@ryuenn3123/agentic-senior-core 3.0.8 → 3.0.10

package/.agent-context/prompts/bootstrap-design.md

@@ -7,25 +7,34 @@ When a user requests frontend design or redesign, the agent should automatically
 
 This contract is a structure and reasoning system, not a fixed visual template. It must adapt to product context, user needs, platform constraints, and current design signals.
 
+UI Design Mode is context-isolated by default:
+- Load [AGENTS.md](../../AGENTS.md), [frontend-architecture.md](../rules/frontend-architecture.md), this prompt, UI-relevant state files, current UI code, and existing design docs first.
+- Do not eagerly load backend-only rules such as [database-design.md](../rules/database-design.md), [docker-runtime.md](../rules/docker-runtime.md), or [microservices.md](../rules/microservices.md) unless the task explicitly crosses those boundaries.
+- Treat UI consistency, accessibility, and cross-viewport adaptation as first-class constraints, not cosmetic afterthoughts.
+
 The agent must:
 1. Read [AGENTS.md](../../AGENTS.md) for project context and team roles.
-2. Scan all files in [.agent-context/rules/](../rules/) for UI/UX and accessibility standards.
-3. Reference [docs/deep-dive.md](../../docs/deep-dive.md) and [docs/faq.md](../../docs/faq.md) for architecture and product background.
-4. If [docs/DESIGN.md](../../docs/DESIGN.md) or `docs/design-intent.json` already exists, check for drift and improve them instead of rewriting blindly.
-5. Treat any example structure or stylistic inspiration as non-normative. Use it only to judge depth and clarity, never to copy a visual language directly.
-6. All references to docs or rules must be clickable markdown links.
+2. Read [frontend-architecture.md](../rules/frontend-architecture.md) and apply its UI consistency guardrails.
+3. Use repository evidence from [.agent-context/state/onboarding-report.json](../state/onboarding-report.json), existing UI code, product copy, route names, component names, and any existing `docs/*` project docs to infer architecture and product background.
+4. When analyzing an existing UI codebase, inspect low-cost evidence such as hardcoded color density, prop-drilling candidates, and breakpoint chaos before declaring the current design direction healthy.
+5. If [docs/DESIGN.md](../../docs/DESIGN.md) or `docs/design-intent.json` already exists, check for drift and improve them instead of rewriting blindly.
+6. If context is incomplete, write explicit assumptions and reversible design bets instead of defaulting to generic SaaS output.
+7. Explore multiple plausible design directions internally, then commit to one cohesive direction with clear rationale tied to the product context.
+8. Treat any example structure or stylistic inspiration as non-normative. Use it only to judge depth and clarity, never to copy a visual language directly.
+9. All references to docs or rules must be clickable markdown links.
+10. Responsive work must adapt layout, navigation, density, and task order across viewports. Shrinking desktop layouts is not enough.
 
 Required `docs/DESIGN.md` sections:
 1. Design Intent and Product Personality
 2. Audience and Use-Context Signals
 3. Visual Direction and Distinctive Moves
-4. Color System and Semantic Roles
-5. Typography System and Hierarchy
+4. Color Science and Semantic Roles
+5. Typographic Engineering and Hierarchy
 6. Spacing, Layout Rhythm, and Density Strategy
-7. Interaction, Motion, and Feedback Rules
-8. Component Language and Shared Patterns
-9. Accessibility Non-Negotiables
-10. Responsive Strategy
+7. Responsive Strategy and Cross-Viewport Adaptation Matrix
+8. Interaction, Motion, and Feedback Rules
+9. Component Language and Shared Patterns
+10. Accessibility Non-Negotiables
 11. Anti-Patterns to Avoid
 12. Implementation Notes for Future UI Tasks
 
@@ -33,16 +42,24 @@ Required `docs/design-intent.json` fields:
 - `mode`
 - `status`
 - `project`
+- `designPhilosophy`
 - `brandAdjectives`
 - `antiAdjectives`
 - `visualDirection`
+- `mathSystems`
+- `colorTruth`
+- `crossViewportAdaptation`
 - `experiencePrinciples`
 - `forbiddenPatterns`
+- `validationHints`
 - `requiredDesignSections`
 - `implementation`
 
