tribunal-kit 8.0.0 → 9.0.1

package/.agent/skills/agent-organizer/SKILL.md

@@ -1,29 +1,56 @@
 ---
 name: agent-organizer
-description: Master Agent orchestration framework. Coordination of sub-agents, workflow definitions, delegation patterns, state management across conversations, memory distillation, and execution loops. Use when assembling multi-agent systems or managing complex agent-to-agent architectures.
-tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+description: Use when Master Agent orchestration framework. Coordination of sub-agents, workflow definitions, delegation patterns, state management across conversations, memory distillation, and execution loops. Use when assembling multi-agent systems or managing complex agent-to-agent architectures.
+version: 5.0.0
+last-updated: 2026-09-13
 skills:
   - parallel-agents
   - fabel-protocol
   - agentic-patterns
+tools: Read, Grep, Glob, Bash, Edit, Write
 scripts-binding:
   - .agent/scripts/swarm_dispatcher.js
   - .agent/scripts/verify_all.js
+  - .agent/scripts/lint_runner.js
 ---
 
 # Agent Organizer — Multi-Agent Orchestration Mastery
 
+## Mandatory Pre-Flight Context Inspection
+
+Before generating, refactoring, or reviewing code in the `agent-organizer` 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 Master Agent orchestration framework. Coordination of sub-agents, workflow definitions, delegation patterns, state management across conversations, memory distillation, and execution loops. Use when assembling multi-agent systems or managing complex agent-to-agent architectures.
+- **DO NOT activate when:** The task falls outside the `agent-organizer` domain or is managed by a different dedicated specialist.
+
+## 🔁 Multi-Pass Execution Protocol
+
+Execute all non-trivial tasks through this 7-pass cognitive loop:
+
+| Pass | Phase | Core Action |
+|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
+| **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
+| **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
+| **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
+| **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
+
 ---
 
-## Mandatory Pre-Flight Context Inspection
+## 🛠️ Technical Architecture & Reference Recipes
 
-Before dispatching multi-agent tasks, you MUST inspect:
+---
 
-1. `swarm-worker-registry.md` / `task.md` → Verify target worker agents and global execution state
-2. Context Window Budget rules (Section 1) → Trim worker payload context to max 3 files per dispatch
-3. Handoff state signals (`COMPLETE`, `BLOCKED`, `ERROR`) → Verify terminal status handling rules
 
 ## Hallucination Traps (Read First)
 
@@ -33,8 +60,6 @@ Before dispatching multi-agent tasks, you MUST inspect:
 
 ---
 
-# Agent Organizer — Multi-Agent Orchestration Mastery
-
 ---
 
 ## 1. The Delegation Sub-Agent Pattern
@@ -123,91 +148,45 @@ Automation without oversight is reckless. The Organizer manages when to pause an
 
 ---
 
----
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
+## 🚨 Edge-Case & Failure Mode Matrix
 
-1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
-2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
-3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
-4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
+| Scenario | Risk | Mitigation Strategy |
+|:---|:---|:---|
+| **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 |
 
 ---
 
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
+## 🤖 LLM-Specific Traps Table
 
-Review these questions before confirming output:
-
-```
-✅ Did I rely ONLY on real, verified tools and methods?
-✅ Is this solution appropriately scoped to the user's constraints?
-✅ Did I handle potential failure modes and edge cases?
-✅ Have I avoided generic boilerplate that doesn't add value?
-```
-
-### 🛑 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 tests, compile success, or equivalent proof) that your output works as intended.
-
-## Pre-Flight Checklist
-
-- [ ] Have I reviewed the user's specific constraints and requests?
-- [ ] Have I checked the environment for relevant existing implementations?
-
-## VBC Protocol (Verification-Before-Completion)
-
-You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
-
----
-
-## 🤖 LLM-Specific Traps
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
-
-1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
-2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
-3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
-4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
+| 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 Integration (Anti-Hallucination)
-
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
+## 🏛️ Tribunal Verification & Guardrails
 
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
+**Active Reviewers:** `orchestrator` · `agent-organizer` · `logic-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
 
