@kevinrabun/judges 1.0.2 → 1.2.0

package/README.md

@@ -2,173 +2,326 @@
 
 An MCP (Model Context Protocol) server that provides a panel of **18 specialized judges** to evaluate AI-generated code — acting as an independent quality gate regardless of which project is being reviewed.
 
-## The Judge Panel
-
-| Judge | Domain | Rule Prefix | What It Evaluates |
-|-------|--------|-------------|-------------------|
-| **Judge Data Security** | Data Security & Privacy | `DATA-` | Encryption, PII handling, secrets management, access controls, GDPR/CCPA/HIPAA compliance |
-| **Judge Cybersecurity** | Cybersecurity & Threat Defense | `CYBER-` | Injection attacks, XSS, CSRF, auth flaws, dependency CVEs, OWASP Top 10 |
-| **Judge Cost Effectiveness** | Cost Optimization | `COST-` | Algorithm efficiency, N+1 queries, memory waste, caching strategy, cloud spend |
-| **Judge Scalability** | Scalability & Performance | `SCALE-` | Statelessness, horizontal scaling, concurrency, bottlenecks, rate limiting |
-| **Judge Cloud Readiness** | Cloud-Native & DevOps | `CLOUD-` | 12-Factor compliance, containerization, observability, graceful shutdown, IaC |
-| **Judge Software Practices** | Engineering Best Practices | `SWDEV-` | SOLID principles, type safety, error handling, testing, input validation, clean code |
-| **Judge Accessibility** | Accessibility (a11y) | `A11Y-` | WCAG compliance, screen reader support, keyboard navigation, ARIA, color contrast |
-| **Judge API Design** | API Design & Contracts | `API-` | REST conventions, versioning, pagination, error responses, consistency |
-| **Judge Reliability** | Reliability & Resilience | `REL-` | Error handling, timeouts, retries, circuit breakers, graceful degradation |
-| **Judge Observability** | Observability & Monitoring | `OBS-` | Structured logging, health checks, metrics, tracing, correlation IDs |
-| **Judge Performance** | Performance & Efficiency | `PERF-` | N+1 queries, sync I/O, caching, memory leaks, algorithmic complexity |
-| **Judge Compliance** | Regulatory Compliance | `COMP-` | GDPR/CCPA, PII protection, consent, data retention, audit trails |
-| **Judge Testing** | Testing & Quality Assurance | `TEST-` | Test coverage, assertions, test isolation, naming, external dependencies |
-| **Judge Documentation** | Documentation & Readability | `DOC-` | JSDoc/docstrings, magic numbers, TODOs, code comments, module docs |
-| **Judge Internationalization** | Internationalization (i18n) | `I18N-` | Hardcoded strings, locale handling, currency formatting, RTL support |
-| **Judge Dependency Health** | Dependency Management | `DEPS-` | Version pinning, deprecated packages, supply chain, import hygiene |
-| **Judge Concurrency** | Concurrency & Async Safety | `CONC-` | Race conditions, unbounded parallelism, missing await, resource cleanup |
-| **Judge Ethics & Bias** | Ethics & Bias | `ETHICS-` | Demographic logic, explainability, dark patterns, inclusive language |
-
-## How It Works
+[![CI](https://github.com/KevinRabun/judges/actions/workflows/ci.yml/badge.svg)](https://github.com/KevinRabun/judges/actions/workflows/ci.yml)
+[![npm](https://img.shields.io/npm/v/@kevinrabun/judges)](https://www.npmjs.com/package/@kevinrabun/judges)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-The tribunal operates in two modes:
-
-1. **Pattern-Based Analysis (Tools)** — The `evaluate_code` and `evaluate_code_single_judge` tools perform heuristic analysis using pattern matching to catch common anti-patterns. This works entirely offline with zero external API calls.
+---
 
-2. **LLM-Powered Deep Analysis (Prompts)** — The server exposes MCP prompts (`judge-data-security`, `judge-cybersecurity`, etc., and `full-tribunal`) that provide each judge's expert persona as a system prompt. When used by an LLM-based client, this enables much deeper, context-aware analysis.
+## Quick Start
 
-## MCP Tools
+### 1. Install and Build
 
-### `get_judges`
-List all available judges with their domains and descriptions.
+```bash
+git clone https://github.com/KevinRabun/judges.git
+cd judges
+npm install
+npm run build
+```
 
-### `evaluate_code`
-Submit code to the **full judges panel**. All 18 judges evaluate independently and return a combined verdict.
+### 2. Try the Demo
 
-**Parameters:**
-- `code` (string, required) — The source code to evaluate
-- `language` (string, required) — Programming language (e.g., "typescript", "python")
-- `context` (string, optional) — Additional context about the code
+Run the included demo to see all 18 judges evaluate a purposely flawed API server:
 
-**Returns:** Combined verdict with overall score, per-judge scores, all findings, and recommendations.
+```bash
+npm run demo
+```
 
-### `evaluate_code_single_judge`
-Submit code to a **specific judge** for targeted review.
+This evaluates [`examples/sample-vulnerable-api.ts`](examples/sample-vulnerable-api.ts) — a file intentionally packed with security holes, performance anti-patterns, and code quality issues — and prints a full verdict with per-judge scores and findings.
 
-**Parameters:**
-- `code` (string, required) — The source code to evaluate
-- `language` (string, required) — Programming language
-- `judgeId` (string, required) — One of: `data-security`, `cybersecurity`, `cost-effectiveness`, `scalability`, `cloud-readiness`, `software-practices`, `accessibility`, `api-design`, `reliability`, `observability`, `performance`, `compliance`, `testing`, `documentation`, `internationalization`, `dependency-health`, `concurrency`, `ethics-bias`
-- `context` (string, optional) — Additional context
+**What you'll see:**
 
-## MCP Prompts
+```
+╔══════════════════════════════════════════════════════════════╗
+║           Judges Panel — Full Tribunal Demo                 ║
+╚══════════════════════════════════════════════════════════════╝
+
+  Overall Verdict : FAIL
+  Overall Score   : 43/100
+  Critical Issues : 15
+  High Issues     : 17
+  Total Findings  : 83
+  Judges Run      : 18
+
+  Per-Judge Breakdown:
+  ────────────────────────────────────────────────────────────────
+  ❌ Judge Data Security              0/100    7 finding(s)
+  ❌ Judge Cybersecurity              0/100    7 finding(s)
+  ❌ Judge Cost Effectiveness        52/100    5 finding(s)
+  ⚠️  Judge Scalability              65/100    4 finding(s)
+  ❌ Judge Cloud Readiness           61/100    4 finding(s)
+  ❌ Judge Software Practices        45/100    6 finding(s)
+  ❌ Judge Accessibility              0/100    8 finding(s)
+  ❌ Judge API Design                 0/100    9 finding(s)
+  ❌ Judge Reliability               54/100    3 finding(s)
+  ❌ Judge Observability             45/100    5 finding(s)
+  ❌ Judge Performance               27/100    5 finding(s)
+  ❌ Judge Compliance                 0/100    4 finding(s)
+  ⚠️  Judge Testing                  90/100    1 finding(s)
+  ⚠️  Judge Documentation            70/100    4 finding(s)
+  ⚠️  Judge Internationalization     65/100    4 finding(s)
+  ⚠️  Judge Dependency Health        90/100    1 finding(s)
+  ❌ Judge Concurrency               44/100    4 finding(s)
+  ❌ Judge Ethics & Bias             65/100    2 finding(s)
+```
 
-- `judge-data-security` — Deep data security review via LLM
-- `judge-cybersecurity` — Deep cybersecurity review via LLM
-- `judge-cost-effectiveness` — Deep cost optimization review via LLM
-- `judge-scalability` — Deep scalability review via LLM
-- `judge-cloud-readiness` — Deep cloud readiness review via LLM
-- `judge-software-practices` — Deep software practices review via LLM
-- `judge-accessibility` — Deep accessibility/WCAG review via LLM
-- `judge-api-design` — Deep API design review via LLM
-- `judge-reliability` — Deep reliability & resilience review via LLM
-- `judge-observability` — Deep observability & monitoring review via LLM
-- `judge-performance` — Deep performance optimization review via LLM
-- `judge-compliance` — Deep regulatory compliance review via LLM
-- `judge-testing` — Deep testing quality review via LLM
-- `judge-documentation` — Deep documentation quality review via LLM
-- `judge-internationalization` — Deep i18n review via LLM
-- `judge-dependency-health` — Deep dependency health review via LLM
-- `judge-concurrency` — Deep concurrency & async safety review via LLM
-- `judge-ethics-bias` — Deep ethics & bias review via LLM
-- `full-tribunal` — All 18 judges via LLM in a single prompt
-
-## Setup
-
-### Build
+### 3. Run the Tests
 
 ```bash
-npm install
-npm run build
+npm test
 ```
 
-### Configure in VS Code (GitHub Copilot / Claude Desktop)
+Runs 184 automated tests covering all 18 judges, markdown formatters, and edge cases.
 
