tribunal-kit 9.2.5 → 9.2.7

package/.agents/skills/antfu-conventions/SKILL.md

@@ -1,26 +1,51 @@
----
-name: antfu-conventions
-description: "Use when Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects: ESM-first, zero-config, type-safe, and clean tooling standards."
-version: 5.0.0
-last-updated: 2026-09-13
-skills:
-  - clean-code
-  - typescript-advanced
-  - monorepo-management
-tools: Read, Grep, Glob, Bash, Edit, Write
-scripts-binding:
-  - .agent/scripts/lint_runner.js
-  - .agent/scripts/verify_all.js
----
-
-# Antfu Conventions — ESM-First & Opinionated Modern Tooling
-
----
-
-## 🛠️ Technical Architecture & Reference Recipes
-
+---
+name: antfu-conventions
+description: "Use when executing, coordinating, planning, or reviewing antfu conventions agent workflows, cognitive loops, and architecture standards."
+version: 6.0.0
+last-updated: 2026-09-29
+skills:
+  - clean-code
+  - typescript-advanced
+  - monorepo-management
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
+---
+
+# Antfu Conventions — ESM-First & Opinionated Modern Tooling
+
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `antfu-conventions` domain, inspect these 5 critical parameters:
+1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
+2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
+3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
+4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
+5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
+
+
+## Activation Boundaries
+- **Activate when:** Use when executing, coordinating, planning, or reviewing antfu conventions agent workflows, cognitive loops, and architecture standards.
+- **DO NOT activate when:** The task falls outside the `antfu-conventions` domain or is managed by a different dedicated specialist agent.
+
+
+## 🔁 Multi-Pass Execution Protocol
+
+| Pass | Phase | Core Action | Adaptive Depth |
+|:---|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
+| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
+| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
+| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
+| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |
+
+
 ---
 
+## 🛠️ Technical Architecture & Reference Recipes
+
 ---
 
 ## 4 Core Tooling Conventions
@@ -51,4 +76,49 @@ export default antfu({
 
 ### 4. Explicit Type Imports (`import type`)
 
-- Enforce `import type { User } from './types'` to allow tree-shaking compilers (esbuild/tsdown) to strip type imports cleanly without runtime side effects.
+- Enforce `import type { User } from './types'` to allow tree-shaking compilers (esbuild/tsdown) to strip type imports cleanly without runtime side effects.
+
+## 🚨 Edge-Case & Failure Mode Matrix
+
+| Scenario | Risk | Production Mitigation |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
+
+
+## 🤖 LLM-Specific Traps Table
+
+| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
+|:---|:---|:---|
+| **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
+| **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
+| **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
+
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `orchestrator` · `agent-organizer` · `logic-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
+
+### 🔬 Evidence Standard (Tri-State Verification)
+Every finding, audit statement, or completion claim must classify its factual certainty:
+- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
+- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
+- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.
+
+### ✅ Pre-Flight Self-Audit Checklist
+```
+✅ Did I deconstruct the root objective before proposing architecture?
+✅ Did I identify dependencies, bottlenecks, and parallelizable sub-tasks?
+✅ Did I avoid over-engineering and select the simplest effective pattern?
+✅ Did I verify assumptions with concrete file reads instead of speculation?
+✅ Did I establish measurable verification criteria before completion?
+```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agents/skills/anti-slop-enforcement/SKILL.md