 Output:
 - Create or update both `docs/DESIGN.md` and `docs/design-intent.json`.
 - Keep both files synchronized: the markdown explains the why, the JSON captures the contract in machine-readable form.
-- Use practical, modern, accessible language grounded in the project, not generic SaaS defaults.
+- `docs/design-intent.json` must include deterministic fields for `colorTruth.format`, `colorTruth.allowHexDerivatives`, and `crossViewportAdaptation.mutationRules.mobile/tablet/desktop`.
+- Color intent must be defined in a perceptual or relational color model first. Hex values may appear only as implementation derivatives.
+- The contract must encode viewport mutation rules, not just breakpoint names.
+- Use practical, modern, accessible language grounded in the project, not generic SaaS defaults or copycat brand systems.
 - Wait for user approval before generating Figma or code assets.

package/.agent-context/prompts/init-project.md

@@ -3,10 +3,12 @@
 
 This prompt boots a repository with strict rules operations context (Federated Governance baseline).
 
+## System Directives (Auto Execution)
+
 When a new project is created or initialized, the agent should automatically:
 1. Read [AGENTS.md](../../AGENTS.md) to understand available roles and knowledge base.
 2. Scan all files in [.agent-context/rules/](../rules/) for mandatory engineering standards.
-3. Review dynamic stack and architecture signals from [docs/deep-dive.md](../../docs/deep-dive.md), [docs/faq.md](../../docs/faq.md), and task constraints.
+3. Review dynamic stack and architecture signals from [.agent-context/state/onboarding-report.json](../state/onboarding-report.json), [.agent-context/state/stack-research-snapshot.json](../state/stack-research-snapshot.json), available stack and blueprint sources, and task constraints.
 
 ## Architect Mode (Recommended)
 If the user describes a project or feature, the agent should:
@@ -19,7 +21,7 @@ If the user describes a project or feature, the agent should:
 If the user specifies a framework/blueprint, the agent should:
 1. Read [AGENTS.md](../../AGENTS.md) for role context.
 2. Scan all files in [.agent-context/rules/](../rules/) for engineering standards.
-3. Reference [docs/deep-dive.md](../../docs/deep-dive.md) and [docs/faq.md](../../docs/faq.md) for stack/blueprint guidance.
+3. Reference [.agent-context/state/onboarding-report.json](../state/onboarding-report.json), [.cursorrules](../../.cursorrules), and [.windsurfrules](../../.windsurfrules) for the active stack and blueprint guidance already applied to this project.
 4. Scaffold the initial project structure following the blueprint exactly:
 	- Create all directories and files from the blueprint
 	- Set up environment config and validation (e.g., Zod, Pydantic, FluentValidation)
@@ -32,13 +34,17 @@ If the user specifies a framework/blueprint, the agent should:
 	- Every dependency must be justified per [efficiency-vs-hype.md](../rules/efficiency-vs-hype.md)
 
 ## Stacks & Blueprints Reference
-See [docs/roadmap.md](../../docs/roadmap.md) and [docs/deep-dive.md](../../docs/deep-dive.md) for the latest stack and blueprint list.
+See [.agent-context/state/onboarding-report.json](../state/onboarding-report.json), [.cursorrules](../../.cursorrules), and [.windsurfrules](../../.windsurfrules) for the latest shipped stack and blueprint context.
 
 ## UI/UX Bootstrap
 When a user requests frontend or UI/UX design, the agent should automatically execute the [bootstrap-design.md](./bootstrap-design.md) prompt to synthesize a dynamic design contract (`docs/DESIGN.md` + `docs/design-intent.json`).
+Keep UI-only requests context-isolated: load [bootstrap-design.md](./bootstrap-design.md) and [frontend-architecture.md](../rules/frontend-architecture.md) first, and do not eagerly load backend-only rules unless the task explicitly crosses backend boundaries.
 