-Add to your MCP settings (`.vscode/mcp.json`, `claude_desktop_config.json`, etc.):
+### 4. Connect to Your Editor
+
+Add the Judges Panel as an MCP server so your AI coding assistant can use it automatically.
+
+**VS Code** — create `.vscode/mcp.json` in your project:
 
 ```json
 {
-  "mcpServers": {
+  "servers": {
     "judges": {
       "command": "node",
-      "args": ["<path-to>/judges/dist/index.js"]
+      "args": ["/absolute/path/to/judges/dist/index.js"]
     }
   }
 }
 ```
 
-### Configure in VS Code Settings (settings.json)
+**Claude Desktop** — add to `claude_desktop_config.json`:
 
 ```json
 {
-  "mcp": {
-    "servers": {
-      "judges": {
-        "command": "node",
-        "args": ["<path-to>/judges/dist/index.js"]
-      }
+  "mcpServers": {
+    "judges": {
+      "command": "node",
+      "args": ["/absolute/path/to/judges/dist/index.js"]
     }
   }
 }
 ```
 
+**Or install from npm** instead of cloning:
+
+```bash
+npm install -g @kevinrabun/judges
+```
+
+Then use `judges` as the command in your MCP config (no `args` needed).
+
+---
+
+## The Judge Panel
+
+| Judge | Domain | Rule Prefix | What It Evaluates |
+|-------|--------|-------------|-------------------|
+| **Data Security** | Data Security & Privacy | `DATA-` | Encryption, PII handling, secrets management, access controls |
+| **Cybersecurity** | Cybersecurity & Threat Defense | `CYBER-` | Injection attacks, XSS, CSRF, auth flaws, OWASP Top 10 |
+| **Cost Effectiveness** | Cost Optimization | `COST-` | Algorithm efficiency, N+1 queries, memory waste, caching strategy |
+| **Scalability** | Scalability & Performance | `SCALE-` | Statelessness, horizontal scaling, concurrency, bottlenecks |
+| **Cloud Readiness** | Cloud-Native & DevOps | `CLOUD-` | 12-Factor compliance, containerization, graceful shutdown, IaC |
+| **Software Practices** | Engineering Best Practices | `SWDEV-` | SOLID principles, type safety, error handling, input validation |
+| **Accessibility** | Accessibility (a11y) | `A11Y-` | WCAG compliance, screen reader support, keyboard navigation, ARIA |
+| **API Design** | API Design & Contracts | `API-` | REST conventions, versioning, pagination, error responses |
+| **Reliability** | Reliability & Resilience | `REL-` | Error handling, timeouts, retries, circuit breakers |
+| **Observability** | Observability & Monitoring | `OBS-` | Structured logging, health checks, metrics, tracing |
+| **Performance** | Performance & Efficiency | `PERF-` | N+1 queries, sync I/O, caching, memory leaks |
+| **Compliance** | Regulatory Compliance | `COMP-` | GDPR/CCPA, PII protection, consent, data retention, audit trails |
+| **Testing** | Testing & Quality Assurance | `TEST-` | Test coverage, assertions, test isolation, naming |
+| **Documentation** | Documentation & Readability | `DOC-` | JSDoc/docstrings, magic numbers, TODOs, code comments |
+| **Internationalization** | Internationalization (i18n) | `I18N-` | Hardcoded strings, locale handling, currency formatting |
+| **Dependency Health** | Dependency Management | `DEPS-` | Version pinning, deprecated packages, supply chain |
+| **Concurrency** | Concurrency & Async Safety | `CONC-` | Race conditions, unbounded parallelism, missing await |
+| **Ethics & Bias** | Ethics & Bias | `ETHICS-` | Demographic logic, dark patterns, inclusive language |
+
+---
+
+## How It Works
+
+The tribunal operates in two modes:
+
+1. **Pattern-Based Analysis (Tools)** — The `evaluate_code` and `evaluate_code_single_judge` tools perform heuristic analysis using pattern matching to catch common anti-patterns. This works entirely offline with zero external API calls.
+
+2. **LLM-Powered Deep Analysis (Prompts)** — The server exposes MCP prompts (e.g., `judge-data-security`, `full-tribunal`) that provide each judge's expert persona as a system prompt. When used by an LLM-based client, this enables deeper, context-aware analysis beyond what pattern matching can detect.
+
+---
+
+## Composable by Design
+
+Judges Panel is intentionally focused on **heuristic pattern detection** — fast, offline, zero-dependency. It does not try to be an AST parser, a CVE scanner, or a linter. Those capabilities belong in dedicated MCP servers that an AI agent can orchestrate alongside Judges.
+
+### Recommended MCP Stack
+
+When your AI coding assistant connects to multiple MCP servers, each one contributes its specialty:
+
+```
+┌─────────────────────────────────────────────────────────┐
+│                   AI Coding Assistant                   │
+│              (Claude, Copilot, Cursor, etc.)            │
+└──────┬──────────┬──────────┬──────────┬────────────────┘
+       │          │          │          │
+       ▼          ▼          ▼          ▼
+  ┌─────────┐ ┌────────┐ ┌────────┐ ┌────────┐
+  │ Judges  │ │  AST   │ │  CVE / │ │ Linter │
+  │  Panel  │ │ Server │ │  SBOM  │ │ Server │
+  └─────────┘ └────────┘ └────────┘ └────────┘
+   Heuristic   Structural  Vuln DB    Style &
+   patterns    analysis    scanning   correctness
+```
+
+| Layer | What It Does | Example Servers |
+|-------|-------------|-----------------|
+| **Judges Panel** | 18-judge quality gate — security patterns, cost, scalability, a11y, compliance, ethics | This server |
+| **AST Analysis** | Deep structural analysis — data flow, complexity metrics, dead code, type tracking | Tree-sitter, Semgrep, SonarQube MCP servers |
+| **CVE / SBOM** | Vulnerability scanning against live databases — known CVEs, license risks, supply chain | OSV, Snyk, Trivy, Grype MCP servers |
+| **Linting** | Language-specific style and correctness rules | ESLint, Ruff, Clippy MCP servers |
+| **Runtime Profiling** | Memory, CPU, latency measurement on running code | Custom profiling MCP servers |
+
+### Why Orchestration Beats a Monolith
+
+| | Monolith | Orchestrated MCP Stack |
+|---|---|---|
+| **Maintenance** | One team owns everything | Each server evolves independently |
+| **Depth** | Shallow coverage of many domains | Deep expertise per server |
+| **Updates** | CVE data stale = full redeploy | CVE server updates on its own |
+| **Language support** | Must embed parsers for every language | AST server handles this |
+| **User choice** | All or nothing | Pick the servers you need |
+| **Offline capability** | Hard to achieve with CVE deps | Judges runs fully offline; CVE server handles network |
+
+### What This Means in Practice
+
+When you ask your AI assistant *"Is this code production-ready?"*, the agent can:
+
+1. **Judges Panel** → Scan for hardcoded secrets, missing error handling, N+1 queries, accessibility gaps, compliance issues
+2. **AST Server** → Analyze cyclomatic complexity, detect unreachable code, trace tainted data flows
+3. **CVE Server** → Check every dependency in `package.json` against known vulnerabilities
+4. **Linter Server** → Enforce team style rules, catch language-specific gotchas
+
+Each server returns structured findings. The AI synthesizes everything into a single, actionable review — no single server needs to do it all.
+
+---
+
+## MCP Tools
+
+### `get_judges`
+List all available judges with their domains and descriptions.
+
+### `evaluate_code`
+Submit code to the **full judges panel**. All 18 judges evaluate independently and return a combined verdict.
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `code` | string | yes | The source code to evaluate |
+| `language` | string | yes | Programming language (e.g., `typescript`, `python`) |
+| `context` | string | no | Additional context about the code |
+
+### `evaluate_code_single_judge`
+Submit code to a **specific judge** for targeted review.
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `code` | string | yes | The source code to evaluate |
+| `language` | string | yes | Programming language |
+| `judgeId` | string | yes | See [judge IDs](#judge-ids) below |
+| `context` | string | no | Additional context |
+
+#### Judge IDs
+
+`data-security` · `cybersecurity` · `cost-effectiveness` · `scalability` · `cloud-readiness` · `software-practices` · `accessibility` · `api-design` · `reliability` · `observability` · `performance` · `compliance` · `testing` · `documentation` · `internationalization` · `dependency-health` · `concurrency` · `ethics-bias`
+
+---
+
+## MCP Prompts
+
+Each judge has a corresponding prompt for LLM-powered deep analysis:
+
+| Prompt | Description |
+|--------|-------------|
+| `judge-data-security` | Deep data security review |
+| `judge-cybersecurity` | Deep cybersecurity review |
+| `judge-cost-effectiveness` | Deep cost optimization review |
+| `judge-scalability` | Deep scalability review |
+| `judge-cloud-readiness` | Deep cloud readiness review |
+| `judge-software-practices` | Deep software practices review |
+| `judge-accessibility` | Deep accessibility/WCAG review |
+| `judge-api-design` | Deep API design review |
+| `judge-reliability` | Deep reliability & resilience review |
+| `judge-observability` | Deep observability & monitoring review |
+| `judge-performance` | Deep performance optimization review |
+| `judge-compliance` | Deep regulatory compliance review |
+| `judge-testing` | Deep testing quality review |
+| `judge-documentation` | Deep documentation quality review |
+| `judge-internationalization` | Deep i18n review |
+| `judge-dependency-health` | Deep dependency health review |
+| `judge-concurrency` | Deep concurrency & async safety review |
+| `judge-ethics-bias` | Deep ethics & bias review |
+| `full-tribunal` | All 18 judges in a single prompt |
+
+---
+
 ## Scoring
 
 Each judge scores the code from **0 to 100**:
 
 | Severity | Score Deduction |
 |----------|----------------|
-| Critical | -20 points |
-| High | -12 points |
-| Medium | -6 points |
-| Low | -3 points |
-| Info | 0 points |
+| Critical | −30 points |
+| High | −18 points |
+| Medium | −10 points |
+| Low | −5 points |
+| Info | −2 points |
 
 **Verdict logic:**
-- **FAIL** — Any critical finding, or score < 50
-- **WARNING** — Any high finding, or score < 75
-- **PASS** — Score ≥ 75 with no critical or high findings
+- **FAIL** — Any critical finding, or score < 60
+- **WARNING** — Any high finding, any medium finding, or score < 80
+- **PASS** — Score ≥ 80 with no critical, high, or medium findings
 
 The **overall tribunal score** is the average of all 18 judges. The overall verdict fails if **any** judge fails.
 
