Judges Panel

Judges Panel

An MCP (Model Context Protocol) server that provides a panel of 45 specialized judges to evaluate AI-generated code — acting as an independent quality gate regardless of which project is being reviewed. Combines deterministic pattern matching & AST analysis (instant, offline, zero LLM calls) with LLM-powered deep-review prompts that let your AI assistant perform expert-persona analysis across all 45 domains.

Highlights:

• Includes an App Builder Workflow (3-step) demo for release decisions, plain-language risk summaries, and prioritized fixes — see Try the Demo.
• Includes V2 context-aware evaluation with policy profiles, evidence calibration, specialty feedback, confidence scoring, and uncertainty reporting.
• Includes public repository URL reporting to clone a repo, run the full tribunal, and output a consolidated markdown report.
• 200+ deterministic auto-fix patches (see src/patches/index.ts) plus LLM-powered deep review.

🧪 Many commands in printHelp are experimental/roadmap. By default, we show GA commands only. Set JUDGES_SHOW_EXPERIMENTAL=1 to reveal stubs; these may not be wired yet.

🔰 Packages

• CLI: @kevinrabun/judges-cli → binary judges (use npx @kevinrabun/judges-cli eval --file app.ts).
• MCP/API: @kevinrabun/judges → programmatic API + MCP server (npm install @kevinrabun/judges).
• VS Code extension: see vscode-extension/.
• GitHub Action: uses: KevinRabun/judges@main (see CI quickstart).

---

Quickstart

CLI (one-off)

# Using the CLI package (recommended)
npx @kevinrabun/judges-cli eval --file src/app.ts

# Show GA commands only (default)
npx @kevinrabun/judges-cli --help

# Show experimental/roadmap commands
echo "JUDGES_SHOW_EXPERIMENTAL=1" >> $GITHUB_ENV
npx @kevinrabun/judges-cli --help

# License scan (supply-chain & license compliance)
npx @kevinrabun/judges-cli license-scan --dir .

CLI vs API: If you want to embed Judges in your app (MCP/API), install @kevinrabun/judges. For the command-line, use @kevinrabun/judges-cli (binary judges).

GitHub Action

name: Judges
on: [pull_request, push]
jobs:
  judges:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: KevinRabun/judges@main
        with:
          path: .
          diff-only: true           # evaluate only changed lines in PRs (default true)
          fail-on-findings: true    # fail on critical/high findings
          upload-sarif: true        # upload SARIF to GitHub Code Scanning

Programmatic API (MCP server included)

npm install @kevinrabun/judges

import { evaluateCode } from "@kevinrabun/judges/api";
const verdict = evaluateCode("const password = 'ProdSecret';", "typescript");
console.log(verdict.overallVerdict, verdict.overallScore);

MCP server

The MCP server runs on stdio and is started by your MCP client (VS Code, Claude Desktop, etc.). Configure it in your MCP settings (e.g. mcp.json):

{
  "servers": {
    "judges": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@kevinrabun/judges"]
    }
  }
}

Or run the server directly:

npx @kevinrabun/judges
# Starts the MCP server on stdio

Config file: .judgesrc.json (supports ${ENV_VAR} substitution via expandEnvPlaceholders). See Configuration.

---

Why Judges?

AI code generators (Copilot, Cursor, Claude, ChatGPT, etc.) write code fast — but they routinely produce insecure defaults, missing auth, hardcoded secrets, and poor error handling. Human reviewers catch some of this, but nobody reviews 45 dimensions consistently.

	ESLint / Biome	SonarQube	Semgrep / CodeQL	Judges
Scope	Style + some bugs	Bugs + code smells	Security patterns	45 domains: security, cost, compliance, a11y, API design, cloud, UX, …
AI-generated code focus	No	No	Partial	Purpose-built for AI output failure modes
Setup	Config per project	Server + scanner	Cloud or local	One command: npx @kevinrabun/judges-cli eval file.ts
Auto-fix patches	Some	No	No	200+ deterministic patches — instant, offline
Non-technical output	No	Dashboard	No	Plain-language findings with What/Why/Next
MCP native	No	No	No	Yes — works inside Copilot, Claude, Cursor
SARIF output	No	Yes	Yes	Yes — upload to GitHub Code Scanning
Cost	Free	$$$$	Free/paid	Free / MIT

Judges doesn't replace linters — it covers the dimensions linters don't: authentication strategy, data sovereignty, cost patterns, accessibility, framework-specific anti-patterns, and architectural issues across multiple files.