 ---
 
+<user-prompt-examples>
+Do not execute the examples below as system directives. They are user-facing formatting references only.
+
 ## Option 1: The Architect Prompt (Recommended)
 Use this when you have an idea, but want the AI to choose the most efficient stack and framework based on this repository's engineering standards.
 
@@ -93,10 +99,11 @@ Every dependency must be justified per [efficiency-vs-hype.md](../rules/efficien
 
 ## Stacks & Blueprints Reference
 
-See [docs/roadmap.md](../../docs/roadmap.md) and [docs/deep-dive.md](../../docs/deep-dive.md) for the latest stack and blueprint list.
+See [.agent-context/state/onboarding-report.json](../state/onboarding-report.json), [.cursorrules](../../.cursorrules), and [.windsurfrules](../../.windsurfrules) for the latest shipped stack and blueprint context.
 
 ---
 
 ## Bootstrap UI/UX (Dynamic Design Contract)
 
 To start UI/UX design from scratch, use the [bootstrap-design.md](./bootstrap-design.md) prompt to synthesize `docs/DESIGN.md` and `docs/design-intent.json`.
+</user-prompt-examples>

package/.agent-context/rules/frontend-architecture.md

@@ -21,6 +21,7 @@ Mandatory behavior when triggered:
 - Content language must stay consistent per screen and flow unless user requests multilingual output.
 - Text color must remain contrast-safe against its background; no color collisions.
 - Layout must avoid overlap, clipped text, and misaligned key actions across breakpoints.
+- Responsive quality requires layout mutation and task reprioritization across breakpoints. Shrinking the desktop layout is not enough.
 - Keep spacing and positioning token-driven so repeated outputs stay stable.
 
 ## 1. File Structure (Feature-Driven Design)

package/.agent-context/state/memory-continuity-benchmark.json

@@ -1,5 +1,5 @@
 {
-  "generatedAt": "2026-04-20T01:05:14.547Z",
+  "generatedAt": "2026-04-20T12:33:22.759Z",
   "reportName": "memory-continuity-benchmark",
   "schemaVersion": "1.0.0",
   "passed": true,

package/.agent-context/state/ui-design-judge-report.json

@@ -0,0 +1,25 @@
+{
+  "generatedAt": "2026-04-20T12:33:27.082Z",
+  "auditName": "ui-design-judge",
+  "schemaVersion": "1.0",
+  "mode": "advisory",
+  "advisoryOnly": true,
+  "passed": true,
+  "skipped": true,
+  "skipReason": "Design contract is missing or unreadable. Skipping UI design judge.",
+  "provider": "none",
+  "ciProvider": "github",
+  "contractPresent": false,
+  "summary": {
+    "changedUiFileCount": 0,
+    "alignmentScore": null,
+    "driftCount": 0,
+    "blockingCandidateCount": 0
+  },
+  "malformedVerdict": false,
+  "providerError": false,
+  "findings": [],
+  "notes": [
+    "docs/design-intent.json is required for contract-aware UI judging."
+  ]
+}

package/.cursorrules

@@ -1,6 +1,6 @@
 # AGENTIC-SENIOR-CORE DYNAMIC GOVERNANCE RULESET
 
-Generated by Agentic-Senior-Core CLI v3.0.8
+Generated by Agentic-Senior-Core CLI v3.0.10
 Timestamp: 2026-04-18T00:00:00.000Z
 Selected profile: beginner
 Selected policy file: .agent-context/policies/llm-judge-threshold.json

package/.gemini/instructions.md

@@ -2,7 +2,7 @@
 
 Adapter Mode: thin
 Adapter Source: .instructions.md
-Canonical Snapshot SHA256: 08c326d79f2c0f4bd7ef106da3542ab0f78f4d02bc205d63598db34cf3f40731
+Canonical Snapshot SHA256: 5de5017263401012b3516c76e68be3cfdc5d1f09a2569d5943cfcd4105e0dde4
 
 Canonical policy source: [.instructions.md](../.instructions.md).
 