-## Example Output
-
-```
-# Judges Panel — Verdict
-
-**Overall Verdict: WARNING** | **Score: 68/100**
-Total critical findings: 1 | Total high findings: 3
-
-## Individual Judge Results
-
-❌ **Judge Data Security** (FAIL, 60/100) — 3 finding(s)
-⚠️ **Judge Cybersecurity** (WARNING, 76/100) — 2 finding(s)
-✅ **Judge Cost Effectiveness** (PASS, 88/100) — 1 finding(s)
-⚠️ **Judge Scalability** (WARNING, 70/100) — 2 finding(s)
-✅ **Judge Cloud Readiness** (PASS, 82/100) — 1 finding(s)
-⚠️ **Judge Software Practices** (WARNING, 72/100) — 3 finding(s)
-```
+---
 
 ## Project Structure
 
 ```
 judges/
 ├── src/
-│   ├── index.ts        # MCP server entry point — tools, prompts, transport
-│   ├── types.ts         # TypeScript interfaces for judges, findings, verdicts
-│   ├── judges.ts        # Judge definitions with expert system prompts
-│   └── evaluator.ts     # Pattern-based analysis engine + scoring
+│   ├── index.ts              # MCP server entry point — tools, prompts, transport
+│   ├── types.ts              # TypeScript interfaces (Finding, JudgeEvaluation, etc.)
+│   ├── evaluators/           # Pattern-based analysis engine for each judge
+│   │   ├── index.ts          # evaluateWithJudge(), evaluateWithTribunal()
+│   │   ├── shared.ts         # Scoring, verdict logic, markdown formatters
+│   │   └── *.ts              # One analyzer per judge (18 files)
+│   └── judges/               # Judge definitions (id, name, domain, system prompt)
+│       ├── index.ts          # JUDGES array, getJudge(), getJudgeSummaries()
+│       └── *.ts              # One definition per judge (18 files)
+├── examples/
+│   ├── sample-vulnerable-api.ts  # Intentionally flawed code (triggers all 18 judges)
+│   └── demo.ts                   # Run: npm run demo
+├── tests/
+│   └── judges.test.ts            # Run: npm test (184 tests)
+├── server.json               # MCP Registry manifest
 ├── package.json
 ├── tsconfig.json
 └── README.md
 ```
 
+---
+
+## Scripts
+
+| Command | Description |
+|---------|-------------|
+| `npm run build` | Compile TypeScript to `dist/` |
+| `npm run dev` | Watch mode — recompile on save |
+| `npm test` | Run the full test suite (184 tests) |
+| `npm run demo` | Run the sample tribunal demo |
+| `npm start` | Start the MCP server |
+| `npm run clean` | Remove `dist/` |
+
+---
+
 ## License
 
 MIT

package/dist/evaluators/shared.js

@@ -20,19 +20,19 @@ export function calculateScore(findings) {
     for (const f of findings) {
         switch (f.severity) {
             case "critical":
-                score -= 20;
+                score -= 30;
                 break;
             case "high":
-                score -= 12;
+                score -= 18;
                 break;
             case "medium":
-                score -= 6;
+                score -= 10;
                 break;
             case "low":
-                score -= 3;
+                score -= 5;
                 break;
             case "info":
-                score -= 0;
+                score -= 2;
                 break;
         }
     }
@@ -41,9 +41,9 @@ export function calculateScore(findings) {
 export function deriveVerdict(findings, score) {
     if (findings.some((f) => f.severity === "critical"))
         return "fail";
-    if (score < 50)
+    if (score < 60)
         return "fail";
-    if (findings.some((f) => f.severity === "high") || score < 75)
+    if (findings.some((f) => f.severity === "high") || findings.some((f) => f.severity === "medium") || score < 80)
         return "warning";
     return "pass";
 }
@@ -57,7 +57,7 @@ export function buildSummary(judge, findings, score, verdict) {
     summary += `Verdict: **${verdict.toUpperCase()}** | Score: **${score}/100**\n`;
     summary += `Findings: ${critical} critical, ${high} high, ${medium} medium, ${low} low\n\n`;
     if (findings.length === 0) {
-        summary += "No issues detected. The code meets the expected standards for this domain.";
+        summary += "No pattern-based issues detected. Heuristic analysis has inherent limits — absence of findings does not guarantee the code is free of defects. Manual expert review is strongly recommended.";
     }
     else {
         summary += "Key issues:\n";