---

Quick Start

Prereqs: Node.js >=18 (>=20 recommended), npx available. The judges CLI binary ships with @kevinrabun/judges-cli (preferred) and also works via npx @kevinrabun/judges.

Packages:

• CLI: npm install -g @kevinrabun/judges-cli (or npx @kevinrabun/judges-cli ...)
• MCP/API: npm install @kevinrabun/judges

Use @kevinrabun/judges for the MCP server and programmatic API. Use @kevinrabun/judges-cli when you want the judges terminal command.

Try it now (no clone needed)

# Install the CLI globally
npm install -g @kevinrabun/judges-cli

# Evaluate any file
judges eval src/app.ts

# Pipe from stdin
cat api.py | judges eval --language python

# Single judge
judges eval --judge cybersecurity server.ts

# SARIF output for CI
judges eval --file app.ts --format sarif > results.sarif

# HTML report with severity filters and dark/light theme
judges eval --file app.ts --format html > report.html

# Fail CI on findings (exit code 1)
judges eval --fail-on-findings src/api.ts

# Suppress known findings via baseline
judges eval --baseline baseline.json src/api.ts

# Use a named preset
judges eval --preset security-only src/api.ts

# Use a config file
judges eval --config .judgesrc.json src/api.ts

# Set a minimum score threshold (exit 1 if below)
judges eval --min-score 80 src/api.ts

# One-line summary for scripts
judges eval --summary src/api.ts

# Agentic skills (orchestrated judge sets)
judges skill ai-code-review --file src/app.ts
judges skill security-review --file src/api.ts --format json
judges skill release-gate --file src/app.ts
judges skills   # list available skills

> Full catalog: [`docs/skills.md`](docs/skills.md)

# List all 45 judges
judges list

Additional CLI Commands

# Interactive project setup wizard
judges init

# Preview auto-fix patches (dry run)
judges fix src/app.ts

# Apply patches directly
judges fix src/app.ts --apply

# License compliance scan (copyleft/unknown detection)
judges license-scan --format json --risk high

# Watch mode — re-evaluate on file save
judges watch src/

# Project-level report (local directory)
judges report . --format html --output report.html

# Evaluate a unified diff (pipe from git diff)
git diff HEAD~1 | judges diff

# Analyze dependencies for supply-chain risks
judges deps --path . --format json

# Run GitHub App server (zero-config PR reviews)
judges app serve --port 4567

# Run GitHub PR review (gh CLI required)
judges review --pr 123 --repo owner/name --diff-only

# Auto-tune presets and configs
judges tune --dir . --apply

# Create a baseline file to suppress known findings
judges baseline create --file src/api.ts -o baseline.json

# Generate CI template files
judges ci-templates --provider github
judges ci-templates --provider gitlab
judges ci-templates --provider azure
judges ci-templates --provider bitbucket

# Generate per-judge rule documentation
judges docs
judges docs --judge cybersecurity
judges docs --output docs/

# Install shell completions
judges completions bash   # eval "$(judges completions bash)"
judges completions zsh
judges completions fish
judges completions powershell

# Install pre-commit hook
judges hook install

# Uninstall pre-commit hook
judges hook uninstall

🔎 Tip: The CLI help now defaults to GA commands only. To see experimental/roadmap commands, run:

JUDGES_SHOW_EXPERIMENTAL=1 judges --help

GitHub App (self-hosted webhook)

Run a zero-config PR reviewer as a GitHub App:

# Run the webhook server locally
judges app serve --port 4567

Required env vars:

• JUDGES_APP_ID – GitHub App ID
• JUDGES_PRIVATE_KEY or JUDGES_PRIVATE_KEY_PATH – PEM private key
• JUDGES_WEBHOOK_SECRET – signature verification secret

Optional:

• JUDGES_MIN_SEVERITY (default: medium)
• JUDGES_MAX_COMMENTS (default: 25)
• JUDGES_TEST_DRY_RUN=1 to avoid live network calls during tests

For local testing, you can expose http://localhost:4567/webhook via ngrok http 4567 and configure the GitHub App webhook URL accordingly.

Use in GitHub Actions

Add Judges to your CI pipeline with zero configuration:

# .github/workflows/judges.yml
name: Judges Code Review
on: [pull_request]

jobs:
  judges:
    runs-on: ubuntu-latest
    permissions:
      contents: read
      security-events: write  # only if using upload-sarif
    steps:
      - uses: actions/checkout@v4
      - uses: KevinRabun/judges@main
        with:
          path: src/api.ts        # file or directory
          format: text             # text | json | sarif | markdown
          upload-sarif: true       # upload to GitHub Code Scanning
          fail-on-findings: true   # fail CI on critical/high findings

Outputs available for downstream steps: verdict, score, findings, critical, high, sarif-file.

