The design language that makes your AI harness better at design.
JavaScript
Sync generated provider output
github-actions[bot]db0f2dfb47f1
diff --git a/.agent/skills/impeccable/reference/critique.md b/.agent/skills/impeccable/reference/critique.mdindex 2a72efcd1..97f1f0e18 100644--- a/.agent/skills/impeccable/reference/critique.md+++ b/.agent/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.agents/skills/impeccable/reference/critique.md b/.agents/skills/impeccable/reference/critique.mdindex c1285ca13..60dfb1545 100644--- a/.agents/skills/impeccable/reference/critique.md+++ b/.agents/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -64,7 +66,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -108,6 +110,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -140,7 +143,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.claude/skills/impeccable/reference/critique.md b/.claude/skills/impeccable/reference/critique.mdindex f4a2f3f6e..4633df420 100644--- a/.claude/skills/impeccable/reference/critique.md+++ b/.claude/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.cursor/skills/impeccable/reference/critique.md b/.cursor/skills/impeccable/reference/critique.mdindex ba1eb1532..ba3b403e4 100644--- a/.cursor/skills/impeccable/reference/critique.md+++ b/.cursor/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.dsh/skills/impeccable/reference/critique.md b/.dsh/skills/impeccable/reference/critique.mdindex e3e120c68..8112e2564 100644--- a/.dsh/skills/impeccable/reference/critique.md+++ b/.dsh/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.gemini/skills/impeccable/reference/critique.md b/.gemini/skills/impeccable/reference/critique.mdindex 99d5e061f..31e87e472 100644--- a/.gemini/skills/impeccable/reference/critique.md+++ b/.gemini/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.github/skills/impeccable/reference/critique.md b/.github/skills/impeccable/reference/critique.mdindex 3799695aa..bb84cf841 100644--- a/.github/skills/impeccable/reference/critique.md+++ b/.github/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.grok/skills/impeccable/reference/critique.md b/.grok/skills/impeccable/reference/critique.mdindex 96eecfd39..94e5479ce 100644--- a/.grok/skills/impeccable/reference/critique.md+++ b/.grok/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.hermes/skills/impeccable/reference/critique.md b/.hermes/skills/impeccable/reference/critique.mdindex dae70898a..6854f27b3 100644--- a/.hermes/skills/impeccable/reference/critique.md+++ b/.hermes/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.kiro/skills/impeccable/reference/critique.md b/.kiro/skills/impeccable/reference/critique.mdindex 5f942dbd4..643779bb0 100644--- a/.kiro/skills/impeccable/reference/critique.md+++ b/.kiro/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.omp/skills/impeccable/reference/critique.md b/.omp/skills/impeccable/reference/critique.mdindex 2c195bcfd..ffcdc2bcc 100644--- a/.omp/skills/impeccable/reference/critique.md+++ b/.omp/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.opencode/skills/impeccable/reference/critique.md b/.opencode/skills/impeccable/reference/critique.mdindex d3a9362c2..7e82e0f95 100644--- a/.opencode/skills/impeccable/reference/critique.md+++ b/.opencode/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.pi/skills/impeccable/reference/critique.md b/.pi/skills/impeccable/reference/critique.mdindex 4e53c2f25..92c02f14a 100644--- a/.pi/skills/impeccable/reference/critique.md+++ b/.pi/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.qoder/skills/impeccable/reference/critique.md b/.qoder/skills/impeccable/reference/critique.mdindex 730b51bde..414e70371 100644--- a/.qoder/skills/impeccable/reference/critique.md+++ b/.qoder/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.rovodev/skills/impeccable/reference/critique.md b/.rovodev/skills/impeccable/reference/critique.mdindex 87c4f5c36..0e547ffa2 100644--- a/.rovodev/skills/impeccable/reference/critique.md+++ b/.rovodev/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.trae-cn/skills/impeccable/reference/critique.md b/.trae-cn/skills/impeccable/reference/critique.mdindex 20d3431e6..a60ca234e 100644--- a/.trae-cn/skills/impeccable/reference/critique.md+++ b/.trae-cn/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.trae/skills/impeccable/reference/critique.md b/.trae/skills/impeccable/reference/critique.mdindex 3790a74d8..7d3a68769 100644--- a/.trae/skills/impeccable/reference/critique.md+++ b/.trae/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.veto/skills/impeccable/reference/critique.md b/.veto/skills/impeccable/reference/critique.mdindex c3213cdcd..8ed38a0a8 100644--- a/.veto/skills/impeccable/reference/critique.md+++ b/.veto/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/.vibe/skills/impeccable/reference/critique.md