package/dist/evaluators/shared.js.map

@@ -1 +1 @@
-{"version":3,"file":"shared.js","sourceRoot":"","sources":["../../src/evaluators/shared.ts"],"names":[],"mappings":"AASA,gFAAgF;AAChF,2EAA2E;AAC3E,iFAAiF;AAEjF;;GAEG;AACH,MAAM,UAAU,cAAc,CAAC,IAAY,EAAE,OAAe;IAC1D,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IAC/B,MAAM,OAAO,GAAa,EAAE,CAAC;IAC7B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACtC,IAAI,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YAC3B,OAAO,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QACtB,CAAC;IACH,CAAC;IACD,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,gFAAgF;AAEhF,MAAM,UAAU,cAAc,CAAC,QAAmB;IAChD,IAAI,KAAK,GAAG,GAAG,CAAC;IAChB,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;QACzB,QAAQ,CAAC,CAAC,QAAQ,EAAE,CAAC;YACnB,KAAK,UAAU;gBACb,KAAK,IAAI,EAAE,CAAC;gBACZ,MAAM;YACR,KAAK,MAAM;gBACT,KAAK,IAAI,EAAE,CAAC;gBACZ,MAAM;YACR,KAAK,QAAQ;gBACX,KAAK,IAAI,CAAC,CAAC;gBACX,MAAM;YACR,KAAK,KAAK;gBACR,KAAK,IAAI,CAAC,CAAC;gBACX,MAAM;YACR,KAAK,MAAM;gBACT,KAAK,IAAI,CAAC,CAAC;gBACX,MAAM;QACV,CAAC;IACH,CAAC;IACD,OAAO,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,KAAK,CAAC,CAAC,CAAC;AAC3C,CAAC;AAED,MAAM,UAAU,aAAa,CAAC,QAAmB,EAAE,KAAa;IAC9D,IAAI,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,UAAU,CAAC;QAAE,OAAO,MAAM,CAAC;IACnE,IAAI,KAAK,GAAG,EAAE;QAAE,OAAO,MAAM,CAAC;IAC9B,IAAI,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,IAAI,KAAK,GAAG,EAAE;QAAE,OAAO,SAAS,CAAC;IAChF,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,gFAAgF;AAEhF,MAAM,UAAU,YAAY,CAC1B,KAAsB,EACtB,QAAmB,EACnB,KAAa,EACb,OAAgB;IAEhB,MAAM,QAAQ,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,UAAU,CAAC,CAAC,MAAM,CAAC;IAC1E,MAAM,IAAI,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,CAAC,MAAM,CAAC;IAClE,MAAM,MAAM,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,QAAQ,CAAC,CAAC,MAAM,CAAC;IACtE,MAAM,GAAG,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,KAAK,CAAC,CAAC,MAAM,CAAC;IAEhE,IAAI,OAAO,GAAG,KAAK,KAAK,CAAC,IAAI,QAAQ,KAAK,CAAC,MAAM,IAAI,CAAC;IACtD,OAAO,IAAI,cAAc,OAAO,CAAC,WAAW,EAAE,iBAAiB,KAAK,UAAU,CAAC;IAC/E,OAAO,IAAI,aAAa,QAAQ,cAAc,IAAI,UAAU,MAAM,YAAY,GAAG,UAAU,CAAC;IAE5F,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC1B,OAAO,IAAI,4EAA4E,CAAC;IAC1F,CAAC;SAAM,CAAC;QACN,OAAO,IAAI,eAAe,CAAC;QAC3B,KAAK,MAAM,CAAC,IAAI,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CACpC,CAAC,UAAU,EAAE,MAAM,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,CAC1C,EAAE,CAAC;YACF,OAAO,IAAI,MAAM,CAAC,CAAC,MAAM,MAAM,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,KAAK,KAAK,CAAC,CAAC,WAAW,IAAI,CAAC;QAC9E,CAAC;IACH,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,MAAM,UAAU,oBAAoB,CAClC,WAA8B,EAC9B,OAAgB,EAChB,KAAa,EACb,aAAqB,EACrB,SAAiB;IAEjB,IAAI,OAAO,GAAG,8BAA8B,CAAC;IAC7C,OAAO,IAAI,sBAAsB,OAAO,CAAC,WAAW,EAAE,iBAAiB,KAAK,UAAU,CAAC;IACvF,OAAO,IAAI,4BAA4B,aAAa,2BAA2B,SAAS,MAAM,CAAC;IAC/F,OAAO,IAAI,iCAAiC,CAAC;IAE7C,KAAK,MAAM,CAAC,IAAI,WAAW,EAAE,CAAC;QAC5B,MAAM,IAAI,GACR,CAAC,CAAC,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,GAAG,CAAC;QACpE,OAAO,IAAI,GAAG,IAAI,MAAM,CAAC,CAAC,SAAS,OAAO,CAAC,CAAC,OAAO,CAAC,WAAW,EAAE,KAAK,CAAC,CAAC,KAAK,WAAW,CAAC,CAAC,QAAQ,CAAC,MAAM,eAAe,CAAC;IAC3H,CAAC;IAED,OAAO,IAAI,WAAW,CAAC;IAEvB,6BAA6B;IAC7B,KAAK,MAAM,CAAC,IAAI,WAAW,EAAE,CAAC;QAC5B,OAAO,IAAI,CAAC,CAAC,OAAO,GAAG,MAAM,CAAC;IAChC,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,gFAAgF;AAEhF;;GAEG;AACH,MAAM,UAAU,uBAAuB,CAAC,OAAwB;IAC9D,IAAI,EAAE,GAAG,OAAO,CAAC,OAAO,CAAC;IAEzB,EAAE,IAAI,4BAA4B,CAAC;IAEnC,KAAK,MAAM,UAAU,IAAI,OAAO,CAAC,WAAW,EAAE,CAAC;QAC7C,KAAK,MAAM,OAAO,IAAI,UAAU,CAAC,QAAQ,EAAE,CAAC;YAC1C,MAAM,aAAa,GACjB,OAAO,CAAC,QAAQ,KAAK,UAAU;gBAC7B,CAAC,CAAC,aAAa;gBACf,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,MAAM;oBAC7B,CAAC,CAAC,SAAS;oBACX,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,QAAQ;wBAC/B,CAAC,CAAC,WAAW;wBACb,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,KAAK;4BAC5B,CAAC,CAAC,QAAQ;4BACV,CAAC,CAAC,SAAS,CAAC;YAEhB,EAAE,IAAI,OAAO,aAAa,OAAO,OAAO,CAAC,MAAM,KAAK,OAAO,CAAC,KAAK,MAAM,CAAC;YACxE,EAAE,IAAI,GAAG,OAAO,CAAC,WAAW,MAAM,CAAC;YACnC,IAAI,OAAO,CAAC,WAAW,IAAI,OAAO,CAAC,WAAW,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAC1D,EAAE,IAAI,uBAAuB,OAAO,CAAC,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC;YACpE,CAAC;YACD,EAAE,IAAI,uBAAuB,OAAO,CAAC,cAAc,MAAM,CAAC;YAC1D,IAAI,OAAO,CAAC,SAAS,EAAE,CAAC;gBACtB,EAAE,IAAI,kBAAkB,OAAO,CAAC,SAAS,MAAM,CAAC;YAClD,CAAC;YACD,EAAE,IAAI,SAAS,CAAC;QAClB,CAAC;IACH,CAAC;IAED,OAAO,EAAE,CAAC;AACZ,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,0BAA0B,CAAC,UAA2B;IACpE,IAAI,EAAE,GAAG,UAAU,CAAC,OAAO,GAAG,MAAM,CAAC;IAErC,EAAE,IAAI,0BAA0B,CAAC;IAEjC,KAAK,MAAM,OAAO,IAAI,UAAU,CAAC,QAAQ,EAAE,CAAC;QAC1C,MAAM,aAAa,GACjB,OAAO,CAAC,QAAQ,KAAK,UAAU;YAC7B,CAAC,CAAC,aAAa;YACf,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,MAAM;gBAC7B,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,QAAQ;oBAC/B,CAAC,CAAC,WAAW;oBACb,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,KAAK;wBAC5B,CAAC,CAAC,QAAQ;wBACV,CAAC,CAAC,SAAS,CAAC;QAEhB,EAAE,IAAI,OAAO,aAAa,OAAO,OAAO,CAAC,MAAM,KAAK,OAAO,CAAC,KAAK,MAAM,CAAC;QACxE,EAAE,IAAI,GAAG,OAAO,CAAC,WAAW,MAAM,CAAC;QACnC,IAAI,OAAO,CAAC,WAAW,IAAI,OAAO,CAAC,WAAW,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC1D,EAAE,IAAI,uBAAuB,OAAO,CAAC,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC;QACpE,CAAC;QACD,EAAE,IAAI,uBAAuB,OAAO,CAAC,cAAc,MAAM,CAAC;QAC1D,IAAI,OAAO,CAAC,SAAS,EAAE,CAAC;YACtB,EAAE,IAAI,kBAAkB,OAAO,CAAC,SAAS,MAAM,CAAC;QAClD,CAAC;QACD,EAAE,IAAI,SAAS,CAAC;IAClB,CAAC;IAED,OAAO,EAAE,CAAC;AACZ,CAAC"}
+{"version":3,"file":"shared.js","sourceRoot":"","sources":["../../src/evaluators/shared.ts"],"names":[],"mappings":"AASA,gFAAgF;AAChF,2EAA2E;AAC3E,iFAAiF;AAEjF;;GAEG;AACH,MAAM,UAAU,cAAc,CAAC,IAAY,EAAE,OAAe;IAC1D,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IAC/B,MAAM,OAAO,GAAa,EAAE,CAAC;IAC7B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACtC,IAAI,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YAC3B,OAAO,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QACtB,CAAC;IACH,CAAC;IACD,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,gFAAgF;AAEhF,MAAM,UAAU,cAAc,CAAC,QAAmB;IAChD,IAAI,KAAK,GAAG,GAAG,CAAC;IAChB,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;QACzB,QAAQ,CAAC,CAAC,QAAQ,EAAE,CAAC;YACnB,KAAK,UAAU;gBACb,KAAK,IAAI,EAAE,CAAC;gBACZ,MAAM;YACR,KAAK,MAAM;gBACT,KAAK,IAAI,EAAE,CAAC;gBACZ,MAAM;YACR,KAAK,QAAQ;gBACX,KAAK,IAAI,EAAE,CAAC;gBACZ,MAAM;YACR,KAAK,KAAK;gBACR,KAAK,IAAI,CAAC,CAAC;gBACX,MAAM;YACR,KAAK,MAAM;gBACT,KAAK,IAAI,CAAC,CAAC;gBACX,MAAM;QACV,CAAC;IACH,CAAC;IACD,OAAO,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,KAAK,CAAC,CAAC,CAAC;AAC3C,CAAC;AAED,MAAM,UAAU,aAAa,CAAC,QAAmB,EAAE,KAAa;IAC9D,IAAI,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,UAAU,CAAC;QAAE,OAAO,MAAM,CAAC;IACnE,IAAI,KAAK,GAAG,EAAE;QAAE,OAAO,MAAM,CAAC;IAC9B,IAAI,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,IAAI,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,QAAQ,CAAC,IAAI,KAAK,GAAG,EAAE;QAAE,OAAO,SAAS,CAAC;IACjI,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,gFAAgF;AAEhF,MAAM,UAAU,YAAY,CAC1B,KAAsB,EACtB,QAAmB,EACnB,KAAa,EACb,OAAgB;IAEhB,MAAM,QAAQ,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,UAAU,CAAC,CAAC,MAAM,CAAC;IAC1E,MAAM,IAAI,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,CAAC,MAAM,CAAC;IAClE,MAAM,MAAM,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,QAAQ,CAAC,CAAC,MAAM,CAAC;IACtE,MAAM,GAAG,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,KAAK,CAAC,CAAC,MAAM,CAAC;IAEhE,IAAI,OAAO,GAAG,KAAK,KAAK,CAAC,IAAI,QAAQ,KAAK,CAAC,MAAM,IAAI,CAAC;IACtD,OAAO,IAAI,cAAc,OAAO,CAAC,WAAW,EAAE,iBAAiB,KAAK,UAAU,CAAC;IAC/E,OAAO,IAAI,aAAa,QAAQ,cAAc,IAAI,UAAU,MAAM,YAAY,GAAG,UAAU,CAAC;IAE5F,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC1B,OAAO,IAAI,8LAA8L,CAAC;IAC5M,CAAC;SAAM,CAAC;QACN,OAAO,IAAI,eAAe,CAAC;QAC3B,KAAK,MAAM,CAAC,IAAI,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CACpC,CAAC,UAAU,EAAE,MAAM,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,CAC1C,EAAE,CAAC;YACF,OAAO,IAAI,MAAM,CAAC,CAAC,MAAM,MAAM,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,KAAK,KAAK,CAAC,CAAC,WAAW,IAAI,CAAC;QAC9E,CAAC;IACH,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,MAAM,UAAU,oBAAoB,CAClC,WAA8B,EAC9B,OAAgB,EAChB,KAAa,EACb,aAAqB,EACrB,SAAiB;IAEjB,IAAI,OAAO,GAAG,8BAA8B,CAAC;IAC7C,OAAO,IAAI,sBAAsB,OAAO,CAAC,WAAW,EAAE,iBAAiB,KAAK,UAAU,CAAC;IACvF,OAAO,IAAI,4BAA4B,aAAa,2BAA2B,SAAS,MAAM,CAAC;IAC/F,OAAO,IAAI,iCAAiC,CAAC;IAE7C,KAAK,MAAM,CAAC,IAAI,WAAW,EAAE,CAAC;QAC5B,MAAM,IAAI,GACR,CAAC,CAAC,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,GAAG,CAAC;QACpE,OAAO,IAAI,GAAG,IAAI,MAAM,CAAC,CAAC,SAAS,OAAO,CAAC,CAAC,OAAO,CAAC,WAAW,EAAE,KAAK,CAAC,CAAC,KAAK,WAAW,CAAC,CAAC,QAAQ,CAAC,MAAM,eAAe,CAAC;IAC3H,CAAC;IAED,OAAO,IAAI,WAAW,CAAC;IAEvB,6BAA6B;IAC7B,KAAK,MAAM,CAAC,IAAI,WAAW,EAAE,CAAC;QAC5B,OAAO,IAAI,CAAC,CAAC,OAAO,GAAG,MAAM,CAAC;IAChC,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,gFAAgF;AAEhF;;GAEG;AACH,MAAM,UAAU,uBAAuB,CAAC,OAAwB;IAC9D,IAAI,EAAE,GAAG,OAAO,CAAC,OAAO,CAAC;IAEzB,EAAE,IAAI,4BAA4B,CAAC;IAEnC,KAAK,MAAM,UAAU,IAAI,OAAO,CAAC,WAAW,EAAE,CAAC;QAC7C,KAAK,MAAM,OAAO,IAAI,UAAU,CAAC,QAAQ,EAAE,CAAC;YAC1C,MAAM,aAAa,GACjB,OAAO,CAAC,QAAQ,KAAK,UAAU;gBAC7B,CAAC,CAAC,aAAa;gBACf,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,MAAM;oBAC7B,CAAC,CAAC,SAAS;oBACX,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,QAAQ;wBAC/B,CAAC,CAAC,WAAW;wBACb,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,KAAK;4BAC5B,CAAC,CAAC,QAAQ;4BACV,CAAC,CAAC,SAAS,CAAC;YAEhB,EAAE,IAAI,OAAO,aAAa,OAAO,OAAO,CAAC,MAAM,KAAK,OAAO,CAAC,KAAK,MAAM,CAAC;YACxE,EAAE,IAAI,GAAG,OAAO,CAAC,WAAW,MAAM,CAAC;YACnC,IAAI,OAAO,CAAC,WAAW,IAAI,OAAO,CAAC,WAAW,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAC1D,EAAE,IAAI,uBAAuB,OAAO,CAAC,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC;YACpE,CAAC;YACD,EAAE,IAAI,uBAAuB,OAAO,CAAC,cAAc,MAAM,CAAC;YAC1D,IAAI,OAAO,CAAC,SAAS,EAAE,CAAC;gBACtB,EAAE,IAAI,kBAAkB,OAAO,CAAC,SAAS,MAAM,CAAC;YAClD,CAAC;YACD,EAAE,IAAI,SAAS,CAAC;QAClB,CAAC;IACH,CAAC;IAED,OAAO,EAAE,CAAC;AACZ,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,0BAA0B,CAAC,UAA2B;IACpE,IAAI,EAAE,GAAG,UAAU,CAAC,OAAO,GAAG,MAAM,CAAC;IAErC,EAAE,IAAI,0BAA0B,CAAC;IAEjC,KAAK,MAAM,OAAO,IAAI,UAAU,CAAC,QAAQ,EAAE,CAAC;QAC1C,MAAM,aAAa,GACjB,OAAO,CAAC,QAAQ,KAAK,UAAU;YAC7B,CAAC,CAAC,aAAa;YACf,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,MAAM;gBAC7B,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,QAAQ;oBAC/B,CAAC,CAAC,WAAW;oBACb,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,KAAK;wBAC5B,CAAC,CAAC,QAAQ;wBACV,CAAC,CAAC,SAAS,CAAC;QAEhB,EAAE,IAAI,OAAO,aAAa,OAAO,OAAO,CAAC,MAAM,KAAK,OAAO,CAAC,KAAK,MAAM,CAAC;QACxE,EAAE,IAAI,GAAG,OAAO,CAAC,WAAW,MAAM,CAAC;QACnC,IAAI,OAAO,CAAC,WAAW,IAAI,OAAO,CAAC,WAAW,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC1D,EAAE,IAAI,uBAAuB,OAAO,CAAC,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC;QACpE,CAAC;QACD,EAAE,IAAI,uBAAuB,OAAO,CAAC,cAAc,MAAM,CAAC;QAC1D,IAAI,OAAO,CAAC,SAAS,EAAE,CAAC;YACtB,EAAE,IAAI,kBAAkB,OAAO,CAAC,SAAS,MAAM,CAAC;QAClD,CAAC;QACD,EAAE,IAAI,SAAS,CAAC;IAClB,CAAC;IAED,OAAO,EAAE,CAAC;AACZ,CAAC"}