Use with Docker (no Node.js required)

# Build the image
docker build -t judges .

# Evaluate a local file
docker run --rm -v $(pwd):/code judges eval --file /code/app.ts

# Pipe from stdin
cat api.py | docker run --rm -i judges eval --language python

# List judges
docker run --rm judges list

Or use as an MCP server

1. Install and Build

git clone https://github.com/KevinRabun/judges.git
cd judges
npm install
npm run build

2. Try the Demo

Run the included demo to see all 45 judges evaluate a purposely flawed API server:

npm run demo

This evaluates 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.

The demo now also includes an App Builder Workflow (3-step) section. In a single run, you get both tribunal output and workflow output:

• Release decision (Ship now / Ship with caution / Do not ship)
• Plain-language summaries of top risks
• Prioritized remediation tasks and AI-fixable P0/P1 items

Sample workflow output (truncated):

╔══════════════════════════════════════════════════════════════╗
║             App Builder Workflow Demo (3-Step)             ║
╚══════════════════════════════════════════════════════════════╝

  Decision       : Do not ship
  Verdict        : FAIL (47/100)
  Risk Counts    : Critical 24 | High 27 | Medium 55

  Step 2 — Plain-Language Findings:
  - [CRITICAL] DATA-001: Hardcoded password detected
      What: ...
      Why : ...
      Next: ...

  Step 3 — Prioritized Tasks:
  - P0 | DEVELOPER | Effort L | DATA-001
      Task: ...
      Done: ...

  AI-Fixable Now (P0/P1):
  - P0 DATA-001: ...

Sample tribunal output (truncated):

╔══════════════════════════════════════════════════════════════╗
║           Judges Panel — Full Tribunal Demo                 ║
╚══════════════════════════════════════════════════════════════╝

  Overall Verdict : FAIL
  Overall Score   : 43/100
  Critical Issues : 15
  High Issues     : 17
  Total Findings  : 83
  Judges Run      : 33

  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 Maintainability           52/100    4 finding(s)
  ❌ Judge Error Handling            27/100    3 finding(s)
  ❌ Judge Authentication             0/100    4 finding(s)
  ❌ Judge Database                   0/100    5 finding(s)
  ❌ Judge Caching                   62/100    3 finding(s)
  ❌ Judge Configuration Mgmt         0/100    3 finding(s)
  ⚠️  Judge Backwards Compat         80/100    2 finding(s)
  ⚠️  Judge Portability              72/100    2 finding(s)
  ❌ Judge UX                        52/100    4 finding(s)
  ❌ Judge Logging Privacy            0/100    4 finding(s)
  ❌ Judge Rate Limiting             27/100    4 finding(s)
  ⚠️  Judge CI/CD                    80/100    2 finding(s)

3. Run the Tests

npm test

Runs automated tests covering all judges, AST parsers, markdown formatters, and edge cases.

4. Connect to Your Editor

VS Code (recommended — zero config)

Install the Judges Panel extension from the Marketplace. It provides:

• Inline diagnostics & quick-fixes on every file save
• @judges chat participant — type @judges in Copilot Chat, or just ask for a "judges panel review" and Copilot routes automatically
• Auto-configured MCP server — all 45 expert-persona prompts available to Copilot with zero setup

code --install-extension kevinrabun.judges-panel

VS Code — manual MCP config

If you prefer explicit workspace config (or want teammates without the extension to benefit), create .vscode/mcp.json:

{
  "servers": {
    "judges": {
      "command": "npx",
      "args": ["-y", "@kevinrabun/judges"]
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "judges": {
      "command": "npx",
      "args": ["-y", "@kevinrabun/judges"]
    }
  }
}

Cursor / other MCP clients

Use the same npx command for any MCP-compatible client:

{
  "command": "npx",
  "args": ["-y", "@kevinrabun/judges"]
}

5. Use Judges in GitHub Copilot PR Reviews

Yes — users can include Judges as part of GitHub-based review workflows, with one important caveat:

• The hosted copilot-pull-request-reviewer on GitHub does not currently let you directly attach arbitrary local MCP servers the same way VS Code does.
• The practical pattern is to run Judges in CI on each PR, publish a report/check, and have Copilot + human reviewers use that output during review.

