tribunal-kit 9.0.0 → 9.0.2

package/.agents/skills/gsap-utils/SKILL.md

@@ -0,0 +1,374 @@
+---
+name: gsap-utils
+description: Use when Official GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe. Use when the user asks about gsap.utils, clamp, mapRange, random, snap, toArray, wrap, or helper utilities in GSAP.
+version: 5.0.0
+last-updated: 2026-09-13
+skills:
+  - motion-engineering
+  - gsap-react
+  - 60fps-animation
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
+---
+
+# gsap.utils — Math & Interpolation Helpers
+
+## Mandatory Pre-Flight Context Inspection
+
+Before generating, refactoring, or reviewing code in the `gsap-utils` 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 Official GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe. Use when the user asks about gsap.utils, clamp, mapRange, random, snap, toArray, wrap, or helper utilities in GSAP.
+- **DO NOT activate when:** The task falls outside the `gsap-utils` 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
+
+---
+
+
+## When to Use This Skill
+
+Apply when writing or reviewing code that uses **gsap.utils** for math, array/collection handling, unit parsing, or value mapping in animations (e.g. mapping scroll to a value, randomizing, snapping to a grid, or normalizing inputs).
+
+**Related skills:** Use with **gsap-core**, **gsap-timeline**, and **gsap-scrolltrigger** when building animations; CustomEase and other easing utilities are in **gsap-plugins**.
+
+## Overview
+
+**gsap.utils** provides pure helpers; no need to register. Use in tween vars (e.g. function-based values), in ScrollTrigger or Observer callbacks, or in any JS that drives GSAP. All are on **gsap.utils** (e.g. `gsap.utils.clamp()`).
+
+**Omitting the value: function form.** Many utils accept the value to transform as the **last** argument. If you omit that argument, the util returns a **function** that accepts the value later. Use the function form when you need to clamp, map, normalize, or snap many values with the same config (e.g. in a mousemove handler or tween callback). **Exception: random()** — pass **true** as the last argument to get a reusable function (do not omit the value); see [random()](<https://gsap.com/docs/v3/GSAP/UtilityMethods/random()>).
+
+```javascript
+// With value: returns the result
+gsap.utils.clamp(0, 100, 150); // 100
+
+// Without value: returns a function you call with the value later
+let c = gsap.utils.clamp(0, 100);
+c(150); // 100
+c(-10); // 0
+```
+
+## Clamping and Ranges
+
+### clamp(min, max, value?)
+
+Constrains a value between min and max. Omit **value** to get a function: `clamp(min, max)(value)`.
+
+```javascript
+gsap.utils.clamp(0, 100, 150); // 100
+gsap.utils.clamp(0, 100, -10); // 0
+
+let clampFn = gsap.utils.clamp(0, 100);
+clampFn(150); // 100
+```
+
+### mapRange(inMin, inMax, outMin, outMax, value?)
+
+Maps a value from one range to another. Use when converting scroll position, progress (0–1), or input range to an animation range. Omit **value** to get a function: `mapRange(inMin, inMax, outMin, outMax)(value)`.
+
+```javascript
+gsap.utils.mapRange(0, 100, 0, 500, 50); // 250
+gsap.utils.mapRange(0, 1, 0, 360, 0.5); // 180 (progress to degrees)
+
+let mapFn = gsap.utils.mapRange(0, 100, 0, 500);
+mapFn(50); // 250
+```
+
+### normalize(min, max, value?)
+
+Returns a value normalized to 0–1 for the given range. Inverse of mapping when the target range is 0–1. Omit **value** to get a function: `normalize(min, max)(value)`.
+
+```javascript
+gsap.utils.normalize(0, 100, 50); // 0.5
+gsap.utils.normalize(100, 300, 200); // 0.5
+
+let normFn = gsap.utils.normalize(0, 100);
+normFn(50); // 0.5
+```
+
+### interpolate(start, end, progress?)
+
+Interpolates between two values at a given progress (0–1). Handles numbers, colors, and objects with matching keys. Omit **progress** to get a function: `interpolate(start, end)(progress)`.