package/dist/index.js

@@ -20,7 +20,7 @@ import { evaluateWithJudge, evaluateWithTribunal, formatVerdictAsMarkdown, forma
 // ─── Create MCP Server ──────────────────────────────────────────────────────
 const server = new McpServer({
     name: "judges",
-    version: "1.0.0",
+    version: "1.2.0",
 });
 // ─── Tool: get_judges ────────────────────────────────────────────────────────
 server.tool("get_judges", "List all available judges on the Agent Tribunal panel, including their areas of expertise and what they evaluate.", {}, async () => {

package/dist/judges/accessibility.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"accessibility.d.ts","sourceRoot":"","sources":["../../src/judges/accessibility.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,kBAAkB,EAAE,eA2BhC,CAAC"}
+{"version":3,"file":"accessibility.d.ts","sourceRoot":"","sources":["../../src/judges/accessibility.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,kBAAkB,EAAE,eAiChC,CAAC"}

package/dist/judges/accessibility.js

@@ -23,6 +23,12 @@ RULES FOR YOUR EVALUATION:
 - Reference specific WCAG 2.2 success criteria (e.g., "1.1.1 Non-text Content", "2.1.1 Keyboard").
 - Indicate the WCAG conformance level impacted (A, AA, or AAA).
 - Recommend fixes with code examples using proper ARIA patterns.
-- Score from 0-100 where 100 means fully WCAG 2.2 AA compliant.`,
+- Score from 0-100 where 100 means fully WCAG 2.2 AA compliant.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code has accessibility defects and actively hunt for them. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed barriers.
+- Absence of findings does not mean the code is accessible. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=accessibility.js.map

package/dist/judges/accessibility.js.map

@@ -1 +1 @@
-{"version":3,"file":"accessibility.js","sourceRoot":"","sources":["../../src/judges/accessibility.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,kBAAkB,GAAoB;IACjD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,sBAAsB;IAC9B,WAAW,EACT,gKAAgK;IAClK,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;gEAmBgD;CAC/D,CAAC"}
+{"version":3,"file":"accessibility.js","sourceRoot":"","sources":["../../src/judges/accessibility.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,kBAAkB,GAAoB;IACjD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,sBAAsB;IAC9B,WAAW,EACT,gKAAgK;IAClK,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;8HAyB8G;CAC7H,CAAC"}

package/dist/judges/api-design.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"api-design.d.ts","sourceRoot":"","sources":["../../src/judges/api-design.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,cAAc,EAAE,eA6B5B,CAAC"}
+{"version":3,"file":"api-design.d.ts","sourceRoot":"","sources":["../../src/judges/api-design.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,cAAc,EAAE,eAmC5B,CAAC"}

package/dist/judges/api-design.js

@@ -25,6 +25,12 @@ RULES FOR YOUR EVALUATION:
 - Reference REST API design guides (Google, Microsoft, Zalando API guidelines).
 - Show corrected URL structures and response schemas in examples.
 - Consider both API producer and consumer perspectives.
-- Score from 0-100 where 100 means exemplary API design.`,
+- Score from 0-100 where 100 means exemplary API design.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the API has design flaws and actively hunt for them. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed design flaws.
+- Absence of findings does not mean the API is well-designed. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=api-design.js.map

package/dist/judges/api-design.js.map

@@ -1 +1 @@
-{"version":3,"file":"api-design.js","sourceRoot":"","sources":["../../src/judges/api-design.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,cAAc,GAAoB;IAC7C,EAAE,EAAE,YAAY;IAChB,IAAI,EAAE,kBAAkB;IACxB,MAAM,EAAE,wBAAwB;IAChC,WAAW,EACT,6KAA6K;IAC/K,UAAU,EAAE,KAAK;IACjB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;yDAqByC;CACxD,CAAC"}
+{"version":3,"file":"api-design.js","sourceRoot":"","sources":["../../src/judges/api-design.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,cAAc,GAAoB;IAC7C,EAAE,EAAE,YAAY;IAChB,IAAI,EAAE,kBAAkB;IACxB,MAAM,EAAE,wBAAwB;IAChC,WAAW,EACT,6KAA6K;IAC/K,UAAU,EAAE,KAAK;IACjB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;gIA2BgH;CAC/H,CAAC"}

package/dist/judges/cloud-readiness.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"cloud-readiness.d.ts","sourceRoot":"","sources":["../../src/judges/cloud-readiness.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,mBAAmB,EAAE,eA2BjC,CAAC"}
+{"version":3,"file":"cloud-readiness.d.ts","sourceRoot":"","sources":["../../src/judges/cloud-readiness.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,mBAAmB,EAAE,eAiCjC,CAAC"}

package/dist/judges/cloud-readiness.js

@@ -23,6 +23,12 @@ RULES FOR YOUR EVALUATION:
 - Reference the 12-Factor App methodology, CNCF patterns, and Well-Architected Framework principles.
 - Distinguish between "can run in the cloud" and "cloud-native."
 - Recommend specific services or patterns (e.g., "Use Azure Key Vault instead of .env files in production").
-- Score from 0-100 where 100 means fully cloud-native.`,
+- Score from 0-100 where 100 means fully cloud-native.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code is not cloud-ready and actively hunt for problems. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed cloud-readiness gaps.
+- Absence of findings does not mean the code is cloud-native. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=cloud-readiness.js.map

package/dist/judges/cloud-readiness.js.map

@@ -1 +1 @@
-{"version":3,"file":"cloud-readiness.js","sourceRoot":"","sources":["../../src/judges/cloud-readiness.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,mBAAmB,GAAoB;IAClD,EAAE,EAAE,iBAAiB;IACrB,IAAI,EAAE,uBAAuB;IAC7B,MAAM,EAAE,oCAAoC;IAC5C,WAAW,EACT,4JAA4J;IAC9J,UAAU,EAAE,OAAO;IACnB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;uDAmBuC;CACtD,CAAC"}
+{"version":3,"file":"cloud-readiness.js","sourceRoot":"","sources":["../../src/judges/cloud-readiness.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,mBAAmB,GAAoB;IAClD,EAAE,EAAE,iBAAiB;IACrB,IAAI,EAAE,uBAAuB;IAC7B,MAAM,EAAE,oCAAoC;IAC5C,WAAW,EACT,4JAA4J;IAC9J,UAAU,EAAE,OAAO;IACnB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;gIAyBgH;CAC/H,CAAC"}

package/dist/judges/compliance.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"compliance.d.ts","sourceRoot":"","sources":["../../src/judges/compliance.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,eAAe,EAAE,eA2B7B,CAAC"}
+{"version":3,"file":"compliance.d.ts","sourceRoot":"","sources":["../../src/judges/compliance.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,eAAe,EAAE,eAiC7B,CAAC"}