Option A (recommended): PR workflow check + report artifact

Create .github/workflows/judges-pr-review.yml:

name: Judges PR Review

on:
  pull_request:
    types: [opened, synchronize, reopened]

jobs:
  judges:
    runs-on: ubuntu-latest
    permissions:
      contents: read
      pull-requests: write

    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Setup Node
        uses: actions/setup-node@v4
        with:
          node-version: 20
          cache: npm

      - name: Install
        run: npm ci

      - name: Generate Judges report
        run: |
          npx tsx -e "import { generateRepoReportFromLocalPath } from './src/reports/public-repo-report.ts';
          const result = generateRepoReportFromLocalPath({
            repoPath: process.cwd(),
            outputPath: 'judges-pr-report.md',
            maxFiles: 600,
            maxFindingsInReport: 150,
          });
          console.log('Overall:', result.overallVerdict, result.averageScore);"

      - name: Upload report artifact
        uses: actions/upload-artifact@v4
        with:
          name: judges-pr-report
          path: judges-pr-report.md

This gives every PR a reproducible Judges output your team (and Copilot) can reference.

Option B: Add Copilot custom instructions in-repo

Add .github/instructions/judges.instructions.md with guidance such as:

When reviewing pull requests:
1. Read the latest Judges report artifact/check output first.
2. Prioritize CRITICAL and HIGH findings in remediation guidance.
3. If findings conflict, defer to security/compliance-related Judges.
4. Include rule IDs (e.g., DATA-001, CYBER-004) in suggested fixes.

This helps keep Copilot feedback aligned with Judges findings.

---

CLI Reference

All commands support --help for usage details.

judges eval

Evaluate a file with all 45 judges or a single judge.

Flag	Description
--file <path> / positional	File to evaluate
--judge <id> / -j <id>	Single judge mode
--language <lang> / -l <lang>	Language hint (auto-detected from extension)
--format <fmt> / -f <fmt>	Output format: text, json, sarif, markdown, html, pdf, junit, codeclimate, github-actions
--output <path> / -o <path>	Write output to file
--fail-on-findings	Exit with code 1 if verdict is FAIL
--baseline <path> / -b <path>	JSON baseline file — suppress known findings
--summary	Print a single summary line (ideal for scripts)
--config <path>	Load a .judgesrc / .judgesrc.json config file
--preset <name>	Use a named preset (see Named Presets for all 22 options)
--min-score <n>	Exit with code 1 if overall score is below this threshold
--verbose	Print timing and debug information
--quiet	Suppress non-essential output
--no-color	Disable ANSI colors

judges init

Interactive wizard that generates project configuration:

• .judgesrc.json — rule customization, disabled judges, severity thresholds
• .github/workflows/judges.yml — GitHub Actions CI workflow
• .gitlab-ci.judges.yml — GitLab CI pipeline (optional)
• azure-pipelines.judges.yml — Azure Pipelines (optional)

judges fix

Preview or apply auto-fix patches from deterministic findings.

Flag	Description
positional	File to fix
--apply	Write patches to disk (default: dry run)
--judge <id>	Limit to a single judge's findings

judges watch

Continuously re-evaluate files on save.

Flag	Description
positional	File or directory to watch (default: .)
--judge <id>	Single judge mode
--fail-on-findings	Exit non-zero if any evaluation fails

judges report

Run a full project-level tribunal on a local directory.

Flag	Description
positional	Directory path (default: .)
--format <fmt>	Output format: text, json, html, markdown
--output <path>	Write report to file
--max-files <n>	Maximum files to analyze (default: 600)
--max-file-bytes <n>	Skip files larger than this (default: 300000)

judges hook

Manage a Git pre-commit hook that runs Judges on staged files.

judges hook install    # add pre-commit hook
judges hook uninstall  # remove pre-commit hook

Detects Husky (.husky/pre-commit) and falls back to .git/hooks/pre-commit. Uses marker-based injection so it won't clobber existing hooks.

judges diff

Evaluate only the changed lines from a unified diff (e.g., git diff output).

Flag	Description
--file <path>	Read diff from file instead of stdin
--format <fmt>	Output format: text, json, sarif, junit, codeclimate
--output <path>	Write output to file

git diff HEAD~1 | judges diff
judges diff --file changes.patch --format sarif

judges deps

Analyze project dependencies for supply-chain risks.