+
+```javascript
+gsap.utils.interpolate(0, 100, 0.5); // 50
+gsap.utils.interpolate('#ff0000', '#0000ff', 0.5); // mid color
+gsap.utils.interpolate({ x: 0, y: 0 }, { x: 100, y: 50 }, 0.5); // { x: 50, y: 25 }
+
+let lerp = gsap.utils.interpolate(0, 100);
+lerp(0.5); // 50
+```
+
+## Random and Snap
+
+### random(minimum, maximum[, snapIncrement, returnFunction]) / random(array[, returnFunction])
+
+Returns a random number in the range **minimum**–**maximum**, or a random element from an **array**. Optional **snapIncrement** snaps the result to the nearest multiple (e.g. `5` → multiples of 5). **To get a reusable function**, pass **true** as the last argument (**returnFunction**); the returned function takes no args and returns a new random value each time. This is the only util that uses `true` for the function form instead of omitting the value.
+
+```javascript
+// immediate value: number in range
+gsap.utils.random(-100, 100); // e.g. 42.7
+gsap.utils.random(0, 500, 5); // 0–500, snapped to nearest 5
+
+// reusable function: pass true as last argument
+let randomFn = gsap.utils.random(-200, 500, 10, true);
+randomFn(); // random value in range, snapped to 10
+randomFn(); // another random value
+
+// array: pick one value at random
+gsap.utils.random(['red', 'blue', 'green']); // "red", "blue", or "green"
+let randomFromArray = gsap.utils.random([0, 100, 200], true);
+randomFromArray(); // 0, 100, or 200
+```
+
+**String form in tween vars:** use `"random(-100, 100)"`, `"random(-100, 100, 5)"`, or `"random([0, 100, 200])"`; GSAP evaluates it per target.
+
+```javascript
+gsap.to('.box', { x: 'random(-100, 100, 5)', duration: 1 });
+gsap.to('.item', { backgroundColor: 'random([red, blue, green])' });
+```
+
+### snap(snapTo, value?)
+
+Snaps a value to the nearest multiple of **snapTo**, or to the nearest value in an array of allowed values. Omit **value** to get a function: `snap(snapTo)(value)` (or `snap(snapArray)(value)`).
+
+```javascript
+gsap.utils.snap(10, 23); // 20
+gsap.utils.snap(0.25, 0.7); // 0.75
+gsap.utils.snap([0, 100, 200], 150); // 100 or 200 (nearest in array)
+
+let snapFn = gsap.utils.snap(10);
+snapFn(23); // 20
+```
+
+Use in tweens for grid or step-based animation:
+
+```javascript
+gsap.to('.x', { x: 200, snap: { x: 20 } });
+```
+
+### shuffle(array)
+
+Returns a new array with the same elements in random order. Use for randomizing order (e.g. stagger from "random" with a copy).
+
+```javascript
+gsap.utils.shuffle([1, 2, 3, 4]); // e.g. [3, 1, 4, 2]
+```
+
+### distribute(config)
+
+**Returns a function** that assigns a value to each target based on its position in the array (or in a grid). Used internally for advanced staggers; use it whenever you need values spread across many elements (e.g. scale, opacity, x, delay). The returned function receives `(index, target, targets)` — either call it manually or pass the result directly into a tween; GSAP will call it per target with index, element, and array.
+
+**Config (all optional):**
+
+| Property | Type                      | Description                                                                                                                                                         |
+| -------- | ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `base`   | Number                    | Starting value. Default `0`.                                                                                                                                        |
+| `amount` | Number                    | Total to distribute across all targets (added to base). E.g. `amount: 1` with 100 targets → 0.01 between each. Use **each** instead to set a fixed step per target. |
+| `each`   | Number                    | Amount to add between each target (added to base). E.g. `each: 1` with 4 targets → 0, 1, 2, 3. Use **amount** instead to split a total.                             |
+| `from`   | Number \| String \| Array | Where distribution starts: index, or `"start"`, `"center"`, `"edges"`, `"random"`, `"end"`, or ratios like `[0.25, 0.75]`. Default `0`.                             |
+| `grid`   | String \| Array           | Use grid position instead of flat index: `[rows, columns]` (e.g. `[5, 10]`) or `"auto"` to detect. Omit for flat array.                                             |
+| `axis`   | String                    | For grid: limit to one axis (`"x"` or `"y"`).                                                                                                                       |
+| `ease`   | Ease                      | Distribute values along an ease curve (e.g. `"power1.inOut"`). Default `"none"`.                                                                                    |
+
+**In a tween:** pass the result of `distribute(config)` as the property value; GSAP calls the function for each target with `(index, target, targets)`.