-### ✅ Pre-Flight Self-Audit
-
-Review these questions before confirming output:
+### ✅ Pre-Flight Self-Audit Checklist
 
 ```
-✅ Did I rely ONLY on real, verified tools and methods?
-✅ Is this solution appropriately scoped to the user's constraints?
-✅ Did I handle potential failure modes and edge cases?
-✅ Have I avoided generic boilerplate that doesn't add value?
+✅ 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 tests, compile success, or equivalent proof) that your output works as intended.
+- ✅ **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/.agent/skills/agentic-patterns/SKILL.md

@@ -1,29 +1,56 @@
 ---
 name: agentic-patterns
-description: AI agent design principles. Agent loops, tool calling, memory architectures, multi-agent coordination, human-in-the-loop gates, and guardrails. Use when building AI agents, autonomous workflows, or any system where an LLM plans and executes multi-step tasks.
-tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+description: Use when AI agent design principles. Agent loops, tool calling, memory architectures, multi-agent coordination, human-in-the-loop gates, and guardrails. Use when building AI agents, autonomous workflows, or any system where an LLM plans and executes multi-step tasks.
+version: 5.0.0
+last-updated: 2026-09-13
 skills:
   - agent-organizer
   - fabel-protocol
   - thinking-protocol
+tools: Read, Grep, Glob, Bash, Edit, Write
 scripts-binding:
   - .agent/scripts/swarm_dispatcher.js
   - .agent/scripts/verify_all.js
+  - .agent/scripts/lint_runner.js
 ---
 
 # Agentic Patterns
 
+## Mandatory Pre-Flight Context Inspection
+
+Before generating, refactoring, or reviewing code in the `agentic-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 AI agent design principles. Agent loops, tool calling, memory architectures, multi-agent coordination, human-in-the-loop gates, and guardrails. Use when building AI agents, autonomous workflows, or any system where an LLM plans and executes multi-step tasks.
+- **DO NOT activate when:** The task falls outside the `agentic-patterns` domain or is managed by a different dedicated specialist.
+
+## 🔁 Multi-Pass Execution Protocol
+
+Execute all non-trivial tasks through this 7-pass cognitive loop:
+
+| Pass | Phase | Core Action |
+|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
+| **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
+| **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
+| **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
+| **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
+
 ---
 
-## Mandatory Pre-Flight Context Inspection
+## 🛠️ Technical Architecture & Reference Recipes
 
-Before designing agentic loops, tool schemas, or memory architectures, you MUST inspect:
+---
 
-1. `package.json` / LLM SDK definitions → Check tool calling syntax (Zod schemas, OpenAI/Anthropic function calling API)
-2. Agent Loop boundaries (Section 1) → Define hard caps on `MAX_STEPS` (default: 10) and explicit termination reasons
-3. Human-in-the-loop gates (Section 5) → Ensure approval gates for destructive, data-deleting, or high-cost API calls
 
 ---
 
@@ -285,91 +312,45 @@ Evidence:    [link to terminal output, test result, or file diff]
 
 ---
 
----
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
+## 🚨 Edge-Case & Failure Mode Matrix
 
-1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
-2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
-3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
-4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
+| Scenario | Risk | Mitigation Strategy |
+|:---|:---|:---|
+| **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 |
 
 ---
 
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
+## 🤖 LLM-Specific Traps Table
 
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-
-Review these questions before confirming output:
-
-```
-✅ Did I rely ONLY on real, verified tools and methods?
-✅ Is this solution appropriately scoped to the user's constraints?
-✅ Did I handle potential failure modes and edge cases?
-✅ Have I avoided generic boilerplate that doesn't add value?
-```
-
-### 🛑 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 tests, compile success, or equivalent proof) that your output works as intended.
-
-## Pre-Flight Checklist
-
-- [ ] Have I reviewed the user's specific constraints and requests?
-- [ ] Have I checked the environment for relevant existing implementations?
-
-## VBC Protocol (Verification-Before-Completion)
-
-You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
+| 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 |
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🏛️ Tribunal Verification & Guardrails
 
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
+**Active Reviewers:** `orchestrator` · `agent-organizer` · `logic-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
 
-1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
-2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
-3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
-4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
-
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
-
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-
-### ✅ Pre-Flight Self-Audit
-
-Review these questions before confirming output:
+### ✅ Pre-Flight Self-Audit Checklist
 