Flag	Description
--path <dir>	Project root to scan (default: .)
--format <fmt>	Output format: text, json

judges deps --path .
judges deps --path ./backend --format json

judges baseline

Create a baseline file to suppress known findings in future evaluations.

judges baseline create --file src/api.ts
judges baseline create --file src/api.ts -o .judges-baseline.json

judges ci-templates

Generate CI/CD configuration templates for popular providers.

judges ci-templates --provider github   # .github/workflows/judges.yml
judges ci-templates --provider gitlab   # .gitlab-ci.judges.yml
judges ci-templates --provider azure    # azure-pipelines.judges.yml
judges ci-templates --provider bitbucket # bitbucket-pipelines.yml (snippet)

judges docs

Generate per-judge rule documentation in Markdown.

Flag	Description
--judge <id>	Generate docs for a single judge
--output <dir>	Write individual .md files per judge

judges docs                          # all judges to stdout
judges docs --judge cybersecurity    # single judge
judges docs --output docs/judges/    # write files to directory

judges completions

Generate shell completion scripts.

eval "$(judges completions bash)"        # Bash
eval "$(judges completions zsh)"         # Zsh
judges completions fish | source         # Fish
judges completions powershell            # PowerShell (Register-ArgumentCompleter)

Named Presets

Use --preset to apply pre-configured evaluation settings:

Preset	Description
strict	All severities, all judges — maximum thoroughness
lenient	Only high and critical findings — fast and focused
security-only	Security-focused — disables non-security judges (cost, scalability, docs, a11y, i18n, UX, etc.)
startup	Skip compliance, sovereignty, i18n judges — move fast
compliance	Only compliance, data-sovereignty, authentication — regulatory focus
performance	Only performance, scalability, caching, cost-effectiveness
react	Tuned for React/Next.js apps — enables accessibility, XSS protection
express	Tuned for Express.js APIs — middleware security, auth, CORS, rate limiting
fastapi	Tuned for Python FastAPI — input validation, async patterns, API security
django	Tuned for Django apps — template security, ORM misuse, CSRF
spring-boot	Tuned for Java Spring Boot — injection, configuration, actuator security
rails	Tuned for Ruby on Rails — mass assignment, CSRF, SQL injection
nextjs	Tuned for Next.js — server/client security, API routes, SSR/ISR
terraform	Tuned for Terraform/OpenTofu IaC — infrastructure security, compliance
kubernetes	Tuned for K8s manifests — security contexts, RBAC, resource limits
onboarding	Smart defaults for first-time adoption — suppresses noisy rules
fintech	Financial services — PCI DSS, cryptography, authentication, audit
healthtech	Healthcare — HIPAA compliance, data sovereignty, encryption, audit trails
saas	Multi-tenant SaaS — tenant isolation, rate limiting, scalability
government	Government/public sector — compliance, sovereignty, authentication
open-source	Open-source projects — documentation, backwards compatibility, security, dependency health
ai-review	AI-generated code review — hallucination detection, security, authentication, correctness

judges eval --preset security-only src/api.ts
judges eval --preset strict --format sarif src/app.ts > results.sarif

CI Output Formats

JUnit XML

Generate JUnit XML for Jenkins, Azure DevOps, GitHub Actions, or GitLab test result viewers:

judges eval --format junit src/api.ts > results.xml

Each judge maps to a <testsuite>, each finding becomes a <testcase> with <failure> for critical/high severity.

CodeClimate / GitLab Code Quality

Generate CodeClimate JSON for GitLab Code Quality or similar tools:

judges eval --format codeclimate src/api.ts > codequality.json

Score Badges

Generate SVG or text badges for your README:

import { generateBadgeSvg, generateBadgeText } from "@kevinrabun/judges/badge";

const svg = generateBadgeSvg(85);          // shields.io-style SVG
const text = generateBadgeText(85);        // "✓ judges 85/100"
const svg2 = generateBadgeSvg(75, "quality"); // custom label

