tribunal-kit 9.2.4 → 9.2.6

package/.agents/skills/harden/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: harden
-description: "Use when Make interfaces production-resilient with robust empty states, error boundaries, loading skeletons, offline indicators, and internationalization (i18n) layout support."
-version: 5.0.0
-last-updated: 2026-09-13
+description: "Use when building, styling, optimizing, and auditing harden components, responsive layouts, design systems, and frontend state."
+version: 6.0.0
+last-updated: 2026-09-29
 skills:
   - polish
   - baseline-ui
@@ -15,41 +15,111 @@ scripts-binding:
 
 # Harden — Production UI Resilience & Edge Case Protection
 
----
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `harden` 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).
 
-## 🛠️ Technical Architecture & Reference Recipes
 
----
+## Activation Boundaries
+- **Activate when:** Use when building, styling, optimizing, and auditing harden components, responsive layouts, design systems, and frontend state.
+- **DO NOT activate when:** The task falls outside the `harden` domain or is managed by a different dedicated specialist agent.
 
----
 
-## 5 Resilience Domains
+## 🔁 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 |
+
 
-### 1. Zero-Data Empty States
+---
+
+## 🛠️ Technical Architecture & Reference Recipes
 
-- Never render empty blank slates or blank boxes.
-- Always render a dedicated empty state component featuring:
-  - Contextual icon or subtle illustration
-  - Clear heading explaining the zero state (_"No active projects found"_)
-  - Secondary helper copy (_"Get started by creating your first project."_)
-  - Prominent primary action CTA button (_"Create Project"_)
+---
+
+## 5 Resilience Domains
+
+### 1. Zero-Data Empty States
+
+- Never render empty blank slates or blank boxes.
+- Always render a dedicated empty state component featuring:
+  - Contextual icon or subtle illustration
+  - Clear heading explaining the zero state (_"No active projects found"_)
+  - Secondary helper copy (_"Get started by creating your first project."_)
+  - Prominent primary action CTA button (_"Create Project"_)
+
+### 2. Error Boundary UI & Retry Hooks
+
+- Wrap high-risk component trees in React/framework Error Boundaries.
+- Display localized inline error callouts with explicit "Retry" action buttons rather than crashing the full page view.
+
+### 3. Cumulative Layout Shift (CLS) Loading Skeletons
+
+- Match skeleton placeholder dimensions EXACTLY to incoming data elements.
+- Use animated pulse keyframes (`@keyframes pulse { 0%, 100% { opacity: 1; } 50% { opacity: 0.4; } }`).
+
+### 4. Extreme String Expansion (i18n)
+
+- German, French, and Spanish strings are 30% - 50% longer than English.
+- Avoid fixed button or container widths (`width: 120px`). Use `min-width` with flexible auto sizing and `flex-wrap: wrap` or text truncation.
+
+### 5. Offline & Network Disconnection Handling
+
+- Detect `navigator.onLine` state and display subtle offline status banners.
+- Disable mutation buttons during offline mode with explicit tooltip explanation.
 
-### 2. Error Boundary UI & Retry Hooks
+## 🚨 Edge-Case & Failure Mode Matrix
 
-- Wrap high-risk component trees in React/framework Error Boundaries.
-- Display localized inline error callouts with explicit "Retry" action buttons rather than crashing the full page view.
+| 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 |
 
-### 3. Cumulative Layout Shift (CLS) Loading Skeletons
 
-- Match skeleton placeholder dimensions EXACTLY to incoming data elements.
-- Use animated pulse keyframes (`@keyframes pulse { 0%, 100% { opacity: 1; } 50% { opacity: 0.4; } }`).
+## 🤖 LLM-Specific Traps Table
 
-### 4. Extreme String Expansion (i18n)
+| 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 |
 
-- German, French, and Spanish strings are 30% - 50% longer than English.
-- Avoid fixed button or container widths (`width: 120px`). Use `min-width` with flexible auto sizing and `flex-wrap: wrap` or text truncation.
 
-### 5. Offline & Network Disconnection Handling
+## 🏛️ Tribunal Verification & Guardrails
 
-- Detect `navigator.onLine` state and display subtle offline status banners.
-- Disable mutation buttons during offline mode with explicit tooltip explanation.
+**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/harness-protocol/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: harness-protocol
-description: "Use when Rules and guidelines for the Marathon long-running agent harness"
-version: 5.0.0
-last-updated: 2026-09-13
+description: "Use when executing, coordinating, planning, or reviewing harness protocol agent workflows, cognitive loops, and architecture standards."
+version: 6.0.0
+last-updated: 2026-09-29
 skills:
   - agentic-patterns
   - behavioral-modes
@@ -16,33 +16,103 @@ scripts-binding:
 
 # Harness Protocol — Long-Running Agent Harness Rules
 
----
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `harness-protocol` 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 harness protocol agent workflows, cognitive loops, and architecture standards.
+- **DO NOT activate when:** The task falls outside the `harness-protocol` 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
 