package/dist/judges/compliance.js

@@ -23,6 +23,12 @@ RULES FOR YOUR EVALUATION:
 - Reference specific regulations and standards (SOC 2 CC6.1, PCI-DSS Req 3.4, GDPR Art. 17).
 - Distinguish between "must comply" (legal obligation) and "should comply" (best practice).
 - Recommend both code changes and process changes where applicable.
-- Score from 0-100 where 100 means fully compliant.`,
+- Score from 0-100 where 100 means fully compliant.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code has compliance gaps and actively hunt for them. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed compliance violations.
+- Absence of findings does not mean the code is compliant. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=compliance.js.map

package/dist/judges/compliance.js.map

@@ -1 +1 @@
-{"version":3,"file":"compliance.js","sourceRoot":"","sources":["../../src/judges/compliance.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,eAAe,GAAoB;IAC9C,EAAE,EAAE,YAAY;IAChB,IAAI,EAAE,kBAAkB;IACxB,MAAM,EAAE,iCAAiC;IACzC,WAAW,EACT,6JAA6J;IAC/J,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;oDAmBoC;CACnD,CAAC"}
+{"version":3,"file":"compliance.js","sourceRoot":"","sources":["../../src/judges/compliance.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,eAAe,GAAoB;IAC9C,EAAE,EAAE,YAAY;IAChB,IAAI,EAAE,kBAAkB;IACxB,MAAM,EAAE,iCAAiC;IACzC,WAAW,EACT,6JAA6J;IAC/J,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;6HAyB6G;CAC5H,CAAC"}

package/dist/judges/concurrency.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"concurrency.d.ts","sourceRoot":"","sources":["../../src/judges/concurrency.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,gBAAgB,EAAE,eA6B9B,CAAC"}
+{"version":3,"file":"concurrency.d.ts","sourceRoot":"","sources":["../../src/judges/concurrency.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,gBAAgB,EAAE,eAmC9B,CAAC"}

package/dist/judges/concurrency.js

@@ -25,6 +25,12 @@ RULES FOR YOUR EVALUATION:
 - Describe the exact sequence of events that could trigger a race condition or deadlock.
 - Recommend specific concurrency primitives or patterns for each issue.
 - Reference Java Concurrency in Practice, Go concurrency patterns, or Rust ownership model as applicable.
-- Score from 0-100 where 100 means thread-safe and correctly concurrent.`,
+- Score from 0-100 where 100 means thread-safe and correctly concurrent.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code has concurrency bugs and actively hunt for them. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed race conditions.
+- Absence of findings does not mean the code is thread-safe. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=concurrency.js.map

package/dist/judges/concurrency.js.map

@@ -1 +1 @@
-{"version":3,"file":"concurrency.js","sourceRoot":"","sources":["../../src/judges/concurrency.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,gBAAgB,GAAoB;IAC/C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,mBAAmB;IACzB,MAAM,EAAE,6BAA6B;IACrC,WAAW,EACT,uIAAuI;IACzI,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;yEAqByD;CACxE,CAAC"}
+{"version":3,"file":"concurrency.js","sourceRoot":"","sources":["../../src/judges/concurrency.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,gBAAgB,GAAoB;IAC/C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,mBAAmB;IACzB,MAAM,EAAE,6BAA6B;IACrC,WAAW,EACT,uIAAuI;IACzI,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;+HA2B+G;CAC9H,CAAC"}

package/dist/judges/cost-effectiveness.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"cost-effectiveness.d.ts","sourceRoot":"","sources":["../../src/judges/cost-effectiveness.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,sBAAsB,EAAE,eA0BpC,CAAC"}
+{"version":3,"file":"cost-effectiveness.d.ts","sourceRoot":"","sources":["../../src/judges/cost-effectiveness.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,sBAAsB,EAAE,eAgCpC,CAAC"}

package/dist/judges/cost-effectiveness.js

@@ -22,6 +22,12 @@ RULES FOR YOUR EVALUATION:
 - Quantify impact where possible (e.g. "This N+1 pattern will generate ~1000 extra queries per request at scale").
 - Recommend specific optimizations with estimated savings.
 - Consider both runtime cost and developer productivity cost.
-- Score from 0-100 where 100 means optimally cost-effective.`,
+- Score from 0-100 where 100 means optimally cost-effective.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code wastes resources and actively hunt for inefficiencies. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed cost waste.
+- Absence of findings does not mean the code is cost-effective. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=cost-effectiveness.js.map

package/dist/judges/cost-effectiveness.js.map

@@ -1 +1 @@
-{"version":3,"file":"cost-effectiveness.js","sourceRoot":"","sources":["../../src/judges/cost-effectiveness.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,sBAAsB,GAAoB;IACrD,EAAE,EAAE,oBAAoB;IACxB,IAAI,EAAE,0BAA0B;IAChC,MAAM,EAAE,yCAAyC;IACjD,WAAW,EACT,sJAAsJ;IACxJ,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;6DAkB6C;CAC5D,CAAC"}
+{"version":3,"file":"cost-effectiveness.js","sourceRoot":"","sources":["../../src/judges/cost-effectiveness.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,sBAAsB,GAAoB;IACrD,EAAE,EAAE,oBAAoB;IACxB,IAAI,EAAE,0BAA0B;IAChC,MAAM,EAAE,yCAAyC;IACjD,WAAW,EACT,sJAAsJ;IACxJ,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;kIAwBkH;CACjI,CAAC"}

package/dist/judges/cybersecurity.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"cybersecurity.d.ts","sourceRoot":"","sources":["../../src/judges/cybersecurity.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,kBAAkB,EAAE,eA0BhC,CAAC"}
+{"version":3,"file":"cybersecurity.d.ts","sourceRoot":"","sources":["../../src/judges/cybersecurity.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,kBAAkB,EAAE,eAgChC,CAAC"}

package/dist/judges/cybersecurity.js

@@ -22,6 +22,12 @@ RULES FOR YOUR EVALUATION:
 - Think like an attacker: describe how each vulnerability could be exploited.
 - Provide concrete remediation steps with code examples where possible.
 - Reference OWASP, CWE IDs, and CVE IDs where applicable.
-- Score from 0-100 where 100 means no exploitable vulnerabilities found.`,
+- Score from 0-100 where 100 means no exploitable vulnerabilities found.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code is vulnerable and actively hunt for exploits. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed vulnerabilities.
+- Absence of findings does not mean the code is secure. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=cybersecurity.js.map

package/dist/judges/cybersecurity.js.map

@@ -1 +1 @@
-{"version":3,"file":"cybersecurity.js","sourceRoot":"","sources":["../../src/judges/cybersecurity.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,kBAAkB,GAAoB;IACjD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,gCAAgC;IACxC,WAAW,EACT,0KAA0K;IAC5K,UAAU,EAAE,OAAO;IACnB,YAAY,EAAE;;;;;;;;;;;;;;;;;;yEAkByD;CACxE,CAAC"}
+{"version":3,"file":"cybersecurity.js","sourceRoot":"","sources":["../../src/judges/cybersecurity.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,kBAAkB,GAAoB;IACjD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,gCAAgC;IACxC,WAAW,EACT,0KAA0K;IAC5K,UAAU,EAAE,OAAO;IACnB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;0HAwB0G;CACzH,CAAC"}

package/dist/judges/data-security.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data-security.d.ts","sourceRoot":"","sources":["../../src/judges/data-security.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,iBAAiB,EAAE,eAwB/B,CAAC"}
+{"version":3,"file":"data-security.d.ts","sourceRoot":"","sources":["../../src/judges/data-security.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,iBAAiB,EAAE,eA8B/B,CAAC"}

package/dist/judges/data-security.js

@@ -20,6 +20,12 @@ RULES FOR YOUR EVALUATION:
 - Be specific: cite exact lines, variable names, or patterns.
 - Always recommend a concrete fix, not just "fix this."
 - Reference standards where applicable (OWASP, NIST 800-53, GDPR Article numbers).
-- Score from 0-100 where 100 means fully compliant with no findings.`,
+- Score from 0-100 where 100 means fully compliant with no findings.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code leaks or mishandles data and actively hunt for exposures. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed data breaches.
+- Absence of findings does not mean data is secure. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=data-security.js.map

package/dist/judges/data-security.js.map

@@ -1 +1 @@
-{"version":3,"file":"data-security.js","sourceRoot":"","sources":["../../src/judges/data-security.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,iBAAiB,GAAoB;IAChD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,yBAAyB;IACjC,WAAW,EACT,8LAA8L;IAChM,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;qEAgBqD;CACpE,CAAC"}
+{"version":3,"file":"data-security.js","sourceRoot":"","sources":["../../src/judges/data-security.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,iBAAiB,GAAoB;IAChD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,yBAAyB;IACjC,WAAW,EACT,8LAA8L;IAChM,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;sHAsBsG;CACrH,CAAC"}

package/dist/judges/dependency-health.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"dependency-health.d.ts","sourceRoot":"","sources":["../../src/judges/dependency-health.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,qBAAqB,EAAE,eA6BnC,CAAC"}
+{"version":3,"file":"dependency-health.d.ts","sourceRoot":"","sources":["../../src/judges/dependency-health.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,qBAAqB,EAAE,eAmCnC,CAAC"}

package/dist/judges/dependency-health.js

@@ -25,6 +25,12 @@ RULES FOR YOUR EVALUATION:
 - Reference OWASP Dependency-Check, OpenSSF Scorecard, and supply chain security best practices.
 - Recommend specific alternatives for problematic dependencies.
 - Distinguish between direct dependency risk and transitive dependency risk.
-- Score from 0-100 where 100 means healthy, secure dependency tree.`,
+- Score from 0-100 where 100 means healthy, secure dependency tree.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the dependency tree has risks and actively hunt for them. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed supply chain risks.
+- Absence of findings does not mean dependencies are healthy. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=dependency-health.js.map