---

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 & Resource Efficiency	COST-	Algorithm efficiency, N+1 queries, memory waste, caching strategy
Scalability	Scalability & Performance	SCALE-	Statelessness, horizontal scaling, concurrency, bottlenecks
Cloud Readiness	Cloud-Native Architecture & DevOps	CLOUD-	12-Factor compliance, containerization, graceful shutdown, IaC
Software Practices	Software Engineering Best Practices & Secure SDLC	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	Monitoring & Diagnostics	OBS-	Structured logging, health checks, metrics, tracing
Performance	Runtime Performance	PERF-	N+1 queries, sync I/O, caching, memory leaks
Compliance	Regulatory & License Compliance	COMP-	GDPR/CCPA, PII protection, consent, data retention, audit trails
Data Sovereignty	Data, Technological & Operational Sovereignty	SOV-	Data residency, cross-border transfers, vendor key management, AI model portability, identity federation, circuit breakers, audit trails, data export
Testing	Test Quality & Coverage	TEST-	Test coverage, assertions, test isolation, naming
Documentation	Documentation & Developer Experience	DOC-	JSDoc/docstrings, magic numbers, TODOs, code comments
Internationalization	i18n & Localization	I18N-	Hardcoded strings, locale handling, currency formatting
Dependency Health	Supply Chain & Dependencies	DEPS-	Version pinning, deprecated packages, supply chain
Concurrency	Concurrency & Thread Safety	CONC-	Race conditions, unbounded parallelism, missing await
Ethics & Bias	AI/ML Fairness & Ethics	ETHICS-	Demographic logic, dark patterns, inclusive language
Maintainability	Code Maintainability & Technical Debt	MAINT-	Any types, magic numbers, deep nesting, dead code, file length
Error Handling	Error Handling & Fault Tolerance	ERR-	Empty catch blocks, missing error handlers, swallowed errors
Authentication	Authentication & Authorization	AUTH-	Hardcoded creds, missing auth middleware, token in query params
Database	Database Design & Query Efficiency	DB-	SQL injection, N+1 queries, connection pooling, transactions
Caching	Caching Strategy & Data Freshness	CACHE-	Unbounded caches, missing TTL, no HTTP cache headers
Configuration Management	Configuration & Secrets Management	CFG-	Hardcoded secrets, missing env vars, config validation
Backwards Compatibility	Backwards Compatibility & Versioning	COMPAT-	API versioning, breaking changes, response consistency
Portability	Platform Portability & Vendor Independence	PORTA-	OS-specific paths, vendor lock-in, hardcoded hosts
UX	User Experience & Interface Quality	UX-	Loading states, error messages, pagination, destructive actions
Logging Privacy	Logging Privacy & Data Redaction	LOGPRIV-	PII in logs, token logging, structured logging, redaction
Rate Limiting	Rate Limiting & Throttling	RATE-	Missing rate limits, unbounded queries, backoff strategy
CI/CD	CI/CD Pipeline & Deployment Safety	CICD-	Test infrastructure, lint config, Docker tags, build scripts
Code Structure	Structural Analysis	STRUCT-	Cyclomatic complexity, nesting depth, function length, dead code, type safety
Agent Instructions	Agent Instruction Markdown Quality & Safety	AGENT-	Instruction hierarchy, conflict detection, unsafe overrides, scope, validation, policy guidance
AI Code Safety	AI-Generated Code Quality & Security	AICS-	Prompt injection, insecure LLM output handling, debug defaults, missing validation, unsafe deserialization of AI responses
Framework Safety	Framework-Specific Security & Best Practices	FW-	React hooks ordering, Express middleware chains, Next.js SSR/SSG pitfalls, Angular/Vue lifecycle patterns, Django/Flask/FastAPI safety, Spring Boot security, ASP.NET Core auth & CORS, Go Gin/Echo/Fiber patterns
IaC Security	Infrastructure as Code	IAC-	Terraform, Bicep, ARM template misconfigurations, hardcoded secrets, missing encryption, overly permissive network/IAM rules
Security	General Security Posture	SEC-	Holistic security assessment — insecure data flows, weak cryptography, unsafe deserialization
Hallucination Detection	AI-Hallucinated API & Import Validation	HALLU-	Detects hallucinated APIs, fabricated imports, and non-existent modules from AI code generators
Intent Alignment	Code–Comment Alignment & Stub Detection	INTENT-	Detects mismatches between stated intent and implementation, placeholder stubs, TODO-only functions
API Contract Conformance	API Design & REST Best Practices	API-	API endpoint input validation, REST conformance, request/response contract consistency
Multi-Turn Coherence	Code Coherence & Consistency	COH-	Self-contradicting patterns, duplicate definitions, dead code, inconsistent naming
Model Fingerprint Detection	AI Code Provenance & Model Attribution	MFPR-	Detects stylistic fingerprints characteristic of specific AI code generators
Over-Engineering	Simplicity & Pragmatism	OVER-	Unnecessary abstractions, wrapper-mania, premature generalization, over-complex patterns
Logic Review	Semantic Correctness & Logic Integrity	LOGIC-	Inverted conditions, dead code, name-body mismatch, off-by-one, incomplete control flow
False-Positive Review	False Positive Detection & Finding Accuracy	FPR-	Meta-judge reviewing pattern-based findings for false positives: string literal context, comment/docstring matches, test scaffolding, IaC template gating

---

How It Works

The tribunal operates in three layers:

1. Pattern-Based Analysis — All tools (evaluate_code, evaluate_code_single_judge, evaluate_project, evaluate_diff) perform heuristic analysis using regex pattern matching to catch common anti-patterns. This layer is instant, deterministic, and runs entirely offline with zero external API calls.