----
+## Rules
+
+1. Each session must start with `tk marathon init "spec"`
+2. Agents must verify they have completed their current task before running `tk marathon mark pass`
+3. If an agent encounters an unrecoverable error, they must run `tk marathon mark fail`
+4. The harness is responsible for tracking overall progression.
+5. All agents must follow the Verification-Before-Completion (VBC) protocol.
+
+## Pre-Flight Checklist
+
+- Check marathon session state
+- Confirm VBC guidelines are followed
+
+## VBC Protocol
+
+- Verify task is complete before marking pass
+
+
+## 4. Ultrawork and Continuous Validation
+
+The Harness supports "Ultrawork" — long-running autonomous batch processing and background continuous validation inspired by Oh-My-OpenAgent (OmO) Team Mode.
+- **Background Execution**: Agents in a marathon session should execute autonomously in the background via the Durable Session Log.
+- **Continuous Validation**: Sub-agents continually validate output via the VBC protocol without polling the user.
+- **Human-in-the-Loop (HitL)**: Interrupt execution and request user approval *only* at explicit Human Gates (e.g., executing a destructive command or finalizing a milestone). Do not yield to the user for intermediate successes.
 
-## Rules
+## 🚨 Edge-Case & Failure Mode Matrix
 
-1. Each session must start with `tk marathon init "spec"`
-2. Agents must verify they have completed their current task before running `tk marathon mark pass`
-3. If an agent encounters an unrecoverable error, they must run `tk marathon mark fail`
-4. The harness is responsible for tracking overall progression.
-5. All agents must follow the Verification-Before-Completion (VBC) protocol.
+| 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 |
 
-## Pre-Flight Checklist
 
-- Check marathon session state
-- Confirm VBC guidelines are followed
+## 🤖 LLM-Specific Traps Table
 
-## VBC Protocol
+| 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 |
 
-- Verify task is complete before marking pass
 
+## 🏛️ Tribunal Verification & Guardrails
 
-## 4. Ultrawork and Continuous Validation
+**Active Reviewers:** `orchestrator` · `agent-organizer` · `logic-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
 
-The Harness supports "Ultrawork" — long-running autonomous batch processing and background continuous validation inspired by Oh-My-OpenAgent (OmO) Team Mode.
-- **Background Execution**: Agents in a marathon session should execute autonomously in the background via the Durable Session Log.
-- **Continuous Validation**: Sub-agents continually validate output via the VBC protocol without polling the user.
-- **Human-in-the-Loop (HitL)**: Interrupt execution and request user approval *only* at explicit Human Gates (e.g., executing a destructive command or finalizing a milestone). Do not yield to the user for intermediate successes.
+### 🔬 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/hf-cli/SKILL.md

@@ -1,8 +1,43 @@
----
-name: hf-cli
-description: "Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`."
----
-
+---
+name: hf-cli
+description: "Use when Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`."
+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
+---
+
+# Hf Cli Engineering
+
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `hf-cli` 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 Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.
+- **DO NOT activate when:** The task falls outside the `hf-cli` 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 |
+
+
 Install: `curl -LsSf https://hf.co/cli/install.sh | bash -s`.
 
 The Hugging Face Hub CLI tool `hf` is available. IMPORTANT: The `hf` command replaces the deprecated `huggingface-cli` command.
@@ -236,4 +271,49 @@ Some command examples:
 
 - Use `hf <command> --help` for full options, descriptions, usage, and real-world examples
 - Authenticate with `HF_TOKEN` env var (recommended) or with `--token`
-- Update the CLI with `hf update` (uses the correct command for the detected install method)
+- Update the CLI with `hf update` (uses the correct command for the detected install method)
+
+## 🚨 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 |
+|:---|:---|:---|
+| **Platform-Dependent Shell Commands** | Hardcoding $(cat ~/.cache/huggingface/token) or piping to jq | Use platform-agnostic token checks via env var HF_TOKEN and native JSON parsing |
+| **VRAM OOM Crash** | Loading 70B model weights on a consumer 16GB GPU without quantization | Calculate parameter bounds (fp16 = VRAM/2, Q4 = VRAM*2) and load with bitsandbytes/GGUF |
+| **Blocking Batch Generation** | Generating large batches synchronously without streaming or yield | Use TextIteratorStreamer or asynchronous generate workers to prevent request timeouts |
+
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `ai-code-reviewer` · `python-pro` · `performance-optimizer`
+**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 model architectures and weights verified to fit within target hardware VRAM budgets?
+✅ Are pipeline requests guarded with bounded timeouts and retry backoffs?
+✅ Are dataset loading scripts operating in streaming mode to prevent out-of-memory errors?
+✅ Are API tokens and cache paths handled portably without assuming UNIX shell environments?
+✅ Are tokenizers and generation parameters (max_new_tokens, temperature) strictly bounded?
+```
+
+### 🛑 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/hf-cloud-aws-context-discovery/SKILL.md

@@ -1,10 +1,43 @@
----
-name: hf-cloud-aws-context-discovery
-description: Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.
----
-
-# AWS Context Discovery
-
+---
+name: hf-cloud-aws-context-discovery
+description: "Use when Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like \"use my AWS account\", \"deploy to AWS\", \"use my profile\", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first."
+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
+---
+
+# AWS Context Discovery
+
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `hf-cloud-aws-context-discovery` 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 Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.
+- **DO NOT activate when:** The task falls outside the `hf-cloud-aws-context-discovery` 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 |
+
+
 Before doing any AWS work, read the user's local AWS config. Don't guess the region, and don't ask the user for things their config already answers.
 