b/.vibe/skills/impeccable/reference/critique.mdindex b3177092c..85d8bc594 100644--- a/.vibe/skills/impeccable/reference/critique.md+++ b/.vibe/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/cursor-plugin/skills/impeccable/reference/critique.md b/cursor-plugin/skills/impeccable/reference/critique.mdindex 29ee47acf..840085415 100644--- a/cursor-plugin/skills/impeccable/reference/critique.md+++ b/cursor-plugin/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.diff --git a/plugin/skills/impeccable/reference/critique.md b/plugin/skills/impeccable/reference/critique.mdindex 387fd6793..825e70817 100644--- a/plugin/skills/impeccable/reference/critique.md+++ b/plugin/skills/impeccable/reference/critique.md@@ -4,11 +4,11 @@ Resolve one stable target, run two independent assessments, synthesize a design### Hard Invariants-- Assessment A (design review) and Assessment B (detector/browser evidence) are both required.-- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask).+- Assessment A (design review) and Assessment B (detector/browser evidence) are both required, except on a native platform (see Assessment Orchestration).+- Assessment A and B MUST run as two isolated sub-agents whenever a sub-agent/Task tool is exposed. Running them inline in this context is "possible" but is NOT permitted; it is a degraded run. Inline is allowed ONLY when no sub-agent tool exists (or the user declined, on harnesses that ask). Native platforms run A alone (see Assessment Orchestration).- If you degrade for any reason, the report's first line MUST be a banner: `⚠️ DEGRADED: single-context (<reason>)`. A silent degraded critique is a failed critique.- Assessment A must finish before detector findings enter the parent synthesis context. Detector output is deterministic, but it still anchors judgment.-- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt.+- A skipped detector is a failed critique run unless `impeccable detect` is missing or crashes after a real attempt, or the platform is native (see Assessment Orchestration).- 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.@@ -30,6 +30,8 @@ Resolve one stable target, run two independent assessments, synthesize a design### Assessment Orchestration+**Native platforms** (`ios` / `android` / `adaptive`): Assessment B does not apply, because `impeccable detect` and the browser overlay read only web markup. Run Assessment A alone in this context and skip both sub-agent gates below, the Codex permission question included: with no B there is nothing to isolate A from, so this is the complete native method and carries no degraded banner. Do not run `impeccable detect` on native source; its empty result reads as clean.+Delegate Assessment A and Assessment B to separate sub-agents. They must not see each other's output. Do not show findings to the user until synthesis.Sub-agent gate (all harnesses):@@ -55,7 +57,7 @@ Return: design-specificity verdict, heuristic scores, cognitive load, emotional### Assessment B: Detector + Browser Evidence-Run the bundled detector and browser visualization evidence. Assessment B is mandatory and must remain isolated from Assessment A until both are complete.+Run the bundled detector and browser visualization evidence. On web, Assessment B is mandatory and must remain isolated from Assessment A until both are complete.CLI scan:```bash@@ -93,6 +95,7 @@ Structure your feedback as a design director would:The report's first line MUST declare how the assessments were run, so a degraded run is never silent:- Dual-agent: `Method: dual-agent (A: <agent-id> · B: <agent-id>)`- Degraded: `⚠️ DEGRADED: single-context (<reason, e.g. no sub-agent tool exposed>)`+- Native: `Method: design review only (detector not applicable, native platform)`#### Design Health Score> *Consult the [Heuristics Scoring Guide](#heuristics-scoring-guide) section below.*@@ -125,7 +128,7 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score**LLM assessment**: Your unanchored evaluation of design specificity. Cover overall coherence, structural sameness, category-interchangeable choices, and missed opportunities for product character.-**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives.+**Deterministic scan**: Summarize what the automated detector found, with counts and file locations. Note any additional issues the detector caught that you missed, and flag any false positives. On a native platform, write `not applicable (native platform)` instead.**Visual overlays** (if injection succeeded): Tell the user that overlays are now visible in the **[Human]** tab in their browser, highlighting the detected issues. Summarize what the console output reported. If browser visualization was attempted but injection failed, say that no reliable user-visible overlay is available and report the fallback signal instead.