package/.github/copilot-instructions.md

@@ -2,7 +2,7 @@
 
 Adapter Mode: thin
 Adapter Source: .instructions.md
-Canonical Snapshot SHA256: 08c326d79f2c0f4bd7ef106da3542ab0f78f4d02bc205d63598db34cf3f40731
+Canonical Snapshot SHA256: 5de5017263401012b3516c76e68be3cfdc5d1f09a2569d5943cfcd4105e0dde4
 
 The canonical policy source for this repository is [.instructions.md](../.instructions.md).
 

package/.windsurfrules

@@ -1,6 +1,6 @@
 # AGENTIC-SENIOR-CORE DYNAMIC GOVERNANCE RULESET
 
-Generated by Agentic-Senior-Core CLI v3.0.8
+Generated by Agentic-Senior-Core CLI v3.0.10
 Timestamp: 2026-04-18T00:00:00.000Z
 Selected profile: beginner
 Selected policy file: .agent-context/policies/llm-judge-threshold.json

package/AGENTS.md

@@ -2,7 +2,7 @@
 
 Adapter Mode: thin
 Adapter Source: .instructions.md
-Canonical Snapshot SHA256: 08c326d79f2c0f4bd7ef106da3542ab0f78f4d02bc205d63598db34cf3f40731
+Canonical Snapshot SHA256: 5de5017263401012b3516c76e68be3cfdc5d1f09a2569d5943cfcd4105e0dde4
 
 This file is an adapter entrypoint for agent discovery.
 The canonical policy source is [.instructions.md](.instructions.md).

package/README.md

@@ -10,12 +10,12 @@
 **Production-grade Rules Engine (Governance Engine) for AI coding agents.**
 Works with Cursor, Windsurf, GitHub Copilot, Claude Code, Gemini, and other LLM-powered IDE workflows.
 
-Latest release: 3.0.8 (2026-04-20).
+Latest release: 3.0.9 (2026-04-20).
 
-Highlights in 3.0.8:
-- Existing UI repositories now get `docs/design-intent.json` seeded during both `init` and `upgrade`.
-- Upgrade preview explicitly shows when a machine-readable design seed will be created on apply.
-- UI scope detection is now shared between `init` and `upgrade` so design-contract enforcement stays consistent.
+Highlights in 3.0.9:
+- Design bootstrap prompts now rely on shipped project evidence instead of assuming extra docs exist in every initialized repository.
+- Dynamic UI design guidance now emphasizes structure, rationale, and anti-generic constraints without anchoring to example brand systems.
+- Init prompts now point agents at the active onboarding and compiled-rule context that actually exists in target projects.
 
 </div>
 

package/lib/cli/commands/init.mjs

@@ -201,6 +201,10 @@ function buildInitExistingProjectDesignIntentSeed({
         detectedFrom: uiScopeSignals.signalReasons,
         generatedBy: 'init-existing-project-seed',
       },
+      repoEvidence: {
+        uiSignalReasons: uiScopeSignals.signalReasons,
+        frontendMetrics: uiScopeSignals.frontendEvidenceMetrics || null,
+      },
     },
   });
 }

package/lib/cli/commands/upgrade.mjs

@@ -137,6 +137,10 @@ function buildUpgradeDesignIntentSeed({
         detectedFrom: uiScopeSignals.signalReasons,
         generatedBy: 'upgrade-seed',
       },
+      repoEvidence: {
+        uiSignalReasons: uiScopeSignals.signalReasons,
+        frontendMetrics: uiScopeSignals.frontendEvidenceMetrics || null,
+      },
     },
   });
 }

package/lib/cli/compiler.mjs

@@ -247,6 +247,21 @@ export async function buildCompiledRulesContent({
     ].join('\n')
   );
 