 ## What to discover
@@ -71,4 +104,49 @@ One or two lines, not a wall of text:
 
 Don't ask the user to confirm the region you just read from their config — they configured it; that is the confirmation.
 
-If something is wrong (credentials expired, profile doesn't exist, no region anywhere), stop and surface the specific error before continuing.
+If something is wrong (credentials expired, profile doesn't exist, no region anywhere), stop and surface the specific error before continuing.
+
+## 🚨 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 |
+|:---|:---|:---|
+| **Platform-Dependent Shell Commands** | Hardcoding $(cat ~/.cache/huggingface/token) or piping to jq | Use platform-agnostic token checks via env var HF_TOKEN and native JSON parsing |
+| **VRAM OOM Crash** | Loading 70B model weights on a consumer 16GB GPU without quantization | Calculate parameter bounds (fp16 = VRAM/2, Q4 = VRAM*2) and load with bitsandbytes/GGUF |
+| **Blocking Batch Generation** | Generating large batches synchronously without streaming or yield | Use TextIteratorStreamer or asynchronous generate workers to prevent request timeouts |
+
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `ai-code-reviewer` · `python-pro` · `performance-optimizer`
+**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 model architectures and weights verified to fit within target hardware VRAM budgets?
+✅ Are pipeline requests guarded with bounded timeouts and retry backoffs?
+✅ Are dataset loading scripts operating in streaming mode to prevent out-of-memory errors?
+✅ Are API tokens and cache paths handled portably without assuming UNIX shell environments?
+✅ Are tokenizers and generation parameters (max_new_tokens, temperature) strictly bounded?
+```
+
+### 🛑 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/hf-cloud-python-env-setup/SKILL.md

@@ -1,10 +1,43 @@
----
-name: hf-cloud-python-env-setup
-description: 'Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.'
----
-
-# Python Environment Setup for SageMaker
-
+---
+name: hf-cloud-python-env-setup
+description: "Use when Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to \"set up the environment\". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs."
+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
+---
+
+# Python Environment Setup for SageMaker
+
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `hf-cloud-python-env-setup` 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 Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.
+- **DO NOT activate when:** The task falls outside the `hf-cloud-python-env-setup` 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 |
+
+
 Most SageMaker deployment failures that look like AWS problems are actually Python environment problems: wrong Python version, broken dependency resolution, stale SDK that doesn't know about a current API. This skill makes env setup boring and correct.
 
 ## Core rules
@@ -87,4 +120,49 @@ PowerShell's quoting rules mangle nested/escaped quotes in inline Python. Don't
 Your boto3 is older than the API surface. Upgrade with `.venv/bin/python -m pip install --upgrade boto3`. Don't downgrade the script to match an old version.
 
 **`sagemaker` (the SDK) installed but the bundled scripts fail**
-The bundled scripts don't use the SDK — they only need `boto3`/`awscli` from `requirements.txt`. Installing `sagemaker` alongside is harmless, but it doesn't replace the requirements install.
+The bundled scripts don't use the SDK — they only need `boto3`/`awscli` from `requirements.txt`. Installing `sagemaker` alongside is harmless, but it doesn't replace the requirements install.
+
+## 🚨 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 |
+|:---|:---|:---|
+| **Platform-Dependent Shell Commands** | Hardcoding $(cat ~/.cache/huggingface/token) or piping to jq | Use platform-agnostic token checks via env var HF_TOKEN and native JSON parsing |
+| **VRAM OOM Crash** | Loading 70B model weights on a consumer 16GB GPU without quantization | Calculate parameter bounds (fp16 = VRAM/2, Q4 = VRAM*2) and load with bitsandbytes/GGUF |
+| **Blocking Batch Generation** | Generating large batches synchronously without streaming or yield | Use TextIteratorStreamer or asynchronous generate workers to prevent request timeouts |
+
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `ai-code-reviewer` · `python-pro` · `performance-optimizer`
+**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 model architectures and weights verified to fit within target hardware VRAM budgets?
+✅ Are pipeline requests guarded with bounded timeouts and retry backoffs?
+✅ Are dataset loading scripts operating in streaming mode to prevent out-of-memory errors?
+✅ Are API tokens and cache paths handled portably without assuming UNIX shell environments?
+✅ Are tokenizers and generation parameters (max_new_tokens, temperature) strictly bounded?
+```
+
+### 🛑 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.