@ryuenn3123/agentic-senior-core 2.5.22 → 3.0.0

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

@@ -16,15 +16,15 @@ Context: You are a Principal Software Architect operating in a workspace with st
 Step 1: Context Gathering
 1. Read `AGENTS.md` to understand your role and available knowledge base.
 2. Scan all files in `.agent-context/rules/` to understand our mandatory engineering laws.
-3. Review the available technology stacks in `.agent-context/stacks/` and blueprints in `.agent-context/blueprints/`.
+3. Review dynamic stack and architecture signals from project docs, repository evidence, and task constraints.
 
 Step 2: Architecture Proposal
 Based strictly on my project description and our repository's existing rules (especially `efficiency-vs-hype.md`):
-1. Propose the most efficient technology stack from our approved profiles.
+1. Propose the most efficient technology stack based on requirements and evidence.
 2. Explain WHY this stack is the best choice for this specific project.
 3. Draft a high-level architecture plan.
 
-Do not write any application code yet. Write your proposal and wait for my approval. Once I approve, you will scaffold the project using the relevant blueprint.
+Do not write any application code yet. Write your proposal and wait for my approval. Once I approve, you will scaffold the project using the selected architecture playbook.
 ```
 
 ---
@@ -38,8 +38,8 @@ I want to build [PROJECT NAME].
 Before writing any code:
 1. Read `AGENTS.md` to understand your role.
 2. Read ALL files in `.agent-context/rules/` to understand our engineering standards.
-3. Read `.agent-context/stacks/[STACK].md` for language-specific guidelines.
-4. Read `.agent-context/blueprints/[BLUEPRINT].md` for the project structure.
+3. Resolve language-specific guidance from dynamic stack signals.
+4. Resolve the project structure from the selected architecture playbook.
 
 Now scaffold the initial project structure following the blueprint exactly:
 - Create all directories and files from the blueprint

package/.agent-context/prompts/refactor.md

@@ -13,8 +13,9 @@ Before making changes:
 1. Read .agent-context/rules/architecture.md — ensure proper layer separation.
 2. Read .agent-context/rules/naming-conv.md — fix all naming violations.
 3. Read .agent-context/rules/error-handling.md — fix error handling patterns.
-4. Read .agent-context/stacks/typescript.md — fix TypeScript-specific issues.
+4. Resolve active language guidance from dynamic stack signals (TypeScript in this repository).
 5. Enforce backend universal principles: no clever hacks, no premature abstraction, readability over brevity.
+6. Enforce Universal SOP hard gate: stop implementation if `docs/architecture-decision-record.md` is missing, and for UI scope stop if `docs/DESIGN.md` is missing.
 
 For every change you make, provide a Reasoning Chain:
 - What was wrong (rule reference)

package/.agent-context/prompts/review-code.md

@@ -12,7 +12,7 @@ Run a comprehensive code review on the current codebase (or the files I'm about
 
 Use these checklists:
 1. Read .agent-context/review-checklists/pr-checklist.md — apply every item.
-2. Read .agent-context/review-checklists/security-audit.md — apply every item.
+2. Read .agent-context/review-checklists/architecture-review.md — apply every item.
 3. Apply documentation scope rules exactly: This applies to documentation, release notes, onboarding text, review summaries, and agent-facing explanations.
 4. Treat scope-style findings as advisory unless they hide factual errors, contract mismatches, or non-negotiable violations.
 5. Enforce documentation hard blockers on changed boundaries: public surface changes, API contract changes, and database structure changes must include synchronized documentation updates.
@@ -20,6 +20,7 @@ Use these checklists:
 7. Enforce cross-session consistency guardian: session handoff must include active architecture contract summary, drift detection must warn before direction changes, and direction changes require explicit user confirmation.
 8. Enforce explain-on-demand state visibility: default responses must avoid unnecessary state-file internals, state internals are exposed only on explicit request, and diagnostic mode must explain relevant state decisions when needed.
 9. Enforce single-source and lazy-loading policy: canonical rule source must be explicitly enforced, language-specific guidance must load lazily based on detected scope, and conflicting duplicate rule instructions must not appear during normal flow.
+10. Enforce Universal SOP hard gate: block coding flow when required project docs are missing (`docs/architecture-decision-record.md`, and for UI scope `docs/DESIGN.md`).
 
 For EVERY violation found:
 - State the exact file and line
@@ -44,7 +45,7 @@ If you want a faster review focusing on the most critical items:
 