2. AST-Based Structural Analysis — The Code Structure judge (STRUCT-* rules) uses real Abstract Syntax Tree parsing to measure cyclomatic complexity, nesting depth, function length, parameter count, dead code, and type safety with precision that regex cannot achieve. All supported languages — TypeScript, JavaScript, Python, Rust, Go, Java, C#, and C++ — are parsed via tree-sitter WASM grammars (real syntax trees compiled to WebAssembly, in-process, zero native dependencies). A scope-tracking structural parser is kept as a fallback when WASM grammars are unavailable. No external AST server required.

3. LLM-Powered Deep Analysis (Prompts) — The server exposes MCP prompts (e.g., judge-data-security, judge-cybersecurity) that provide each judge's expert persona as a system prompt. When used by an LLM-based client (Copilot, Claude, Cursor, etc.), the host LLM performs deeper, context-aware probabilistic analysis beyond what static patterns can detect. This is where the systemPrompt on each judge comes alive — Judges itself makes no LLM calls, but it provides the expert criteria so your AI assistant can act as 45 specialized reviewers.

---

Composable by Design

Judges Panel is a dual-layer review system: instant deterministic tools (offline, no API keys) for pattern and AST analysis, plus 45 expert-persona MCP prompts that unlock LLM-powered deep analysis when connected to an AI client. It does not try to be a CVE scanner or a linter. Those capabilities belong in dedicated MCP servers that an AI agent can orchestrate alongside Judges.

Built-in AST Analysis

Unlike earlier versions that recommended a separate AST MCP server, Judges Panel now includes real AST-based structural analysis out of the box:

• TypeScript, JavaScript, Python, Rust, Go, Java, C#, C++ — All parsed with a unified tree-sitter WASM engine for full syntax-tree analysis (functions, complexity, nesting, dead code, type safety). Falls back to a scope-tracking structural parser when WASM grammars are unavailable

The Code Structure judge (STRUCT-*) uses these parsers to accurately measure:

Rule	Metric	Threshold
STRUCT-001	Cyclomatic complexity	> 10 per function (high)
STRUCT-002	Nesting depth	> 4 levels (medium)
STRUCT-003	Function length	> 50 lines (medium)
STRUCT-004	Parameter count	> 5 parameters (medium)
STRUCT-005	Dead code	Unreachable statements (low)
STRUCT-006	Weak types	any, dynamic, Object, interface{}, unsafe (medium)
STRUCT-007	File complexity	> 40 total cyclomatic complexity (high)
STRUCT-008	Extreme complexity	> 20 per function (critical)
STRUCT-009	Extreme parameters	> 8 parameters (high)
STRUCT-010	Extreme function length	> 150 lines (high)

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     │  │  CVE / │  │ Linter │
  │   Panel      │  │  SBOM  │  │ Server │
  │ ─────────────│  └────────┘  └────────┘
  │ 44 Heuristic │   Vuln DB     Style &
  │   judges     │   scanning    correctness
  │ + AST judge  │
  └──────────────┘
   Patterns +
   structural
   analysis

Layer	What It Does	Example Servers
Judges Panel	45-judge quality gate — security patterns, AST analysis, cost, scalability, a11y, compliance, sovereignty, ethics, dependency health, agent instruction governance, AI code safety, framework safety	This server
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

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, plus analyze cyclomatic complexity, detect dead code, and flag deeply nested functions via AST
2. CVE Server → Check every dependency in package.json against known vulnerabilities
3. 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

evaluate_v2

Run a V2 context-aware tribunal evaluation designed to raise feedback quality toward lead engineer/architect-level review:

• Policy profile calibration (default, startup, regulated, healthcare, fintech, public-sector)
• Context ingestion (architecture notes, constraints, standards, known risks, data-boundary model)
• Runtime evidence hooks (tests, coverage, latency, error rate, vulnerability counts)
• Specialty feedback aggregation by judge/domain
• Confidence scoring and explicit uncertainty reporting