 ```
-✅ Did I rely ONLY on real, verified tools and methods?
-✅ Is this solution appropriately scoped to the user's constraints?
-✅ Did I handle potential failure modes and edge cases?
-✅ Have I avoided generic boilerplate that doesn't add value?
+✅ 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 tests, compile success, or equivalent proof) that your output works as intended.
+- ✅ **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/.agent/skills/agentic-workflows-2026/SKILL.md

@@ -1,28 +1,65 @@
 ---
 name: agentic-workflows-2026
-description: Advanced 2026-2027 AI agent loops, ReAct planning, structured tool calling via Zod/Pydantic, streaming generative UI, and human-in-the-loop gates.
-tools: Read, Grep, Glob, Edit, Write
-version: 3.0.0
-last-updated: 2026-08-05
-script: .agent/scripts/swarm_dispatcher.js
-scripts-binding:
-  - .agent/scripts/swarm_dispatcher.js
-  - .agent/scripts/context_broker.js
+description: Use when Advanced 2026-2027 AI agent loops, ReAct planning, structured tool calling via Zod/Pydantic, streaming generative UI, and human-in-the-loop gates.
+version: 5.0.0
+last-updated: 2026-09-13
 skills:
   - agentic-patterns
   - generative-ui-expert
   - parallel-agents
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/swarm_dispatcher.js
+  - .agent/scripts/context_broker.js
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Agentic Workflows 2026 — Multi-Agent Architecture
 
 ## Mandatory Pre-Flight Context Inspection
 
-Before designing autonomous agent loops:
+Before generating, refactoring, or reviewing code in the `agentic-workflows-2026` 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 Advanced 2026-2027 AI agent loops, ReAct planning, structured tool calling via Zod/Pydantic, streaming generative UI, and human-in-the-loop gates.
+- **DO NOT activate when:** The task falls outside the `agentic-workflows-2026` domain or is managed by a different dedicated specialist.
+
+## 🔁 Multi-Pass Execution Protocol
+
+Execute all non-trivial tasks through this 7-pass cognitive loop:
+
+| Pass | Phase | Core Action |
+|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
+| **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
+| **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
+| **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
+| **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
+
+---
+
+## 🛠️ Technical Architecture & Reference Recipes
+
+## 2026 Agentic Architecture Invariants
+
+1. **Context Window Token Budget**:
+   Truncate or summarize completed worker waves before fanning into the supervisor agent. Never pass raw multi-megabyte tool outputs across subagents.
+2. **Deterministic Fan-In**:
+   Always aggregate worker results using `Promise.allSettled()` to prevent one failing subagent from crashing the entire swarm orchestration.
+3. **Structured Failure Handoff**:
+   If an agent fails 3 consecutive iterations, halt execution and yield an explicit diagnosis payload to the user rather than spinning in an infinite retry loop.
 
-1. Tool Contract Validation → Enforce strict JSON Schema / Zod validation for every tool call
-2. Hard Execution Limit → Enforce a maximum iteration cap (max 10 turns) to prevent infinite loops
-3. Human-in-the-Loop Gate → Require human approval for destructive operations (file deletion, production deploy, DB writes)
+---
 