+
+```javascript
+// Scale: middle elements 0.5, outer edges 3 (amount 2.5 distributed from center)
+gsap.to('.class', {
+  scale: gsap.utils.distribute({
+    base: 0.5,
+    amount: 2.5,
+    from: 'center',
+  }),
+});
+```
+
+**Manual use:** call the returned function with `(index, target, targets)` to get the value for that index.
+
+```javascript
+const distributor = gsap.utils.distribute({
+  base: 50,
+  amount: 100,
+  from: 'center',
+  ease: 'power1.inOut',
+});
+const targets = gsap.utils.toArray('.box');
+const valueForIndex2 = distributor(2, targets[2], targets);
+```
+
+See [distribute()](https://gsap.com/docs/v3/GSAP/UtilityMethods/distribute/) for more.
+
+## Units and Parsing
+
+### getUnit(value)
+
+Returns the unit string of a value (e.g. `"px"`, `"%"`, `"deg"`). Use when normalizing or converting values.
+
+```javascript
+gsap.utils.getUnit('100px'); // "px"
+gsap.utils.getUnit('50%'); // "%"
+gsap.utils.getUnit(42); // "" (unitless)
+```
+
+### unitize(value, unit)
+
+Appends a unit to a number, or returns the value as-is if it already has a unit. Use when building CSS values or tween end values.
+
+```javascript
+gsap.utils.unitize(100, 'px'); // "100px"
+gsap.utils.unitize('2rem', 'px'); // "2rem" (unchanged)
+```
+
+### splitColor(color, returnHSL?)
+
+Converts a color string into an array: **[red, green, blue]** (0–255), or **[red, green, blue, alpha]** (4 elements for RGBA when alpha is present or required). Pass **true** as the second argument (**returnHSL**) to get **[hue, saturation, lightness]** or **[hue, saturation, lightness, alpha]** (HSL/HSLA) instead. Works with `"rgb()"`, `"rgba()"`, `"hsl()"`, `"hsla()"`, hex, and named colors (e.g. `"red"`). Use when animating color components or building gradients. See [splitColor()](https://gsap.com/docs/v3/GSAP/UtilityMethods/splitColor/).
+
+```javascript
+gsap.utils.splitColor('red'); // [255, 0, 0]
+gsap.utils.splitColor('#6fb936'); // [111, 185, 54]
+gsap.utils.splitColor('rgba(204, 153, 51, 0.5)'); // [204, 153, 51, 0.5] (4 elements)
+gsap.utils.splitColor('#6fb936', true); // [94, 55, 47] (HSL: hue, saturation, lightness)
+```
+
+## Arrays and Collections
+
+### selector(scope)
+
+Returns a scoped selector function that finds elements only within the given element (or ref). Use in components so selectors like `".box"` match only descendants of that component, not the whole document. Accepts a DOM element or a ref (e.g. React ref; handles `.current`).
+
+```javascript
+const q = gsap.utils.selector(containerRef);
+q('.box'); // array of .box elements inside container
+gsap.to(q('.circle'), { x: 100 });
+```
+
+### toArray(value, scope?)
+
+Converts a value to an array: selector string (scoped to element), NodeList, HTMLCollection, single element, or array. Use when passing mixed inputs to GSAP (e.g. targets) and a true array is needed.
+
+```javascript
+gsap.utils.toArray('.item'); // array of elements
+gsap.utils.toArray('.item', container); // scoped to container
+gsap.utils.toArray(nodeList); // [ ... ] from NodeList
+```
+
+### pipe(...functions)
+
+Composes functions: **pipe(f1, f2, f3)(value)** returns f3(f2(f1(value))). Use when applying a chain of transforms (e.g. normalize → mapRange → snap) in a tween or callback.
+
+```javascript
+const fn = gsap.utils.pipe(
+  v => gsap.utils.normalize(0, 100, v),
+  v => gsap.utils.snap(0.1, v),
+);
+fn(50); // normalized then snapped
+```
+
+### wrap(min, max, value?)
+
+Wraps a value into the range min–max (inclusive min, exclusive max). Use for infinite scroll or cyclic values. Omit **value** to get a function: `wrap(min, max)(value)`.
