high",
       "openrouter/anthropic/claude-opus-5:high",
       "openrouter/openai/gpt-5.6-sol:xhigh",
       "openrouter/anthropic/claude-fable-5:high",
@@ -107,8 +105,7 @@ export const orchestratorModelConfig = {
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-opus-4-8:high",
-      "openrouter/x-ai/grok-4.5",
-      "openrouter/z-ai/glm-5.2:xhigh"
+      "openrouter/x-ai/grok-4.6",
     ],
     excludedTools: ["ask_user_question"],
 };
@@ -130,9 +127,9 @@ export const reviewerAModelConfig = {
       "openai/gpt-5.5:xhigh",
       "anthropic/claude-opus-4-8:high",
       "github-copilot/claude-opus-4.8:high",
-      "xai/grok-4.5:high",
-      "zai/glm-5.2:xhigh",
-      "zai-coding-cn/glm-5.2:xhigh",
+      "xai/grok-4.6:high",
+      "zai/glm-5.3:high",
+      "zai-coding-cn/glm-5.3:high",
       "openrouter/anthropic/claude-opus-5:high",
       "openrouter/anthropic/claude-fable-5:high",
       "openrouter/moonshotai/kimi-k3:max",
@@ -140,8 +137,7 @@ export const reviewerAModelConfig = {
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-opus-4-8:high",
-      "openrouter/x-ai/grok-4.5",
-      "openrouter/z-ai/glm-5.2:xhigh"
+      "openrouter/x-ai/grok-4.6",
     ],
     excludedTools: ["ask_user_question"],
     schema: reviewDecisionSchema,
@@ -164,9 +160,9 @@ export const reviewerBModelConfig = {
       "openai/gpt-5.5:xhigh",
       "anthropic/claude-opus-4-8:high",
       "github-copilot/claude-opus-4.8:high",
-      "xai/grok-4.5:high",
-      "zai/glm-5.2:xhigh",
-      "zai-coding-cn/glm-5.2:xhigh",
+      "xai/grok-4.6:high",
+      "zai/glm-5.3:high",
+      "zai-coding-cn/glm-5.3:high",
       "openrouter/openai/gpt-5.6-sol:xhigh",
       "openrouter/anthropic/claude-opus-5:high",
       "openrouter/anthropic/claude-fable-5:high",
@@ -174,8 +170,7 @@ export const reviewerBModelConfig = {
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/anthropic/claude-opus-4-8:high",
-      "openrouter/x-ai/grok-4.5",
-      "openrouter/z-ai/glm-5.2:xhigh"
+      "openrouter/x-ai/grok-4.6",
     ],
     excludedTools: ["ask_user_question"],
     schema: reviewDecisionSchema,

package/dist/builtin/workflows/builtin/ralph.ts

@@ -13,6 +13,10 @@ import { runRalphWorkflow } from "./ralph-runner.js";
 export default workflow({
   name: "ralph",
   description: "Raw prompt → research-prompt-refinement → research → orchestrate → multi-model parallel review loop with bounded iteration and immutable acceptance criteria. When launching follow-up ralph runs from review findings, pass the ORIGINAL task text as acceptance_criteria so deltas cannot drift from the literal contract. If the task includes submitting a pull request (or MR/review), remove that final action from the prompt text and set create_pr=true instead when preparing the workflow inputs.",
+  // The 15-minute default, stated rather than inherited: this is a per-workflow
+  // product decision, so a future change to the global default must not silently
+  // re-cadence a long autonomous run.
+  heartbeatIntervalMinutes: 15,
   inputs: {
     prompt: Type.String({ description: "The task or goal to research, execute, and refine. Do not include PR/MR submission instructions here; strip them from the task text and request them via create_pr=true instead." }),
     acceptance_criteria: Type.Optional(Type.String({ description: "Original immutable task contract this run must remain consistent with. Defaults to prompt. Orchestrators launching follow-up runs from reviewer findings should pass the ORIGINAL task text here." })),