@@ -0,0 +1,118 @@
+---
+name: anti-slop-enforcement
+description: "Use when Tribunal extraction of the anti-slop rule sets. Enforces Purpose-Gates, Hard-Gates, and Liveliness Dials for UI engineering."
+version: 6.0.0
+last-updated: 2026-09-29
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
+---
+
+# Anti-Slop Enforcement Guidelines
+
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `anti-slop-enforcement` domain, inspect these 5 critical parameters:
+1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
+2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
+3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
+4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
+5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
+
+
+## Activation Boundaries
+- **Activate when:** Use when Tribunal extraction of the anti-slop rule sets. Enforces Purpose-Gates, Hard-Gates, and Liveliness Dials for UI engineering.
+- **DO NOT activate when:** The task falls outside the `anti-slop-enforcement` domain or is managed by a different dedicated specialist agent.
+
+
+## 🔁 Multi-Pass Execution Protocol
+
+| Pass | Phase | Core Action | Adaptive Depth |
+|:---|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
+| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
+| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
+| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
+| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |
+
+
+This skill provides the definition for what constitutes "slop" and how to enforce intentionality.
+
+## 1. The Liveliness Dials
+Before writing any UI code, the agent MUST articulate the following three dials:
+
+- **ENERGY (1-3):**
+  - `1`: Baseline, calm, muted (Corporate, B2B SaaS).
+  - `2`: Bright, punchy, confident (Modern Developer Tool).
+  - `3`: Maximalist, high-contrast, aggressive (Consumer App, Hype Landing Page).
+
+- **RHYTHM (1-3):**
+  - `1`: Uniform, standard grids, predictable alignment.
+  - `2`: Syncopated, broken-grid elements, overlapping layers, dynamic spacing.
+  - `3`: Chaotic, brutalist, anti-alignment.
+
+- **MOTION (1-3):**
+  - `1`: Static, CSS hover only.
+  - `2`: Micro-interactions, route transitions (Framer Motion / View Transitions).
+  - `3`: Heavy scroll-jacking, GSAP, spring physics orchestration.
+
+## 2. Hard Gates (Absolute Bans)
+Do not allow these under any circumstances:
+1. **The Purple Cliché:** Using `#8B5CF6`, `violet-500`, or purple-to-blue mesh gradients as a default "tech" aesthetic.
+2. **Fake Data:** Generating fake statistics ("10,000+ users", "5-star rating") unless provided in the prompt.
+3. **Card-in-Card Mud:** Cards nested inside cards with the same background color and no border/shadow contrast.
+4. **Hex Hacks:** Using raw hex codes instead of the design system's variables (e.g., `oklch`).
+
+## 3. Purpose-Gates (Allowed only with stated purpose)
+These techniques are permitted ONLY IF the agent writes down a one-line reason (purpose) before generating the code:
+1. **Glassmorphism (`backdrop-filter: blur`)**: Must state *why* the layer beneath needs to be partially visible.
+2. **Gradients**: Must state *why* a solid color wasn't enough (e.g., "Using subtle gradient to indicate depth on the active tab").
+3. **Bento Grids**: Must state *why* the data requires a multi-column irregular grid instead of a standard list or card array.
+4. **Shadows > 20px**: Must state the z-index hierarchy reasoning for the massive shadow.
+
+## 🚨 Edge-Case & Failure Mode Matrix
+
+| Scenario | Risk | Production Mitigation |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
+
+
+## 🤖 LLM-Specific Traps Table
+
+| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
+|:---|:---|:---|
+| **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
+| **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
+| **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |
+
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `frontend-reviewer` · `type-safety` · `ui-ux-auditor` · `complexity-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
+
+### 🔬 Evidence Standard (Tri-State Verification)
+Every finding, audit statement, or completion claim must classify its factual certainty:
+- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
+- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
+- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.
+
+### ✅ Pre-Flight Self-Audit Checklist
+```
+✅ Are all component props strictly typed with zero implicit "any"?
+✅ Are responsive breakpoints, fluid typography, and optical balance verified?
+✅ Is accessibility (ARIA labels, keyboard navigation, contrast ratio >= 4.5:1) validated?
+✅ Are re-renders minimized and state lifecycles cleanly separated?
+✅ Did I verify all imported UI components and icon sets actually exist?
+```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agents/skills/api-patterns/SKILL.md

@@ -1,26 +1,51 @@
----
-name: api-patterns
-description: "Use when API design mastery. REST, GraphQL, tRPC, and gRPC selection. Request/response design, pagination (cursor/offset), filtering, versioning, rate limiting, error formats (RFC 9457), authentication (JWT/OAuth2/API keys), idempotency, file uploads, webhooks, and OpenAPI documentation. Use when designing APIs, choosing protocols, or implementing API standards."
-version: 5.0.0
-last-updated: 2026-09-13
-skills:
-  - api-security-auditor
-  - backend-security-expert
-  - schema-reviewer
-tools: Read, Grep, Glob, Bash, Edit, Write
-scripts-binding:
-  - .agent/scripts/lint_runner.js
-  - .agent/scripts/verify_all.js
----
-
-# API Patterns — Design & Protocol Mastery
-
----
-
-## 🛠️ Technical Architecture & Reference Recipes
-
+---
+name: api-patterns
+description: "Use when designing, implementing, auditing, and hardening api patterns server logic, APIs, background jobs, and error boundaries."
+version: 6.0.0
+last-updated: 2026-09-29
+skills:
+  - api-security-auditor
+  - backend-security-expert
+  - schema-reviewer
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
+---
+
+# API Patterns — Design & Protocol Mastery
+
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `api-patterns` domain, inspect these 5 critical parameters:
+1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
+2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
+3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
+4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
+5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
+
+
+## Activation Boundaries
+- **Activate when:** Use when designing, implementing, auditing, and hardening api patterns server logic, APIs, background jobs, and error boundaries.
+- **DO NOT activate when:** The task falls outside the `api-patterns` domain or is managed by a different dedicated specialist agent.
+
+
+## 🔁 Multi-Pass Execution Protocol
+
+| Pass | Phase | Core Action | Adaptive Depth |
+|:---|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
+| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
+| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
+| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
+| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |
+
+
 ---
 