+
+```javascript
+gsap.utils.wrap(0, 360, 370); // 10
+gsap.utils.wrap(0, 360, -10); // 350
+
+let wrapFn = gsap.utils.wrap(0, 360);
+wrapFn(370); // 10
+```
+
+### wrapYoyo(min, max, value?)
+
+Wraps value in range with a yoyo (bounces at ends). Use for back-and-forth within a range. Omit **value** to get a function: `wrapYoyo(min, max)(value)`.
+
+```javascript
+gsap.utils.wrapYoyo(0, 100, 150); // 50 (bounces back)
+
+let wrapY = gsap.utils.wrapYoyo(0, 100);
+wrapY(150); // 50
+```
+
+## Best practices
+
+- ✅ Omit the value argument to get a reusable function when the same range/config is used many times (e.g. scroll handler, tween callback): `let mapFn = gsap.utils.mapRange(0, 1, 0, 360); mapFn(progress)`.
+- ✅ Use **snap** for grid-aligned or step-based values; use **toArray** when GSAP or your code needs a real array from a selector or NodeList.
+- ✅ Use **gsap.utils.selector(scope)** in components so selectors are scoped to a container or ref.
+
+## Do Not
+
+- ❌ Assume **mapRange** / **normalize** handle units; they work on numbers. Use **getUnit** / **unitize** when units matter.
+- ❌ Override or rely on undocumented behavior; stick to the documented API.
+
+### Learn More
+
+https://gsap.com/docs/v3/HelperFunctions
+
+---
+
+## 🚨 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 |
+|:---|:---|:---|
+| **The Instant Pop Trap** | Conditionally unmounting elements without animated interpolation | Use AnimatePresence or coordinate morphs with continuous geometry |
+| **Layout Thrashing** | Animating width, height, top, or left inside animation loops | Animate composite-only transform (translate3d, scale) and opacity |
+| **Sluggish Duration** | Setting micro-interaction transitions to 600ms+ causing interface lag | Cap interactive feedback at 160ms–240ms with snappy ease-out curves |
+
+---
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Active Reviewers:** `frontend-reviewer` · `motion-reviewer` · `ui-ux-auditor`
+**Slash Command:** `/review` or `/tribunal-full`
+
+### ✅ Pre-Flight Self-Audit Checklist
+
+```
+✅ Does animation maintain 60fps/120fps using transform and opacity?
+✅ Is optical mass conserved across state interpolations without volume collapse?
+✅ Is duration capped within micro-interaction budgets (160ms–280ms)?
+✅ Is prefers-reduced-motion respected with graceful instant fallbacks?
+✅ Did I prevent layout thrashing and continuous geometry mutations?
+```
+
+### 🛑 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/harden/SKILL.md

@@ -0,0 +1,130 @@
+---
+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
+skills:
+  - polish
+  - baseline-ui
+  - resilience-reviewer
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
+---
+
+# Harden — Production UI Resilience & Edge Case Protection
+
+## Mandatory Pre-Flight Context Inspection
+
+Before generating, refactoring, or reviewing 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).
+
+## Activation Boundaries
+
+- **Activate when:** Use when Make interfaces production-resilient with robust empty states, error boundaries, loading skeletons, offline indicators, and internationalization (i18n) layout support.
+- **DO NOT activate when:** The task falls outside the `harden` 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
+
+---
+
+
+---
+
+## 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.
+
+---
+
+## 🚨 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 |
+|:---|:---|:---|
+| **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`
+
+### ✅ 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 focus, contrast) 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

@@ -0,0 +1,115 @@
+---
+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
+skills:
+  - agentic-patterns
+  - behavioral-modes
+  - plan-writing
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/session_manager.js
+  - .agent/scripts/verify_all.js
+  - .agent/scripts/lint_runner.js
+---
+
+# Harness Protocol — Long-Running Agent Harness Rules
+
+## Mandatory Pre-Flight Context Inspection
+
+Before generating, refactoring, or reviewing 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 Rules and guidelines for the Marathon long-running agent harness
+- **DO NOT activate when:** The task falls outside the `harness-protocol` 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
+
+---
+
+
+## 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
+
+---
+
+## 🚨 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 |
+|:---|:---|:---|
+| **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`
+
+### ✅ 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.