package/dist/builtin/workflows/builtin/tournament-runner.ts

@@ -125,8 +125,6 @@ export async function runTournament(ctx: WorkflowRunContext<TournamentInputs>) {
         context: "fresh" as const,
         reads: [first.path, second.path],
         schema: judgeDecisionSchema,
-        output: path,
-        outputMode: "file-only" as const,
       };
     });
     const judgeResults = await ctx.parallel(judgeSteps, {
@@ -141,6 +139,11 @@ export async function runTournament(ctx: WorkflowRunContext<TournamentInputs>) {
       const second = reverse ? left : right;
       const name = `judge-round-${round}-match-${index + 1}`;
       const decision = decisionFrom(resultByName(judgeResults, name));
+      // Judge decisions are inter-stage data: the bracket reducer reads
+      // schema-shaped JSON from these paths, so the runner persists the
+      // structured decisions itself rather than the stage artifact channel.
+      const judgeArtifactPath = judgeArtifactPaths.at(-pairs.length + index)!;
+      await writeFile(judgeArtifactPath, `${JSON.stringify(decision, null, 2)}\n`);
       const winner = decision.winner === "first" ? first : second;
       next.push(winner);
       matches.push({
@@ -151,7 +154,7 @@ export async function runTournament(ctx: WorkflowRunContext<TournamentInputs>) {
         winner: winner.label,
         rationale: decision.rationale,
         evidence: decision.evidence,
-        judge_artifact_path: judgeArtifactPaths.at(-pairs.length + index)!,
+        judge_artifact_path: judgeArtifactPath,
       });
     }
     if (bye !== undefined) next.push(bye);

package/dist/builtin/workflows/builtin/tournament.ts

@@ -6,6 +6,10 @@ import { runTournament } from "./tournament-runner.js";
 export default workflow({
   name: "tournament",
   description: "Run several independent whole-task attempts through a balanced pairwise judging bracket and return an auditable winner.",
+  // The 15-minute default, stated rather than inherited: this is a per-workflow
+  // product decision, so a future change to the global default must not silently
+  // re-cadence a long autonomous run.
+  heartbeatIntervalMinutes: 15,
   inputs: {
     prompt: Type.String({ description: "Task every competing agent must attempt independently." }),
     num_attempts: Type.Integer({

package/dist/builtin/workflows/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/workflows",
-  "version": "0.9.13",
+  "version": "0.9.14-alpha.2",
   "private": true,
   "description": "Atomic extension for multi-stage workflow authoring and execution.",
   "contributors": [
@@ -83,7 +83,7 @@
   },
   "peerDependencies": {
     "@bastani/atomic": "*",
-    "@earendil-works/pi-tui": "^0.84.1"
+    "@earendil-works/pi-tui": "^0.84.2"
   },
   "peerDependenciesMeta": {
     "@bastani/atomic": {

package/dist/builtin/workflows/skills/impeccable/SKILL.md

@@ -1,7 +1,7 @@
 ---
 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: 4.0.3
+version: 4.1.1
 ---
 
 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.
@@ -9,11 +9,11 @@ This skill gives you the tools and permission to create design that earns to be
 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 .agents/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.
+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 .agents/skills/impeccable/scripts/...` command in this skill and its references, and `.agents/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. 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.
 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.
 

package/dist/builtin/workflows/skills/impeccable/agents/impeccable_asset_producer.toml

@@ -1,21 +1,19 @@
 name = "impeccable_asset_producer"
 description = "Produces clean reusable raster assets from approved Impeccable mock references without redesigning the direction."
 model_reasoning_effort = "medium"
-nickname_candidates = ["Asset Plate", "Clean Plate", "Crop Cutter"]
+nickname_candidates = ["Asset Plate", "Clean Plate", "Re-Render"]
 developer_instructions = '''
 # 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: 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. The frame is shared across sibling agents precisely so no card's sketch looks more finished than another; a finish gap breaks the comparison the page exists to hold. 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.
+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
 