 ```
 Quick review the current code. Check ONLY:
-1. Any use of `any` type? (rules/stacks/typescript.md)
+1. Any use of `any` type? (dynamic TypeScript stack guidance)
 2. Any empty catch blocks? (rules/error-handling.md)
 3. Any N+1 queries? (rules/performance.md)
 4. Any hardcoded secrets? (rules/security.md)

package/.agent-context/review-checklists/pr-checklist.md

@@ -44,7 +44,7 @@ VERDICT: PASS / FAIL (X/Y items passed)
 - [ ] No premature abstraction (base classes/util layers created only after repeated stable patterns)
 - [ ] Readability over brevity for maintainability (no compressed one-liners that hide intent)
 
-### 3. Type Safety (→ stacks/typescript.md)
+### 3. Type Safety (→ dynamic TypeScript stack guidance)
 - [ ] No `any` type anywhere (use `unknown` + narrowing)
 - [ ] No `// @ts-ignore` (use `@ts-expect-error` with justification comment)
 - [ ] All function return types are explicit
@@ -129,3 +129,10 @@ VERDICT: PASS / FAIL (X/Y items passed)
 - [ ] Canonical rule source is explicitly defined and enforced
 - [ ] Language-specific guidance is loaded lazily based on detected scope
 - [ ] No conflicting duplicate rule instructions during normal flow
+
+### 15. Universal SOP Consolidation
+- [ ] `.agent-context/rules/` remains the default guidance source for implementation and review
+- [ ] Backend and frontend mindset checks are both applied when scope spans API and UI boundaries
+- [ ] Security and testing requirements remain mandatory after static template purge
+- [ ] Coding flow is blocked if `docs/architecture-decision-record.md` (or `docs/Architecture-Decision-Record.md`) is missing
+- [ ] UI implementation flow is blocked if `docs/DESIGN.md` is missing

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

@@ -13,6 +13,17 @@ These principles are mandatory for backend and shared core modules.
 
 If a short and a clear implementation are functionally equivalent, choose the clear implementation.
 
+## Universal SOP Baseline (Mandatory)
+
+The `.agent-context/rules/` directory is the default guidance source for implementation and review.
+
+- Backend and frontend mindset checks are both required when a task spans API and UI boundaries.
+- Security and testing are non-negotiable baseline requirements.
+- Hard block before coding:
+  - `docs/architecture-decision-record.md` (alias: `docs/Architecture-Decision-Record.md`) must exist.
+  - For UI scope, `docs/DESIGN.md` must exist.
+- If required project context docs are missing, stop implementation and bootstrap docs before writing application code.
+
 ## Rules as Guardian (Cross-Session Consistency)
 
 These guardrails are mandatory to preserve architecture direction across sessions.

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

@@ -11,8 +11,8 @@ UI scope trigger signals (any one is enough):
 - feature requests that include frontend deliverables even when backend changes are also included
 
 Mandatory behavior when triggered:
-- apply frontend excellence rubric checks from `.agent-context/review-checklists/frontend-excellence-rubric.md`
-- apply usability checks from `.agent-context/review-checklists/frontend-usability.md`
+- apply consolidated review checks from `.agent-context/review-checklists/pr-checklist.md`
+- apply structural checks from `.agent-context/review-checklists/architecture-review.md`
 - score and review generated UI work against visual intent, interaction quality, and conversion clarity
 - reject template-only repetitive outputs and force a distinct layout direction
 

package/.agent-context/state/architecture-map.md

@@ -14,7 +14,7 @@
 
 ## Required Agent Behavior
 
-1. Before editing a `critical` area, load `.agent-context/review-checklists/security-audit.md` and `.agent-context/review-checklists/performance-audit.md`.
+1. Before editing a `critical` area, load `.agent-context/review-checklists/pr-checklist.md` and `.agent-context/review-checklists/architecture-review.md`.
 2. For boundary-crossing changes, verify no circular dependencies are introduced (see `dependency-map.md`).
 3. Every critical-path change must include explicit risk notes in PR description.
 