package/dist/judges/dependency-health.js.map

@@ -1 +1 @@
-{"version":3,"file":"dependency-health.js","sourceRoot":"","sources":["../../src/judges/dependency-health.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,qBAAqB,GAAoB;IACpD,EAAE,EAAE,mBAAmB;IACvB,IAAI,EAAE,yBAAyB;IAC/B,MAAM,EAAE,6BAA6B;IACrC,WAAW,EACT,uJAAuJ;IACzJ,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;oEAqBoD;CACnE,CAAC"}
+{"version":3,"file":"dependency-health.js","sourceRoot":"","sources":["../../src/judges/dependency-health.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,qBAAqB,GAAoB;IACpD,EAAE,EAAE,mBAAmB;IACvB,IAAI,EAAE,yBAAyB;IAC/B,MAAM,EAAE,6BAA6B;IACrC,WAAW,EACT,uJAAuJ;IACzJ,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;gIA2BgH;CAC/H,CAAC"}

package/dist/judges/documentation.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"documentation.d.ts","sourceRoot":"","sources":["../../src/judges/documentation.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,kBAAkB,EAAE,eA6BhC,CAAC"}
+{"version":3,"file":"documentation.d.ts","sourceRoot":"","sources":["../../src/judges/documentation.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,kBAAkB,EAAE,eAmChC,CAAC"}

package/dist/judges/documentation.js

@@ -25,6 +25,12 @@ RULES FOR YOUR EVALUATION:
 - Reference documentation best practices (Diátaxis framework, Google developer documentation style guide).
 - Provide example documentation snippets in recommendations.
 - Evaluate from the perspective of a new developer encountering the code for the first time.
-- Score from 0-100 where 100 means exemplary documentation.`,
+- Score from 0-100 where 100 means exemplary documentation.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the documentation is inadequate and actively hunt for gaps. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed documentation gaps.
+- Absence of findings does not mean the documentation is good. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=documentation.js.map

package/dist/judges/documentation.js.map

@@ -1 +1 @@
-{"version":3,"file":"documentation.js","sourceRoot":"","sources":["../../src/judges/documentation.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,kBAAkB,GAAoB;IACjD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,sCAAsC;IAC9C,WAAW,EACT,6JAA6J;IAC/J,UAAU,EAAE,KAAK;IACjB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;4DAqB4C;CAC3D,CAAC"}
+{"version":3,"file":"documentation.js","sourceRoot":"","sources":["../../src/judges/documentation.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,kBAAkB,GAAoB;IACjD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,sCAAsC;IAC9C,WAAW,EACT,6JAA6J;IAC/J,UAAU,EAAE,KAAK;IACjB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;iIA2BiH;CAChI,CAAC"}

package/dist/judges/ethics-bias.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"ethics-bias.d.ts","sourceRoot":"","sources":["../../src/judges/ethics-bias.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,eAAe,EAAE,eA6B7B,CAAC"}
+{"version":3,"file":"ethics-bias.d.ts","sourceRoot":"","sources":["../../src/judges/ethics-bias.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,eAAe,EAAE,eAmC7B,CAAC"}

package/dist/judges/ethics-bias.js

@@ -25,6 +25,12 @@ RULES FOR YOUR EVALUATION:
 - Reference the EU AI Act, NIST AI RMF (AI 100-1), IEEE Ethically Aligned Design.
 - Recommend specific fairness tools (Fairlearn, AI Fairness 360, What-If Tool).
 - Evaluate proportionally: not all code involves AI/ML — score based on relevance.
-- Score from 0-100 where 100 means fully ethical and bias-aware.`,
+- Score from 0-100 where 100 means fully ethical and bias-aware.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code has ethical risks or bias and actively hunt for them. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed ethical violations.
+- Absence of findings does not mean the code is ethical. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=ethics-bias.js.map

package/dist/judges/ethics-bias.js.map

@@ -1 +1 @@
-{"version":3,"file":"ethics-bias.js","sourceRoot":"","sources":["../../src/judges/ethics-bias.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,eAAe,GAAoB;IAC9C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,yBAAyB;IACjC,WAAW,EACT,0JAA0J;IAC5J,UAAU,EAAE,QAAQ;IACpB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;iEAqBiD;CAChE,CAAC"}
+{"version":3,"file":"ethics-bias.js","sourceRoot":"","sources":["../../src/judges/ethics-bias.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,eAAe,GAAoB;IAC9C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,yBAAyB;IACjC,WAAW,EACT,0JAA0J;IAC5J,UAAU,EAAE,QAAQ;IACpB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;2HA2B2G;CAC1H,CAAC"}

package/dist/judges/internationalization.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"internationalization.d.ts","sourceRoot":"","sources":["../../src/judges/internationalization.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,yBAAyB,EAAE,eA2BvC,CAAC"}
+{"version":3,"file":"internationalization.d.ts","sourceRoot":"","sources":["../../src/judges/internationalization.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,yBAAyB,EAAE,eAiCvC,CAAC"}

package/dist/judges/internationalization.js

@@ -23,6 +23,12 @@ RULES FOR YOUR EVALUATION:
 - Reference Unicode standards, CLDR, W3C i18n best practices.
 - Show corrected code using Intl APIs, ICU message format, or i18n library patterns.
 - Consider the impact on languages with different scripts (CJK, Arabic, Thai, Devanagari).
-- Score from 0-100 where 100 means fully internationalization-ready.`,
+- Score from 0-100 where 100 means fully internationalization-ready.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code will break in non-English locales and actively hunt for i18n defects. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed i18n problems.
+- Absence of findings does not mean the code is internationalization-ready. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=internationalization.js.map

package/dist/judges/internationalization.js.map

@@ -1 +1 @@
-{"version":3,"file":"internationalization.js","sourceRoot":"","sources":["../../src/judges/internationalization.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,yBAAyB,GAAoB;IACxD,EAAE,EAAE,sBAAsB;IAC1B,IAAI,EAAE,4BAA4B;IAClC,MAAM,EAAE,qBAAqB;IAC7B,WAAW,EACT,oJAAoJ;IACtJ,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;qEAmBqD;CACpE,CAAC"}
+{"version":3,"file":"internationalization.js","sourceRoot":"","sources":["../../src/judges/internationalization.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,yBAAyB,GAAoB;IACxD,EAAE,EAAE,sBAAsB;IAC1B,IAAI,EAAE,4BAA4B;IAClC,MAAM,EAAE,qBAAqB;IAC7B,WAAW,EACT,oJAAoJ;IACtJ,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;8IAyB8H;CAC7I,CAAC"}

package/dist/judges/observability.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"observability.d.ts","sourceRoot":"","sources":["../../src/judges/observability.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,kBAAkB,EAAE,eA2BhC,CAAC"}
+{"version":3,"file":"observability.d.ts","sourceRoot":"","sources":["../../src/judges/observability.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,kBAAkB,EAAE,eAiChC,CAAC"}

package/dist/judges/observability.js

@@ -23,6 +23,12 @@ RULES FOR YOUR EVALUATION:
 - Reference OpenTelemetry semantic conventions and Prometheus best practices.
 - Recommend specific instrumentation code snippets.
 - Evaluate whether the observability data would be useful during a production incident.
-- Score from 0-100 where 100 means fully observable and debuggable in production.`,
+- Score from 0-100 where 100 means fully observable and debuggable in production.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code is unobservable and will be impossible to debug in production. Actively hunt for monitoring gaps. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed observability gaps.
+- Absence of findings does not mean the code is observable. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=observability.js.map

package/dist/judges/observability.js.map

@@ -1 +1 @@
-{"version":3,"file":"observability.js","sourceRoot":"","sources":["../../src/judges/observability.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,kBAAkB,GAAoB;IACjD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,0BAA0B;IAClC,WAAW,EACT,8JAA8J;IAChK,UAAU,EAAE,KAAK;IACjB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;kFAmBkE;CACjF,CAAC"}
+{"version":3,"file":"observability.js","sourceRoot":"","sources":["../../src/judges/observability.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,kBAAkB,GAAoB;IACjD,EAAE,EAAE,eAAe;IACnB,IAAI,EAAE,qBAAqB;IAC3B,MAAM,EAAE,0BAA0B;IAClC,WAAW,EACT,8JAA8J;IAChK,UAAU,EAAE,KAAK;IACjB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;8HAyB8G;CAC7H,CAAC"}

package/dist/judges/performance.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"performance.d.ts","sourceRoot":"","sources":["../../src/judges/performance.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,gBAAgB,EAAE,eA6B9B,CAAC"}
+{"version":3,"file":"performance.d.ts","sourceRoot":"","sources":["../../src/judges/performance.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,gBAAgB,EAAE,eAmC9B,CAAC"}

package/dist/judges/performance.js

@@ -25,6 +25,12 @@ RULES FOR YOUR EVALUATION:
 - Quantify impact where possible (e.g., "This creates ~10,000 objects per request that will pressure GC").
 - Recommend specific optimizations with before/after code examples.
 - Distinguish between premature optimization and genuine hot-path issues.
-- Score from 0-100 where 100 means optimally performant.`,
+- Score from 0-100 where 100 means optimally performant.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code has performance problems and actively hunt for bottlenecks. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed performance regressions.
+- Absence of findings does not mean the code is performant. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=performance.js.map

package/dist/judges/performance.js.map

@@ -1 +1 @@
-{"version":3,"file":"performance.js","sourceRoot":"","sources":["../../src/judges/performance.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,gBAAgB,GAAoB;IAC/C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,mBAAmB;IACzB,MAAM,EAAE,qBAAqB;IAC7B,WAAW,EACT,kKAAkK;IACpK,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;yDAqByC;CACxD,CAAC"}
+{"version":3,"file":"performance.js","sourceRoot":"","sources":["../../src/judges/performance.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,gBAAgB,GAAoB;IAC/C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,mBAAmB;IACzB,MAAM,EAAE,qBAAqB;IAC7B,WAAW,EACT,kKAAkK;IACpK,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;8HA2B8G;CAC7H,CAAC"}