@@ -27,47 +25,45 @@ Expect:
 - 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.
+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:
+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.
+- Target production size, or at least 2x display size when dimensions are known. Never default to the small size of a full-page mock crop.
+- Remove UI text, navigation, buttons, labels, and body copy.
 - 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.
+- Remove letterboxing, empty padding, baked card corners, borders, shadows, caption bands, and layout background unless the parent says those pixels are intrinsic.
+- Keep the final assets directory clean: only files the build will consume. Source crops, reference crops, masks, and contact sheets go 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.
+Ask blockers once, globally. Missing source path/crops or output directory blocks production. Exact dimensions, compression targets, retina variants, and format preferences do not; choose defaults and report them.
 
 ## Workflow
 
 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`: can ship as a crop, format conversion, compression pass, or sourced replacement with no generative cleanup.
+   - `direct`: ships after format conversion, compression, or renaming because the parent supplied a real standalone source: 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. Treat full-page mock crops as references, not production-resolution source assets. Put a role in `direct` only when the provided source is already a clean, sufficiently large source asset with no semantic text or presentation chrome.
+3. Crops from the mock are binding visual references, never shipping pixels: a full-page mock's effective resolution is reference grade, and a shipped crop, however close it looks, is how a beautiful comp becomes 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. Treat every crop as binding reference. Use the harness's native image tool by default when generation or editing is needed; otherwise use the skill's generate-image.mjs.
+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 a semantic HTML/CSS/SVG recommendation when 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.
 
-Codex: the imagegen skill's built-in `image_gen` path is the native tool here; prefer it for generation and editing.
+Codex: the imagegen skill's built-in `image_gen` path is the native tool here; prefer it for generation, editing, and the chroma-key workflow.
 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.
+9. Save outputs non-destructively in the requested project directory, and leave the intent with the file: after every generation, run `node .agents/skills/impeccable/scripts/embed-prompt.mjs <asset> --prompt "<the prompt used>"` so the prompt lives inside the image itself. 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.
 
 Use `direct` only for provided source assets that can already ship after crop tightening, conversion, compression, or naming. Do not ship a small crop from the full-page mock as `direct` just because it looks close.
 
-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.
-
-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.
+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 first, classify it as crop-derived cleanup or clean-plate work.
 
-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.
+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. Ship a screenshot raster only when the parent explicitly says the screenshot itself is the final asset.
 
-For transparency, prefer true alpha output when the tool supports it. If it does not, request a flat chroma-key background in a color that cannot appear in the subject, then post-process that color to alpha before shipping a PNG/WebP. Do not ship the keyed background as the final asset.
+Semantic does not mean ignored. For every semantic role, write a concrete implementation handoff for the parent craft agent: the DOM/component layers, CSS-owned visual treatment, SVG/canvas/icon-library pieces, responsive behavior, and which nearby produced raster assets it composes with. For logos and icons, prefer inline SVG/vector or icon-library implementation unless the parent provides a production logo raster.
 