+## 🛠️ Technical Architecture & Reference Recipes
+
 ## Hallucination Traps (Read First)
 
 - ❌ JWT in URL query params → ✅ `Authorization: Bearer` header only. Query params get logged in server access logs.
@@ -215,4 +240,40 @@ Protect against:
 | **Session**                                     | Traditional server-rendered apps       |
 | **OAuth 2.0 / OIDC**                            | Third-party login, delegated access    |
 | **API Key**                                     | Server-to-server, public API consumers |
-| **Passkey (WebAuthn)**                          | Modern passwordless (2026+)            |
+| **Passkey (WebAuthn)**                          | Modern passwordless (2026+)            |
+
+## 🚨 Edge-Case & Failure Mode Matrix
+
+| Scenario | Risk | Production Mitigation |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
+
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `logic-reviewer` · `security-auditor` · `api-architect` · `resilience-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
+
+### 🔬 Evidence Standard (Tri-State Verification)
+Every finding, audit statement, or completion claim must classify its factual certainty:
+- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
+- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
+- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.
+
+### ✅ Pre-Flight Self-Audit Checklist
+```
+✅ Are all inputs and boundary payloads validated against schemas (Zod/Pydantic)?
+✅ Are SQL and database queries parameterized with zero string concatenation?
+✅ Are error boundaries and timeout/retry policies explicitly declared?
+✅ Are authentication and object-level authorization (IDOR/BOLA) checked before business logic?
+✅ Did I verify that imported dependencies exist in package manifests?
+```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agents/skills/api-security-auditor/SKILL.md

@@ -1,26 +1,59 @@
----
-name: api-security-auditor
-description: "Use when API Security auditing mastery. Rate limiting architecture, API key management, payload validation, IDOR (Insecure Direct Object Reference) prevention, mass assignment flaws, GraphQL security, and server-side mitigations. Use when building external APIs, B2B services, or reviewing endpoint security."
-version: 5.0.0
-last-updated: 2026-09-13
-skills:
-  - backend-security-expert
-  - vulnerability-scanner
-  - schema-reviewer
-tools: Read, Grep, Glob, Bash, Edit, Write
-scripts-binding:
-  - .agent/scripts/lint_runner.js
-  - .agent/scripts/verify_all.js
----
-
-# API Security Auditor — Endpoint Hardening Mastery
-
----
-
-## 🛠️ Technical Architecture & Reference Recipes
-
----
-
+---
+name: api-security-auditor
+description: "Use when designing, implementing, auditing, and hardening api security auditor server logic, APIs, background jobs, and error boundaries."
+version: 6.0.0
+last-updated: 2026-09-29
+skills:
+  - backend-security-expert
+  - vulnerability-scanner
+  - schema-reviewer
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
+---
+
+# API Security Auditor — Endpoint Hardening Mastery
+
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `api-security-auditor` domain, inspect these 5 critical parameters:
+1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
+2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
+3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
+4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
+5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
+
+
+## Activation Boundaries
+- **Activate when:** Use when designing, implementing, auditing, and hardening api security auditor server logic, APIs, background jobs, and error boundaries.
+- **DO NOT activate when:** The task falls outside the `api-security-auditor` domain or is managed by a different dedicated specialist agent.
+
+
+## 🔁 Multi-Pass Execution Protocol
+
+| Pass | Phase | Core Action | Adaptive Depth |
+|:---|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
+| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
+| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
+| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
+| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |
+
+
+## ⚠️ Tribunal Audit Constraints (MANDATORY)
+When performing audits, you MUST adhere to the following rules:
+- **Do not speculate.** Only report vulnerabilities you can prove exist in the code.
+- **Do not report generic best practices as vulnerabilities.** (e.g., "Consider adding rate limiting" is not a vulnerability unless you are specifically tasked with a rate limiting audit).
+- **Provide source evidence.** Quote the exact line of code that causes the issue.
+- **Provide exact location where possible.** (File and line number).
+- **Separate observation from impact.** Clearly distinguish what the code does from what an attacker could do.
+- **Use the approved finding schema.** Output all findings strictly using the Machine-Readable Finding Contract (`id`, `category`, `severity`, `confidence`, `status`, `title`, `location`, `evidence`, `impact`, `remediation`, `validation`).
+
+
+## 🛠️ Technical Architecture & Reference Recipes
+
 ---
 