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

@@ -1,5 +1,5 @@
 {
-  "generatedAt": "2026-04-18T05:17:09.876Z",
+  "generatedAt": "2026-04-18T12:31:23.643Z",
   "reportName": "memory-continuity-benchmark",
   "schemaVersion": "1.0.0",
   "passed": true,

package/.agents/workflows/init-project.md

@@ -8,13 +8,13 @@ description: Initialize a new project using Agentic-Senior-Core blueprints and e
 
 1. Read all rule files from `.agent-context/rules/` to understand engineering standards.
 
-2. Read the language-specific profile from `.agent-context/stacks/` based on the project's tech stack.
+2. Resolve language-specific guidance from dynamic stack signals based on the project's goals and constraints.
 
-3. Read the chosen blueprint from `.agent-context/blueprints/` (e.g., `api-nextjs.md` or `nestjs-logic.md`).
+3. Resolve the chosen architecture playbook (e.g., `api-nextjs` or `nestjs-logic`).
 
 4. Scaffold the complete project structure following the blueprint exactly:
    - Create all directories and files
-   - Set up strict `tsconfig.json` (all flags from `stacks/typescript.md`)
+   - Set up strict `tsconfig.json` (using active TypeScript guidance)
    - Create `.env.example` with placeholder values
    - Set up Zod-validated environment config
    - Set up error handling foundation (base error class + global handler)

package/.agents/workflows/refactor.md

@@ -10,7 +10,7 @@ description: Refactor code or extract a module following architecture and naming
 
 3. Read `.agent-context/rules/error-handling.md` to understand error handling patterns.
 
-4. Read the active language profile from `.agent-context/stacks/` (e.g., `typescript.md`).
+4. Resolve the active language profile from dynamic stack signals (e.g., TypeScript guidance).
 
 5. Analyze the target code for violations:
    - Layer leaks (business logic in controllers, SQL in services)

package/.agents/workflows/review-code.md

@@ -1,12 +1,11 @@
----
-description: Run a comprehensive code review using PR checklist and security audit
+description: Run a comprehensive code review using PR and architecture checklists
 ---
 
 ## Workflow: Review Code
 
 1. Read `.agent-context/review-checklists/pr-checklist.md` and apply every item against the current codebase.
 
-2. Read `.agent-context/review-checklists/security-audit.md` and apply every item against the current codebase.
+2. Read `.agent-context/review-checklists/architecture-review.md` and apply every item against the current codebase.
 
 3. For every violation found, provide a Reasoning Chain:
    - State the exact file and line
@@ -21,8 +20,8 @@ description: Run a comprehensive code review using PR checklist and security aud
 - PASS or FAIL for each item
 - Reasoning Chain for each failure
 
-## SECURITY AUDIT RESULTS
-- Severity rating (CRITICAL / HIGH / MEDIUM / LOW) for each finding
+## ARCHITECTURE REVIEW RESULTS
+- Boundary violation summary and risk level for each finding
 - Specific remediation for each finding
 
 ## VERDICT: PASS or FAIL

package/.cursorrules

@@ -1,7 +1,7 @@
 # AGENTIC-SENIOR-CORE DYNAMIC GOVERNANCE RULESET
 
-Generated by Agentic-Senior-Core CLI v2.5.22
-Timestamp: 2026-04-18T03:00:00.000Z
+Generated by Agentic-Senior-Core CLI v3.0.0
+Timestamp: 2026-04-18T00:00:00.000Z
 Selected profile: beginner
 Selected policy file: .agent-context/policies/llm-judge-threshold.json
 
@@ -9,85 +9,41 @@ Selected policy file: .agent-context/policies/llm-judge-threshold.json
 1. Follow this compiled rulebook as the primary source.
 2. Resolve exceptions from .agent-override.md only when explicitly defined.
 3. Use architecture-map.md and dependency-map.md as change safety boundaries.
-4. Enforce pr-checklist.md before declaring completion.
-
-## OVERRIDE PROTOCOL
-- Default: strict compliance with this file.
-- Exception path: .agent-override.md may explicitly allow narrow deviations.
-- Scope policy: every override must include module scope, rationale, and expiry date.
+4. Enforce pr-checklist.md and architecture-review.md before declaring completion.
 