package/dist/judges/reliability.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"reliability.d.ts","sourceRoot":"","sources":["../../src/judges/reliability.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,gBAAgB,EAAE,eA6B9B,CAAC"}
+{"version":3,"file":"reliability.d.ts","sourceRoot":"","sources":["../../src/judges/reliability.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,gBAAgB,EAAE,eAmC9B,CAAC"}

package/dist/judges/reliability.js

@@ -25,6 +25,12 @@ RULES FOR YOUR EVALUATION:
 - Reference patterns from "Release It!" (Michael Nygard) and the SRE book (Google).
 - Describe failure scenarios: "If X fails, then Y happens, causing Z impact."
 - Recommend specific resilience libraries or patterns with configuration examples.
-- Score from 0-100 where 100 means highly resilient and fault-tolerant.`,
+- Score from 0-100 where 100 means highly resilient and fault-tolerant.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code will fail in production and actively hunt for reliability gaps. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed reliability risks.
+- Absence of findings does not mean the code is reliable. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=reliability.js.map

package/dist/judges/reliability.js.map

@@ -1 +1 @@
-{"version":3,"file":"reliability.js","sourceRoot":"","sources":["../../src/judges/reliability.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,gBAAgB,GAAoB;IAC/C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,mBAAmB;IACzB,MAAM,EAAE,0BAA0B;IAClC,WAAW,EACT,gKAAgK;IAClK,UAAU,EAAE,KAAK;IACjB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;wEAqBwD;CACvE,CAAC"}
+{"version":3,"file":"reliability.js","sourceRoot":"","sources":["../../src/judges/reliability.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,gBAAgB,GAAoB;IAC/C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,mBAAmB;IACzB,MAAM,EAAE,0BAA0B;IAClC,WAAW,EACT,gKAAgK;IAClK,UAAU,EAAE,KAAK;IACjB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;4HA2B4G;CAC3H,CAAC"}

package/dist/judges/scalability.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"scalability.d.ts","sourceRoot":"","sources":["../../src/judges/scalability.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,gBAAgB,EAAE,eA2B9B,CAAC"}
+{"version":3,"file":"scalability.d.ts","sourceRoot":"","sources":["../../src/judges/scalability.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,gBAAgB,EAAE,eAiC9B,CAAC"}

package/dist/judges/scalability.js

@@ -23,6 +23,12 @@ RULES FOR YOUR EVALUATION:
 - Think about what breaks first when traffic increases 10x or 100x.
 - Distinguish between "works now" and "will work at scale."
 - Recommend specific architectural patterns (CQRS, event sourcing, circuit breakers, etc.).
-- Score from 0-100 where 100 means fully scalable with no bottlenecks.`,
+- Score from 0-100 where 100 means fully scalable with no bottlenecks.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code will not scale and actively hunt for bottlenecks. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed scalability limits.
+- Absence of findings does not mean the code will scale. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=scalability.js.map

package/dist/judges/scalability.js.map

@@ -1 +1 @@
-{"version":3,"file":"scalability.js","sourceRoot":"","sources":["../../src/judges/scalability.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,gBAAgB,GAAoB;IAC/C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,mBAAmB;IACzB,MAAM,EAAE,2BAA2B;IACnC,WAAW,EACT,+JAA+J;IACjK,UAAU,EAAE,OAAO;IACnB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;uEAmBuD;CACtE,CAAC"}
+{"version":3,"file":"scalability.js","sourceRoot":"","sources":["../../src/judges/scalability.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,gBAAgB,GAAoB;IAC/C,EAAE,EAAE,aAAa;IACjB,IAAI,EAAE,mBAAmB;IACzB,MAAM,EAAE,2BAA2B;IACnC,WAAW,EACT,+JAA+J;IACjK,UAAU,EAAE,OAAO;IACnB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;2HAyB2G;CAC1H,CAAC"}

package/dist/judges/software-practices.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"software-practices.d.ts","sourceRoot":"","sources":["../../src/judges/software-practices.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,sBAAsB,EAAE,eA6BpC,CAAC"}
+{"version":3,"file":"software-practices.d.ts","sourceRoot":"","sources":["../../src/judges/software-practices.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,sBAAsB,EAAE,eAmCpC,CAAC"}

package/dist/judges/software-practices.js

@@ -22,9 +22,15 @@ YOUR EVALUATION CRITERIA:
 
 RULES FOR YOUR EVALUATION:
 - Assign rule IDs with prefix "SWDEV-" (e.g. SWDEV-001).
-- Be constructive: explain why a practice matters, not just that it's wrong.
+- Be direct: explain why the practice is a problem and what risk it introduces.
 - Provide refactored code examples when recommending improvements.
 - Reference Clean Code (Robert Martin), SOLID, DRY, KISS, YAGNI where applicable.
-- Score from 0-100 where 100 means exemplary software engineering.`,
+- Score from 0-100 where 100 means exemplary software engineering.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the code has engineering quality problems and actively hunt for them. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed code quality issues.
+- Absence of findings does not mean the code follows best practices. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=software-practices.js.map

package/dist/judges/software-practices.js.map

@@ -1 +1 @@
-{"version":3,"file":"software-practices.js","sourceRoot":"","sources":["../../src/judges/software-practices.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,sBAAsB,GAAoB;IACrD,EAAE,EAAE,oBAAoB;IACxB,IAAI,EAAE,0BAA0B;IAChC,MAAM,EAAE,mDAAmD;IAC3D,WAAW,EACT,6LAA6L;IAC/L,UAAU,EAAE,OAAO;IACnB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;mEAqBmD;CAClE,CAAC"}
+{"version":3,"file":"software-practices.js","sourceRoot":"","sources":["../../src/judges/software-practices.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,sBAAsB,GAAoB;IACrD,EAAE,EAAE,oBAAoB;IACxB,IAAI,EAAE,0BAA0B;IAChC,MAAM,EAAE,mDAAmD;IAC3D,WAAW,EACT,6LAA6L;IAC/L,UAAU,EAAE,OAAO;IACnB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;uIA2BuH;CACtI,CAAC"}

package/dist/judges/testing.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"testing.d.ts","sourceRoot":"","sources":["../../src/judges/testing.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,YAAY,EAAE,eA6B1B,CAAC"}
+{"version":3,"file":"testing.d.ts","sourceRoot":"","sources":["../../src/judges/testing.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C,eAAO,MAAM,YAAY,EAAE,eAmC1B,CAAC"}

package/dist/judges/testing.js

@@ -25,6 +25,12 @@ RULES FOR YOUR EVALUATION:
 - Reference testing best practices (Kent Beck, Martin Fowler's Test Pyramid, FIRST principles).
 - Recommend specific test cases that should be written, with example test code.
 - Evaluate both the tests AND the testability of the code under test.
-- Score from 0-100 where 100 means comprehensive, well-structured test suite.`,
+- Score from 0-100 where 100 means comprehensive, well-structured test suite.
+
+ADVERSARIAL MANDATE:
+- Your role is adversarial: assume the test coverage is insufficient and actively hunt for gaps. Do not give the benefit of the doubt.
+- Never praise or compliment the code. Report only problems, risks, and deficiencies.
+- If you are uncertain whether something is an issue, flag it — false positives are preferred over missed testing gaps.
+- Absence of findings does not mean the code is well-tested. It means your analysis reached its limits. State this explicitly.`,
 };
 //# sourceMappingURL=testing.js.map

package/dist/judges/testing.js.map

@@ -1 +1 @@
-{"version":3,"file":"testing.js","sourceRoot":"","sources":["../../src/judges/testing.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,YAAY,GAAoB;IAC3C,EAAE,EAAE,SAAS;IACb,IAAI,EAAE,eAAe;IACrB,MAAM,EAAE,yBAAyB;IACjC,WAAW,EACT,oKAAoK;IACtK,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;8EAqB8D;CAC7E,CAAC"}
+{"version":3,"file":"testing.js","sourceRoot":"","sources":["../../src/judges/testing.ts"],"names":[],"mappings":"AAEA,MAAM,CAAC,MAAM,YAAY,GAAoB;IAC3C,EAAE,EAAE,SAAS;IACb,IAAI,EAAE,eAAe;IACrB,MAAM,EAAE,yBAAyB;IACjC,WAAW,EACT,oKAAoK;IACtK,UAAU,EAAE,MAAM;IAClB,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;+HA2B+G;CAC9H,CAAC"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kevinrabun/judges",
-  "version": "1.0.2",
+  "version": "1.2.0",
   "description": "18 specialized judges that evaluate AI-generated code for security, cost, and quality.",
   "mcpName": "io.github.KevinRabun/judges",
   "type": "module",
@@ -19,6 +19,8 @@
     "start": "node dist/index.js",
     "dev": "tsc --watch",
     "clean": "rimraf dist",
+    "test": "npx tsx --test tests/judges.test.ts",
+    "demo": "npx tsx examples/demo.ts",
     "prepublishOnly": "npm run build"
   },
   "keywords": [
@@ -48,6 +50,7 @@
   },
   "devDependencies": {
     "@types/node": "^25.3.0",
+    "tsx": "^4.19.4",
     "typescript": "^5.9.3"
   }
 }

package/server.json

@@ -7,12 +7,12 @@
     "url": "https://github.com/kevinrabun/judges",
     "source": "github"
   },
-  "version": "1.0.2",
+  "version": "1.2.0",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@kevinrabun/judges",
-      "version": "1.0.2",
+      "version": "1.2.0",
       "transport": {
         "type": "stdio"
       }