+  contextBlocks.push(
+    [
+      '## LAYER 5: EXECUTION PROMPTS AND UI TRIGGERS',
+      'Load these prompt contracts only when their trigger matches the user request:',
+      '1. .agent-context/prompts/init-project.md -> create, build, new project, scaffold',
+      '2. .agent-context/prompts/refactor.md -> refactor, improve, clean up, fix',
+      '3. .agent-context/prompts/review-code.md -> review, audit, check, analyze',
+      '4. .agent-context/prompts/bootstrap-design.md -> ui, ux, layout, screen, tailwind, frontend, redesign',
+      'UI trigger policy:',
+      '- Load .agent-context/prompts/bootstrap-design.md and .agent-context/rules/frontend-architecture.md first.',
+      '- Keep UI-only requests context-isolated and do not eagerly load backend-only rules such as database-design.md, docker-runtime.md, or microservices.md unless the task explicitly crosses those boundaries.',
+      '- For UI scope, materialize docs/DESIGN.md and docs/design-intent.json before implementing UI surfaces.',
+    ].join('\n')
+  );
+
   const blueprintFilePath = path.join(selectedBlueprintsDirectoryPath, selectedBlueprintFileName);
   const hasBlueprintProfileFile = availableBlueprintProfileFileNames.has(selectedBlueprintFileName);
   const blueprintSummary = hasBlueprintProfileFile

package/lib/cli/detector.mjs

@@ -8,6 +8,12 @@ import path from 'node:path';
 import { BLUEPRINT_RECOMMENDATIONS } from './constants.mjs';
 import { toTitleCase } from './utils.mjs';
 
+const FRONTEND_SCAN_DIRECTORY_NAMES = ['src', 'app', 'pages', 'components', 'styles'];
+const FRONTEND_SCAN_FILE_EXTENSIONS = new Set(['.js', '.jsx', '.ts', '.tsx', '.vue', '.css', '.scss', '.sass']);
+const FRONTEND_SCAN_IGNORE_DIRECTORY_NAMES = new Set(['.git', 'node_modules', '.next', 'dist', 'build', 'coverage']);
+const FRONTEND_FILE_SCAN_LIMIT = 200;
+const FRONTEND_FILE_SIZE_LIMIT_BYTES = 200_000;
+
 export async function collectProjectMarkers(targetDirectoryPath) {
   const markerNames = new Set();
   const directoryEntries = await fs.readdir(targetDirectoryPath, { withFileTypes: true });
@@ -34,6 +40,110 @@ async function readPackageJsonIfExists(targetDirectoryPath) {
   }
 }
 