 ## BOOTSTRAP CHAIN (MANDATORY)
 Load every layer before responding. Do not skip steps:
 1. .agent-context/rules/
-2. .agent-context/stacks/
-3. .agent-context/blueprints/
-4. .agent-context/skills/
-5. .agent-context/prompts/
-6. .agent-context/profiles/
-7. .agent-context/state/
-8. .agent-context/policies/llm-judge-threshold.json
+2. Dynamic stack strategy signals from project context and live evidence.
+3. Dynamic architecture playbook signals from requirements and repository state.
+4. .agent-context/prompts/
+5. .agent-context/review-checklists/
+6. .agent-context/state/
+7. .agent-context/policies/llm-judge-threshold.json
+8. docs/ project context (or bootstrap prompts when docs are not materialized)
 
 Primary entrypoint: .cursorrules
 Mirror entrypoint: .windsurfrules
 Canonical baseline: .instructions.md
-## LAYER 1: UNIVERSAL RULES (MANDATORY)
-Read every file under .agent-context/rules/ before implementation:
-1. .agent-context/rules/api-docs.md
-2. .agent-context/rules/architecture.md
-3. .agent-context/rules/database-design.md
-4. .agent-context/rules/efficiency-vs-hype.md
-5. .agent-context/rules/error-handling.md
-6. .agent-context/rules/event-driven.md
-7. .agent-context/rules/frontend-architecture.md
-8. .agent-context/rules/git-workflow.md
-9. .agent-context/rules/microservices.md
-10. .agent-context/rules/naming-conv.md
-11. .agent-context/rules/performance.md
-12. .agent-context/rules/realtime.md
-13. .agent-context/rules/security.md
-14. .agent-context/rules/testing.md
 
+## LAYER 1: UNIVERSAL RULES (MANDATORY)
+Read every file under .agent-context/rules/ before implementation.
 Conflict resolution: prioritize data safety and API contract integrity first, then writing polish.
-## LAYER 2: STACK PROFILE (typescript.md)
-Source: .agent-context/stacks/typescript.md
-Summary: TypeScript Stack Profile — The "Galak" Standard
-Load this stack profile to enforce language-specific conventions.
-## LAYER 3: BLUEPRINT PROFILE (api-nextjs.md)
-Source: .agent-context/blueprints/api-nextjs.md
-Summary: Blueprint: Next.js API Project (App Router)
-Load this blueprint when scaffolding or changing architecture boundaries.
-## LAYER 3B: CI/CD GUARDRAILS
-Load these CI blueprints when pipeline or release logic is touched:
-1. .agent-context/blueprints/ci-github-actions.md
-2. .agent-context/blueprints/ci-gitlab.md
-## SKILL PACK: Frontend
-Source: .agent-context/skills/frontend.md
-Default tier: advance
-Selected tier: advance
-Evidence: Frontend usability audit, accessibility checks, and visual regression output.
-Purpose: Unified frontend delivery covering UI architecture, motion, accessibility, and conversion clarity.
-Load this skill pack and apply every Must-Have Check.
-## SKILL PACK: Fullstack
-Source: .agent-context/skills/fullstack.md
-Default tier: advance
-Selected tier: advance
-Evidence: End-to-end tests, contract validation, and feature parity review.
-Purpose: Single-path product delivery across frontend and backend boundaries.
-Load this skill pack and apply every Must-Have Check.
-## SKILL PACK: CLI
-Source: .agent-context/skills/cli.md
-Default tier: advance
-Selected tier: advance
-Evidence: CLI smoke tests, dry-run output, and automation-friendly reports.
-Purpose: Smart command-line delivery with safe defaults, machine-readable output, and upgrade flows.
-Load this skill pack and apply every Must-Have Check.
-## LAYER 7: STATE AWARENESS (MANDATORY)
-Load these files before touching critical paths:
-1. .agent-context/state/architecture-map.md
-2. .agent-context/state/dependency-map.md
-Use these maps to prevent unsafe cross-module changes.
+
+## LAYER 2 POLICY: DYNAMIC STACK STRATEGY
+Resolve stack guidance lazily from project evidence. Do not depend on deleted static stack directories.
+
+## LAYER 3 POLICY: DYNAMIC ARCHITECTURE PLAYBOOKS
+Resolve architecture guidance lazily from project docs and task boundaries. Do not depend on deleted static blueprint directories.
+
+## STATE AWARENESS (MANDATORY)
+Load .agent-context/state/architecture-map.md and .agent-context/state/dependency-map.md before touching critical paths.
+
 ## REVIEW CHECKLISTS (MANDATORY)
 1. .agent-context/review-checklists/pr-checklist.md
-2. .agent-context/review-checklists/security-audit.md (when security-sensitive)
-3. .agent-context/review-checklists/performance-audit.md (when perf-critical)
+2. .agent-context/review-checklists/architecture-review.md
 Do not claim done before checklist pass.
+
+## UNIVERSAL SOP HARD GATES
+- Stop coding if docs/architecture-decision-record.md (or docs/Architecture-Decision-Record.md) is missing.
+- For UI scope, stop coding if docs/DESIGN.md is missing.