 ## Insecure Direct Object Reference (IDOR)
@@ -152,4 +185,49 @@ const server = new ApolloServer({
   schema,
   introspection: process.env.NODE_ENV !== 'production',
 });
-```
+```
+
+## 🚨 Edge-Case & Failure Mode Matrix
+
+| Scenario | Risk | Production Mitigation |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
+
+
+## 🤖 LLM-Specific Traps Table
+
+| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
+|:---|:---|:---|
+| **Unchecked Payload Cast** | Casting request bodies to TypeScript types without runtime schema validation | Parse request payloads through Zod/Pydantic schemas before business logic |
+| **Silent Error Swallowing** | Catching errors with empty catch blocks or logging without rethrowing | Propagate structured errors with status codes and contextual stack traces |
+| **Unparameterized Query** | Concatenating user inputs into SQL/Prisma query strings | Always use parameterized bindings or type-safe ORM query builders |
+
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `logic-reviewer` · `security-auditor` · `api-architect` · `resilience-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
+
+### 🔬 Evidence Standard (Tri-State Verification)
+Every finding, audit statement, or completion claim must classify its factual certainty:
+- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
+- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
+- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.
+
+### ✅ Pre-Flight Self-Audit Checklist
+```
+✅ Are all inputs and boundary payloads validated against schemas (Zod/Pydantic)?
+✅ Are SQL and database queries parameterized with zero string concatenation?
+✅ Are error boundaries and timeout/retry policies explicitly declared?
+✅ Are authentication and object-level authorization (IDOR/BOLA) checked before business logic?
+✅ Did I verify that imported dependencies exist in package manifests?
+```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agents/skills/app-builder/SKILL.md

@@ -1,36 +1,58 @@
----
-name: app-builder
-description: "Use when Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents."
-version: 5.0.0
-last-updated: 2026-09-13
-skills:
-  - nextjs-react-expert
-  - react-specialist
-  - project-idioms
-tools: Read, Grep, Glob, Bash, Edit, Write
-scripts-binding:
-  - .agent/scripts/lint_runner.js
-  - .agent/scripts/verify_all.js
----
-
-# App Builder — Application Orchestrator
-
----
-
-## 🛠️ Technical Architecture & Reference Recipes
-
+---
+name: app-builder
+description: "Use when executing, coordinating, planning, or reviewing app builder agent workflows, cognitive loops, and architecture standards."
+version: 6.0.0
+last-updated: 2026-09-29
+skills:
+  - nextjs-react-expert
+  - react-specialist
+  - project-idioms
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
+---
+
+# App Builder — Application Orchestrator
+
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `app-builder` domain, inspect these 5 critical parameters:
+1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
+2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
+3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
+4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
+5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
+
+
+## Activation Boundaries
+- **Activate when:** Use when executing, coordinating, planning, or reviewing app builder agent workflows, cognitive loops, and architecture standards.
+- **DO NOT activate when:** The task falls outside the `app-builder` domain or is managed by a different dedicated specialist agent.
+
+
+## 🔁 Multi-Pass Execution Protocol
+
+| Pass | Phase | Core Action | Adaptive Depth |
+|:---|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
+| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
+| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
+| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
+| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |
+
+
 ---
 
+## 🛠️ Technical Architecture & Reference Recipes
+
 ## Hallucination Traps (Read First)
 
 - ❌ Generating entire applications in one shot -> ✅ Build one module at a time, verify each
 - ❌ Choosing a tech stack without asking the user -> ✅ Always ask about existing preferences, team skills, and deployment target
 - ❌ Hardcoding API keys or secrets during scaffolding -> ✅ Use .env.example with placeholder values from day one
 
----
-
----
-
+---
 ## When This Skill Activates
 
 Activate when the user request involves:
@@ -203,10 +225,7 @@ Report the URL to the user.
 |React Native|`templates/react-native-app/`|Cross-platform mobile|
 |API Only|`templates/api-only/`|Backend service, no UI|
 
----
-
----
-
+---
 ## Agent Coordination
 
 How App Builder orchestrates specialist agents.
@@ -532,4 +551,40 @@ Monorepo:
 | File storage | -       | Cloudinary, S3               |
 | Payment      | Stripe  | LemonSqueezy, Paddle         |
 | Email        | -       | Resend, SendGrid             |
-| Search       | -       | Algolia, Typesense           |
+| Search       | -       | Algolia, Typesense           |
+
+## 🚨 Edge-Case & Failure Mode Matrix
+
+| Scenario | Risk | Production Mitigation |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
+
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `orchestrator` · `agent-organizer` · `logic-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
+
+### 🔬 Evidence Standard (Tri-State Verification)
+Every finding, audit statement, or completion claim must classify its factual certainty:
+- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
+- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
+- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.
+
+### ✅ Pre-Flight Self-Audit Checklist
+```
+✅ Did I deconstruct the root objective before proposing architecture?
+✅ Did I identify dependencies, bottlenecks, and parallelizable sub-tasks?
+✅ Did I avoid over-engineering and select the simplest effective pattern?
+✅ Did I verify assumptions with concrete file reads instead of speculation?
+✅ Did I establish measurable verification criteria before completion?
+```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.