 ## Prompt Pattern
 
@@ -82,19 +78,17 @@ Remove letterboxing, padding, card borders, rounded clipping, CSS shadows, persp
 Do not add new objects. Do not change the concept. Do not redesign the composition.
 ```
 
-For transparent cutouts, use a chroma-key workflow by default: generate on a flat color that cannot appear in the subject, then post-process to alpha; use true native transparency only when the tool supports it or the parent authorizes it.
-
-Codex: run the chroma-key workflow through the imagegen skill's built-in-first path.
+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.
 
 ## 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.
+For each semantic row include `id`, `implementation`, `notes`, and `qa_status`. The `implementation` is a concrete build handoff, not a note that no asset was produced: name the likely HTML/CSS/SVG/canvas/icon/component pieces and the visual responsibilities 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.
+`qa_status` is `accepted`, `needs_parent_review`, or `blocked`. `accepted` only after visual comparison passes. `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. `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.
+End with `execution_order`, `blockers`, and `assumptions` sections. Keep blockers global and minimal; per-asset rows 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.
 '''

package/dist/builtin/workflows/skills/impeccable/agents/impeccable_documenter.toml

@@ -19,6 +19,7 @@ Expect: the project root; the artifact path(s); the direction contract text (THE
 2. Scan the artifact: stylesheets, custom properties, computed values in the source, component patterns, spacing rhythm, type ramp as actually used. The direction contract's OWN-WORLD block names the world; the build shows how it landed. Where they diverge, the build wins and the prose may note the divergence.
 3. Write DESIGN.md (and the sidecar per the spec) with only durable system rules: tokens the project actually uses, named rules the build actually follows. Skip one-off values; a token used once is not a system.
 4. Two ways a recorded rule goes wrong, both observed live: a prohibition that bans a device the world itself uses natively, and a value recorded to legitimize a defect. Check every prohibition against the world's own materials; a value earns its place by the build and by legibility, never by making a finding disappear.
+5. Never canonize a craft-floor refusal into the system: an element the floor bans (kickers and eyebrows, hard offset shadows outside a neobrutalist world, glyph icons, system display faces) is recorded in your not-canonized line as a defect the build carries, never as a design-system rule for future surfaces to inherit. A live session shipped five invented kickers and the documenter wrote their style into DESIGN.md; that is how one violation becomes the house style.
 
 ## Output Contract
 

package/dist/builtin/workflows/skills/impeccable/agents/impeccable_finish_reviewer.toml

@@ -5,31 +5,37 @@ nickname_candidates = ["Finishing Eye", "Contract Judge", "Ceiling Check"]
 developer_instructions = '''
 # 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.
 
-You run under a hard turn ceiling that ends the run without warning, and a run that ends before the five sections are written returns nothing; a review built from what you saw beats a perfect review that never arrives. So treat reading as an allowance, not a prerequisite: read only the provided inputs, never the skill's own reference files, 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. 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: the contract is the builder's abstraction of the comp, and a review anchored on it inherits whatever that 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); 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.
-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. 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/review/hero-repro.png` exists: the hero reproduction checkpoint's capture at the comp's own dimensions; its absence means the reproduction phase ran unproven, a material finding. 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.** 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. 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; 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 renders) as contradicted on its face; imitation material is the single most reliable mark of machine-made design. 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.
+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 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: 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.
 
-## Verdict Pass
+## Disposition
 
-When the parent returns with post-fix recaptures, you are scoring, not re-hunting. 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").
+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 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. 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/dist/builtin/workflows/skills/impeccable/agents/impeccable_manual_edit_applier.toml

@@ -18,12 +18,12 @@ Expect a self-contained handoff with:
 - Event id.
 - Page URL.
 - Optional chunk metadata.
-- Optional repair metadata. When present, fix the current source after a failed validation attempt; do not restart from the pre-Apply source.
+- Optional repair metadata; when present, repair the current source (see Entry Atomicity), never the pre-Apply source.
 - Optional deadline.
 - The current event `batch`.
 - Optional `evidencePath`.
 
-The user already clicked Apply. Do not ask what to do. Do not discard edits. Do not run `live-poll.mjs`, `live-commit-manual-edits.mjs`, or any live server endpoint. Do not run `live-commit-manual-edits.mjs` for a leased manual Apply event. Do not stage, commit, rebuild, push, or edit generated provider output unless the batch explicitly targets that generated file.
+The user already clicked Apply. Do not ask what to do. Do not discard edits. Do not run `live-poll.mjs`, `live-commit-manual-edits.mjs`, or any live server endpoint. Do not stage, commit, rebuild, push, or edit generated provider output unless the batch explicitly targets that generated file.
 
 ## Workflow
 

package/dist/builtin/workflows/skills/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/dist/builtin/workflows/skills/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/dist/builtin/workflows/skills/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 STOP and use Codex's structured user-input/question tool when available; if unavailable, ask directly in chat 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. STOP and use Codex's structured user-input/question tool when available; if unavailable, ask directly in chat to clarify what you cannot infer. Name the exact addition and the job it would do.
 
 ## Why it reads flat