package/.gemini/instructions.md

@@ -2,7 +2,7 @@
 
 Adapter Mode: thin
 Adapter Source: .instructions.md
-Canonical Snapshot SHA256: 2a2a036b4fb90f9e668163b83614f2339044c0d021a6eaf2f380e626dfe72de0
+Canonical Snapshot SHA256: 354edbbfaedec284ddcc6d4a5bb5393a7f5385650d1a6ae84a2d9633b5a6d10d
 
 Canonical policy source: [.instructions.md](../.instructions.md).
 
@@ -10,12 +10,11 @@ Canonical policy source: [.instructions.md](../.instructions.md).
 
 1. Load [.instructions.md](../.instructions.md) first.
 2. Apply baseline rules from [.agent-context/rules/](../.agent-context/rules).
-3. Load language profile from [.agent-context/stacks/](../.agent-context/stacks).
-4. Use [.agent-context/blueprints/](../.agent-context/blueprints) when creating new modules/projects.
-5. Load domain skills from [.agent-context/skills/](../.agent-context/skills).
-6. Load request templates from [.agent-context/prompts/](../.agent-context/prompts).
-7. Apply team defaults from [.agent-context/profiles/](../.agent-context/profiles), state awareness from [.agent-context/state/](../.agent-context/state), and policy thresholds from [.agent-context/policies/](../.agent-context/policies).
+3. Load request templates from [.agent-context/prompts/](../.agent-context/prompts).
+4. Apply review contracts from [.agent-context/review-checklists/](../.agent-context/review-checklists).
+5. Apply state awareness from [.agent-context/state/](../.agent-context/state) and policy thresholds from [.agent-context/policies/](../.agent-context/policies).
+6. Resolve stack and architecture choices dynamically from project context docs plus live evidence.
 
 ## Completion Gate
 
-Run [.agent-context/review-checklists/pr-checklist.md](../.agent-context/review-checklists/pr-checklist.md) before declaring completion.
+Run [.agent-context/review-checklists/pr-checklist.md](../.agent-context/review-checklists/pr-checklist.md) before declaring completion.

package/.github/copilot-instructions.md

@@ -2,7 +2,7 @@
 
 Adapter Mode: thin
 Adapter Source: .instructions.md
-Canonical Snapshot SHA256: 2a2a036b4fb90f9e668163b83614f2339044c0d021a6eaf2f380e626dfe72de0
+Canonical Snapshot SHA256: 354edbbfaedec284ddcc6d4a5bb5393a7f5385650d1a6ae84a2d9633b5a6d10d
 
 The canonical policy source for this repository is [.instructions.md](../.instructions.md).
 
@@ -10,11 +10,10 @@ The canonical policy source for this repository is [.instructions.md](../.instru
 
 1. Read [.instructions.md](../.instructions.md) first.
 2. Read baseline rules in [.agent-context/rules/](../.agent-context/rules).
-3. Load language profile from [.agent-context/stacks/](../.agent-context/stacks).
-4. Load blueprints from [.agent-context/blueprints/](../.agent-context/blueprints) for scaffolding requests.
-5. Load domain skills from [.agent-context/skills/](../.agent-context/skills).
-6. Load request templates from [.agent-context/prompts/](../.agent-context/prompts).
-7. Apply team defaults from [.agent-context/profiles/](../.agent-context/profiles), state awareness from [.agent-context/state/](../.agent-context/state), and thresholds from [.agent-context/policies/](../.agent-context/policies).
+3. Load request templates from [.agent-context/prompts/](../.agent-context/prompts).
+4. Apply review contracts from [.agent-context/review-checklists/](../.agent-context/review-checklists).
+5. Apply state awareness from [.agent-context/state/](../.agent-context/state) and thresholds from [.agent-context/policies/](../.agent-context/policies).
+6. Resolve stack and architecture choices dynamically from project context docs plus live evidence.
 