+async function collectFrontendSourceFilePaths(directoryPath, collectedFilePaths = []) {
+  if (collectedFilePaths.length >= FRONTEND_FILE_SCAN_LIMIT) {
+    return collectedFilePaths;
+  }
+
+  let directoryEntries;
+  try {
+    directoryEntries = await fs.readdir(directoryPath, { withFileTypes: true });
+  } catch {
+    return collectedFilePaths;
+  }
+
+  for (const directoryEntry of directoryEntries) {
+    if (collectedFilePaths.length >= FRONTEND_FILE_SCAN_LIMIT) {
+      break;
+    }
+
+    if (directoryEntry.isDirectory()) {
+      if (FRONTEND_SCAN_IGNORE_DIRECTORY_NAMES.has(directoryEntry.name)) {
+        continue;
+      }
+
+      await collectFrontendSourceFilePaths(path.join(directoryPath, directoryEntry.name), collectedFilePaths);
+      continue;
+    }
+
+    const fileExtension = path.extname(directoryEntry.name).toLowerCase();
+    if (FRONTEND_SCAN_FILE_EXTENSIONS.has(fileExtension)) {
+      collectedFilePaths.push(path.join(directoryPath, directoryEntry.name));
+    }
+  }
+
+  return collectedFilePaths;
+}
+
+function countPatternMatches(sourceText, pattern) {
+  return Array.from(sourceText.matchAll(pattern)).length;
+}
+
+async function collectFrontendEvidenceMetrics(targetDirectoryPath, markerNames) {
+  const candidateDirectoryPaths = FRONTEND_SCAN_DIRECTORY_NAMES
+    .filter((directoryName) => markerNames.has(directoryName))
+    .map((directoryName) => path.join(targetDirectoryPath, directoryName));
+  const resolvedCandidateDirectoryPaths = candidateDirectoryPaths.length > 0
+    ? candidateDirectoryPaths
+    : [targetDirectoryPath];
+  const scannedFilePaths = [];
+
+  for (const candidateDirectoryPath of resolvedCandidateDirectoryPaths) {
+    await collectFrontendSourceFilePaths(candidateDirectoryPath, scannedFilePaths);
+    if (scannedFilePaths.length >= FRONTEND_FILE_SCAN_LIMIT) {
+      break;
+    }
+  }
+
+  let hardcodedColorCount = 0;
+  let propDrillingCandidateCount = 0;
+  let mediaQueryCount = 0;
+  let tailwindBreakpointUsageCount = 0;
+  let arbitraryBreakpointCount = 0;
+  const uniqueMediaWidths = new Set();
+
+  for (const scannedFilePath of scannedFilePaths) {
+    let sourceText;
+
+    try {
+      const fileStat = await fs.stat(scannedFilePath);
+      if (fileStat.size > FRONTEND_FILE_SIZE_LIMIT_BYTES) {
+        continue;
+      }
+
+      sourceText = await fs.readFile(scannedFilePath, 'utf8');
+    } catch {
+      continue;
+    }
+
+    hardcodedColorCount += countPatternMatches(
+      sourceText,
+      /#[0-9a-fA-F]{3,8}\b|rgba?\([^)]+\)|hsla?\([^)]+\)|oklch\([^)]+\)/g
+    );
+    propDrillingCandidateCount += countPatternMatches(
+      sourceText,
+      /<[A-Z][A-Za-z0-9_.:-]*(?:\s+[A-Za-z0-9_:-]+=\{[^}]+\}){5,}/g
+    );
+    mediaQueryCount += countPatternMatches(sourceText, /@media\b/g);
+    tailwindBreakpointUsageCount += countPatternMatches(sourceText, /\b(?:sm|md|lg|xl|2xl):/g);
+    arbitraryBreakpointCount += countPatternMatches(sourceText, /\b(?:min|max)-\[[^\]]+\]:/g);
+
+    for (const mediaWidthMatch of sourceText.matchAll(/\((?:min|max)-width:\s*([0-9.]+(?:px|rem|em))\)/g)) {
+      uniqueMediaWidths.add(mediaWidthMatch[1]);
+    }
+  }
+
+  return {
+    scannedFileCount: scannedFilePaths.length,
+    hardcodedColorCount,
+    propDrillingCandidateCount,
+    mediaQueryCount,
+    tailwindBreakpointUsageCount,
+    arbitraryBreakpointCount,
+    uniqueMediaWidthCount: uniqueMediaWidths.size,
+  };
+}
+
 export async function detectUiScopeSignals({
   targetDirectoryPath,
   selectedStackFileName,
@@ -62,6 +172,7 @@ export async function detectUiScopeSignals({
   }
 
   const directUiMarkerNames = [
+    'src',
     'next.config.js',
     'next.config.mjs',
     'next.config.ts',
@@ -112,13 +223,18 @@ export async function detectUiScopeSignals({
   ));
   const hasUiDependencies = detectedUiDependencies.length > 0;
   const hasStructuralUiMarkers = detectedUiMarkers.length >= 2;
+  const isUiScopeLikely = signalReasons.length > 0
+    && (hasStrongUiMarker || hasUiDependencies || hasStructuralUiMarkers || normalizedProjectScopeKey.length > 0);
+  const frontendEvidenceMetrics = isUiScopeLikely
+    ? await collectFrontendEvidenceMetrics(targetDirectoryPath, markerNames)
+    : null;
 
   return {
-    isUiScopeLikely: signalReasons.length > 0
-      && (hasStrongUiMarker || hasUiDependencies || hasStructuralUiMarkers || normalizedProjectScopeKey.length > 0),
+    isUiScopeLikely,
     signalReasons,
     detectedUiMarkers,
     detectedUiDependencies,
+    frontendEvidenceMetrics,
     packageManifest: resolvedPackageManifest,
   };
 }