 ## Core ReAct Loop Pattern (Zod + TypeScript)
 
@@ -74,7 +111,47 @@ export async function runAgentLoop(task: string, maxTurns = 10) {
        └── Dispatch Worker C (Frontend) ──> WorkerResult C ──┘
 ```
 
-## 🛑 Verification-Before-Completion (VBC) Protocol
+---
+
+## 🚨 Edge-Case & Failure Mode Matrix
+
+| Scenario | Risk | Mitigation Strategy |
+|:---|:---|:---|
+| **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`
+
+### ✅ 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 checks performed before business logic execution?
+✅ Did I verify that imported dependencies exist in package.json/requirements.txt?
+```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
 
-- Validate tool arguments before tool execution.
-- Log complete agent trace trajectory for auditability.
+**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/.agent/skills/ai-app-hardening/SKILL.md

@@ -1,28 +1,54 @@
 ---
 name: ai-app-hardening
-description: OWASP Top 10 for LLMs (2026), prompt injection defense, model output sanitization, indirect injection defense, and automated SBOM dependency security.
-tools: Read, Grep, Glob, Edit, Write
-version: 3.0.0
-last-updated: 2026-08-05
-script: .agent/scripts/security_scan.js
-scripts-binding:
-  - .agent/scripts/security_scan.js
-  - .agent/scripts/guardrail_engine.js
+description: Use when OWASP Top 10 for LLMs (2026), prompt injection defense, model output sanitization, indirect injection defense, and automated SBOM dependency security.
+version: 5.0.0
+last-updated: 2026-09-13
 skills:
   - ai-prompt-injection-defense
   - vulnerability-scanner
   - backend-security-expert
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/security_scan.js
+  - .agent/scripts/guardrail_engine.js
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # AI Application Hardening & Indirect Prompt Injection Defense
 
 ## Mandatory Pre-Flight Context Inspection
 
-Before deploying AI features:
+Before generating, refactoring, or reviewing code in the `ai-app-hardening` 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
 
-1. Indirect Prompt Injection Defense → Sanitize third-party content (scraped URLs, PDF imports, RAG docs) before feeding to LLMs
-2. XML Delimiter Sandboxing → Enclose user/external inputs inside `<external_context>` and instruct model to ignore instructions within
-3. Insecure Output Handling (OWASP LLM02) → Escape HTML/script tags on all rendered model outputs
+- **Activate when:** Use when OWASP Top 10 for LLMs (2026), prompt injection defense, model output sanitization, indirect injection defense, and automated SBOM dependency security.
+- **DO NOT activate when:** The task falls outside the `ai-app-hardening` domain or is managed by a different dedicated specialist.
+
+## 🔁 Multi-Pass Execution Protocol
+
+Execute all non-trivial tasks through this 7-pass cognitive loop:
+
+| Pass | Phase | Core Action |
+|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
+| **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
+| **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
+| **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
+| **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
+
+---
+
+## 🛠️ Technical Architecture & Reference Recipes
 
 ## Indirect Prompt Injection Defense Filter
 
@@ -53,7 +79,47 @@ export function sanitizeRAGDocument(rawDocumentContent: string): string {
 | **LLM04** | Model Denial of Service              | Hard `max_tokens` limit + IP bucket rate limiting   |
 | **LLM07** | System Prompt Leakage                | System prompt redaction guards in output stream     |
 
-## 🛑 Verification-Before-Completion (VBC) Protocol
+---
+
+## 🚨 Edge-Case & Failure Mode Matrix
+
+| Scenario | Risk | Mitigation Strategy |
+|:---|:---|:---|
+| **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 |
+|:---|:---|:---|
+| **Hardcoded Secret Pattern** | Committing API keys, tokens, or private salts into source code | Load credentials strictly via runtime environment variables and secret stores |
+| **Prompt Injection Surface** | Directly concatenating untrusted user input into LLM system prompts | Wrap user content in isolated delimiters and strip injection control sequences |
+| **Missing Authorization Check** | Relying only on authentication token presence without checking tenant/object RBAC | Verify user permissions against the specific target record ID before mutation |
+
+---
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `security-auditor` · `penetration-tester` · `backend-security-expert`
+**Slash Command:** `/review` or `/tribunal-full`
+
+### ✅ Pre-Flight Self-Audit Checklist
+
+```
+✅ Are user inputs sanitized and treated as untrusted at system boundaries?
+✅ Are secrets loaded strictly via environment variables with zero hardcoding?
+✅ Is least-privilege enforcement active on APIs, tokens, and storage buckets?
+✅ Are prompt-injection delimiters and sanitizers wrapped around LLM inputs?
+✅ Did I verify encryption in transit and at rest for sensitive customer data?
+```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
 
-- Run prompt injection test suite against external RAG context inputs.
-- Audit tool calls for privilege escalation risks.
+**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.