 ## Completion Gate
 

package/.windsurfrules

@@ -1,7 +1,7 @@
 # AGENTIC-SENIOR-CORE DYNAMIC GOVERNANCE RULESET
 
-Generated by Agentic-Senior-Core CLI v2.5.22
-Timestamp: 2026-04-18T03:00:00.000Z
+Generated by Agentic-Senior-Core CLI v3.0.0
+Timestamp: 2026-04-18T00:00:00.000Z
 Selected profile: beginner
 Selected policy file: .agent-context/policies/llm-judge-threshold.json
 
@@ -9,85 +9,41 @@ Selected policy file: .agent-context/policies/llm-judge-threshold.json
 1. Follow this compiled rulebook as the primary source.
 2. Resolve exceptions from .agent-override.md only when explicitly defined.
 3. Use architecture-map.md and dependency-map.md as change safety boundaries.
-4. Enforce pr-checklist.md before declaring completion.
-
-## OVERRIDE PROTOCOL
-- Default: strict compliance with this file.
-- Exception path: .agent-override.md may explicitly allow narrow deviations.
-- Scope policy: every override must include module scope, rationale, and expiry date.
+4. Enforce pr-checklist.md and architecture-review.md before declaring completion.
 
 ## BOOTSTRAP CHAIN (MANDATORY)
 Load every layer before responding. Do not skip steps:
 1. .agent-context/rules/
-2. .agent-context/stacks/
-3. .agent-context/blueprints/
-4. .agent-context/skills/
-5. .agent-context/prompts/
-6. .agent-context/profiles/
-7. .agent-context/state/
-8. .agent-context/policies/llm-judge-threshold.json
+2. Dynamic stack strategy signals from project context and live evidence.
+3. Dynamic architecture playbook signals from requirements and repository state.
+4. .agent-context/prompts/
+5. .agent-context/review-checklists/
+6. .agent-context/state/
+7. .agent-context/policies/llm-judge-threshold.json
+8. docs/ project context (or bootstrap prompts when docs are not materialized)
 
 Primary entrypoint: .cursorrules
 Mirror entrypoint: .windsurfrules
 Canonical baseline: .instructions.md
-## LAYER 1: UNIVERSAL RULES (MANDATORY)
-Read every file under .agent-context/rules/ before implementation:
-1. .agent-context/rules/api-docs.md
-2. .agent-context/rules/architecture.md
-3. .agent-context/rules/database-design.md
-4. .agent-context/rules/efficiency-vs-hype.md
-5. .agent-context/rules/error-handling.md
-6. .agent-context/rules/event-driven.md
-7. .agent-context/rules/frontend-architecture.md
-8. .agent-context/rules/git-workflow.md
-9. .agent-context/rules/microservices.md
-10. .agent-context/rules/naming-conv.md
-11. .agent-context/rules/performance.md
-12. .agent-context/rules/realtime.md
-13. .agent-context/rules/security.md
-14. .agent-context/rules/testing.md
 
+## LAYER 1: UNIVERSAL RULES (MANDATORY)
+Read every file under .agent-context/rules/ before implementation.
 Conflict resolution: prioritize data safety and API contract integrity first, then writing polish.
-## LAYER 2: STACK PROFILE (typescript.md)
-Source: .agent-context/stacks/typescript.md
-Summary: TypeScript Stack Profile — The "Galak" Standard
-Load this stack profile to enforce language-specific conventions.
-## LAYER 3: BLUEPRINT PROFILE (api-nextjs.md)
-Source: .agent-context/blueprints/api-nextjs.md
-Summary: Blueprint: Next.js API Project (App Router)
-Load this blueprint when scaffolding or changing architecture boundaries.
-## LAYER 3B: CI/CD GUARDRAILS
-Load these CI blueprints when pipeline or release logic is touched:
-1. .agent-context/blueprints/ci-github-actions.md
-2. .agent-context/blueprints/ci-gitlab.md
-## SKILL PACK: Frontend
-Source: .agent-context/skills/frontend.md
-Default tier: advance
-Selected tier: advance
-Evidence: Frontend usability audit, accessibility checks, and visual regression output.
-Purpose: Unified frontend delivery covering UI architecture, motion, accessibility, and conversion clarity.
-Load this skill pack and apply every Must-Have Check.
-## SKILL PACK: Fullstack
-Source: .agent-context/skills/fullstack.md
-Default tier: advance
-Selected tier: advance
-Evidence: End-to-end tests, contract validation, and feature parity review.
-Purpose: Single-path product delivery across frontend and backend boundaries.
-Load this skill pack and apply every Must-Have Check.
-## SKILL PACK: CLI
-Source: .agent-context/skills/cli.md
-Default tier: advance
-Selected tier: advance
-Evidence: CLI smoke tests, dry-run output, and automation-friendly reports.
-Purpose: Smart command-line delivery with safe defaults, machine-readable output, and upgrade flows.
-Load this skill pack and apply every Must-Have Check.
-## LAYER 7: STATE AWARENESS (MANDATORY)
-Load these files before touching critical paths:
-1. .agent-context/state/architecture-map.md
-2. .agent-context/state/dependency-map.md
-Use these maps to prevent unsafe cross-module changes.
+
+## LAYER 2 POLICY: DYNAMIC STACK STRATEGY
+Resolve stack guidance lazily from project evidence. Do not depend on deleted static stack directories.
+
+## LAYER 3 POLICY: DYNAMIC ARCHITECTURE PLAYBOOKS
+Resolve architecture guidance lazily from project docs and task boundaries. Do not depend on deleted static blueprint directories.
+
+## STATE AWARENESS (MANDATORY)
+Load .agent-context/state/architecture-map.md and .agent-context/state/dependency-map.md before touching critical paths.
+
 ## REVIEW CHECKLISTS (MANDATORY)
 1. .agent-context/review-checklists/pr-checklist.md
-2. .agent-context/review-checklists/security-audit.md (when security-sensitive)
-3. .agent-context/review-checklists/performance-audit.md (when perf-critical)
+2. .agent-context/review-checklists/architecture-review.md
 Do not claim done before checklist pass.
+
+## UNIVERSAL SOP HARD GATES
+- Stop coding if docs/architecture-decision-record.md (or docs/Architecture-Decision-Record.md) is missing.
+- For UI scope, stop coding if docs/DESIGN.md is missing.

package/AGENTS.md

@@ -2,7 +2,7 @@
 
 Adapter Mode: thin
 Adapter Source: .instructions.md
-Canonical Snapshot SHA256: 2a2a036b4fb90f9e668163b83614f2339044c0d021a6eaf2f380e626dfe72de0
+Canonical Snapshot SHA256: 354edbbfaedec284ddcc6d4a5bb5393a7f5385650d1a6ae84a2d9633b5a6d10d
 
 This file is an adapter entrypoint for agent discovery.
 The canonical policy source is [.instructions.md](.instructions.md).
@@ -11,13 +11,11 @@ The canonical policy source is [.instructions.md](.instructions.md).
 
 1. Load [.instructions.md](.instructions.md) first as the single source of truth.
 2. Read baseline governance from [.agent-context/rules/](.agent-context/rules).
-3. Load language conventions from [.agent-context/stacks/](.agent-context/stacks).
-4. Load scaffolding references from [.agent-context/blueprints/](.agent-context/blueprints) when creating modules/projects.
-5. Load domain packs from [.agent-context/skills/](.agent-context/skills).
-6. Apply request templates from [.agent-context/prompts/](.agent-context/prompts).
-7. Apply team governance defaults from [.agent-context/profiles/](.agent-context/profiles).
-8. Read change-risk maps from [.agent-context/state/](.agent-context/state).
-9. Enforce policy thresholds from [.agent-context/policies/](.agent-context/policies).
+3. Apply request templates from [.agent-context/prompts/](.agent-context/prompts).
+4. Enforce review contracts from [.agent-context/review-checklists/](.agent-context/review-checklists).
+5. Read change-risk maps and continuity state from [.agent-context/state/](.agent-context/state).
+6. Enforce policy thresholds from [.agent-context/policies/](.agent-context/policies).
+7. Use dynamic stack and architecture reasoning from project context docs and live research signals.
 
 ## Trigger Rules
 
@@ -25,4 +23,4 @@ The canonical policy source is [.instructions.md](.instructions.md).
 - Refactor or fix requests: propose plan first, then execute safely.
 - Completion: run [.agent-context/review-checklists/pr-checklist.md](.agent-context/review-checklists/pr-checklist.md) before declaring done.
 
-If this adapter drifts from canonical behavior, refresh from [.instructions.md](.instructions.md) and update the hash metadata.
+If this adapter drifts from canonical behavior, refresh from [.instructions.md](.instructions.md) and update the hash metadata.

package/CONTRIBUTING.md

@@ -9,8 +9,8 @@ Thanks for wanting to make AI agents write better code. Here's how to contribute
 | Type | Where | Description |
 |------|-------|-------------|
 | New rule | `.agent-context/rules/` | Universal engineering standard |
-| New stack | `.agent-context/stacks/` | Language-specific profile (Python, Go, Java, etc.) |
-| New blueprint | `.agent-context/blueprints/` | Project scaffolding template |
+| Stack strategy update | `.agent-context/rules/`, `.agent-context/state/stack-research-snapshot.json` | Dynamic language/runtime guidance and evidence |
+| Architecture playbook update | `.agent-context/prompts/`, `lib/cli/compiler.mjs` | Dynamic scaffolding and project-context guidance |
 | New checklist | `.agent-context/review-checklists/` | Self-audit guide |
 | State intelligence update | `.agent-context/state/` | Architecture boundaries and dependency map |
 | Override policy update | `.agent-override.md` | Scoped enterprise rule exceptions |
@@ -44,36 +44,23 @@ If all three are "yes", it belongs here.
 
 ---
 
-## How to Add a New Stack Profile (e.g., Python)
-
-1. Create `.agent-context/stacks/python.md`
-2. Follow the structure of `stacks/typescript.md`:
-   - Compiler/linter configuration (non-negotiable settings)
-   - Type system rules (the equivalent of "ban any")
-   - Validation at boundaries (Pydantic, marshmallow, etc.)
-   - Import conventions
-   - Async patterns
-   - Preferred libraries with justification
-   - Banned patterns with alternatives
-3. Update `AGENTS.md` to add the new stack to the manifest table
-4. Run `bun scripts/validate.ts` to verify everything links correctly
-5. Open a PR
+## How to Add or Adjust Stack Strategy Signals (e.g., Python)
+
+1. Update relevant universal guidance in `.agent-context/rules/` (typing, validation, architecture constraints).
+2. Add or adjust measurable stack evidence in `.agent-context/state/stack-research-snapshot.json`.
+3. Update stack-facing wording in prompts or CLI output when behavior changes.
+4. Run `npm run validate` to verify references and policy checks.
+5. Open a PR.
 
 ---
 
-## How to Add a New Blueprint
-
-1. Create `.agent-context/blueprints/<framework-name>.md`
-2. Include:
-   - Tech stack summary
-   - Complete directory structure
-   - Code patterns for each layer (with full examples)
-   - Environment validation setup
-   - Error handling setup
-   - Scaffolding checklist
-3. Update `AGENTS.md` manifest
-4. Update `prompts/init-project.md` available blueprints table
-5. Validate and PR
+## How to Add or Adjust Architecture Playbooks
+
+1. Update the architecture options in `.agent-context/prompts/init-project.md` and related discovery guidance.
+2. Update compiler/init behavior if generated project-context guidance or bootstrap flow changes.
+3. Keep transport/service/repository separation and validation boundaries explicit in examples.
+4. Run `npm run validate` and `npm test`.
+5. Open a PR.
 
 ---
 
@@ -96,7 +83,7 @@ If all three are "yes", it belongs here.
 1. **Fork** the repository
 2. **Branch** from `main`: `feat/add-python-stack` or `docs/fix-security-typo`
 3. **Write** your content following the quality standard above
-4. **Validate**: `bun scripts/validate.ts` must pass
+4. **Validate**: `npm run validate` must pass
 5. **Commit** with Conventional Commits: `feat(stacks): add Python profile`
 6. **Open PR** with:
    - What you added/changed
@@ -123,7 +110,7 @@ git clone https://github.com/fatidaprilian/Agentic-Senior-Core.git
 cd Agentic-Senior-Core
 
 # Validate
-bun run validate
+npm run validate
 
 # Test interactive CLI
 node ./bin/agentic-senior-core.js init /tmp/test-project