Supports:

• Code mode: code + language
• Project mode: files[]

Parameter	Type	Required	Description
code	string	conditional	Source code for single-file mode
language	string	conditional	Programming language for single-file mode
files	array	conditional	{ path, content, language }[] for project mode
context	string	no	High-level review context
includeAstFindings	boolean	no	Include AST/code-structure findings (default: true)
minConfidence	number	no	Minimum finding confidence to include (0-1, default: 0)
policyProfile	enum	no	default, startup, regulated, healthcare, fintech, public-sector
evaluationContext	object	no	Structured architecture/constraint context
evidence	object	no	Runtime/operational evidence for confidence calibration

evaluate_app_builder_flow

Run a 3-step app-builder workflow for technical and non-technical stakeholders:

1. Tribunal review (code/project/diff)
2. Plain-language translation of top risks
3. Prioritized remediation tasks with AI-fixable P0/P1 extraction

Supports:

• Code mode: code + language
• Project mode: files[]
• Diff mode: code + language + changedLines[]

Parameter	Type	Required	Description
code	string	conditional	Full source content (code/diff mode)
language	string	conditional	Programming language (code/diff mode)
files	array	conditional	{ path, content, language }[] for project mode
changedLines	number[]	no	1-based changed lines for diff mode
context	string	no	Optional business/technical context
maxFindings	number	no	Max translated top findings (default: 10)
maxTasks	number	no	Max generated tasks (default: 20)
includeAstFindings	boolean	no	Include AST/code-structure findings (default: true)
minConfidence	number	no	Minimum finding confidence to include (0-1, default: 0)

evaluate_public_repo_report

Clone a public repository URL, run the full judges panel across eligible source files, and generate a consolidated markdown report.

Parameter	Type	Required	Description
repoUrl	string	yes	Public repository URL (https://...)
branch	string	no	Optional branch name
outputPath	string	no	Optional path to write report markdown
maxFiles	number	no	Max files analyzed (default: 600)
maxFileBytes	number	no	Max file size in bytes (default: 300000)
maxFindingsInReport	number	no	Max detailed findings in output (default: 150)
credentialMode	string	no	Credential detection mode: standard (default) or strict
includeAstFindings	boolean	no	Include AST/code-structure findings (default: true)
minConfidence	number	no	Minimum finding confidence to include (0-1, default: 0)
enableMustFixGate	boolean	no	Enable must-fix gate summary for high-confidence dangerous findings (default: false)
mustFixMinConfidence	number	no	Confidence threshold for must-fix gate triggers (0-1, default: 0.85)
mustFixDangerousRulePrefixes	string[]	no	Optional dangerous rule prefixes for gate matching (e.g., AUTH, CYBER, DATA)
keepClone	boolean	no	Keep cloned repo on disk for inspection

Quick examples

Generate a report from CLI:

npm run report:public-repo -- --repoUrl https://github.com/microsoft/vscode --output reports/vscode-judges-report.md

# stricter credential-signal mode (optional)
npm run report:public-repo -- --repoUrl https://github.com/openclaw/openclaw --credentialMode strict --output reports/openclaw-judges-report-strict.md

# judge findings only (exclude AST/code-structure findings)
npm run report:public-repo -- --repoUrl https://github.com/openclaw/openclaw --includeAstFindings false --output reports/openclaw-judges-report-no-ast.md

# show only findings at 80%+ confidence
npm run report:public-repo -- --repoUrl https://github.com/openclaw/openclaw --minConfidence 0.8 --output reports/openclaw-judges-report-high-confidence.md

# include must-fix gate summary in the generated report
npm run report:public-repo -- --repoUrl https://github.com/openclaw/openclaw --enableMustFixGate true --mustFixMinConfidence 0.9 --mustFixDangerousPrefix AUTH --mustFixDangerousPrefix CYBER --output reports/openclaw-judges-report-mustfix.md

# opinionated quick-start mode (recommended first run)
npm run report:quickstart -- --repoUrl https://github.com/openclaw/openclaw --output reports/openclaw-quickstart.md

Call from MCP client:

{
  "tool": "evaluate_public_repo_report",
  "arguments": {
    "repoUrl": "https://github.com/microsoft/vscode",
    "branch": "main",
    "maxFiles": 400,
    "maxFindingsInReport": 120,
    "credentialMode": "strict",
    "includeAstFindings": false,
    "minConfidence": 0.8,
    "enableMustFixGate": true,
    "mustFixMinConfidence": 0.9,
    "mustFixDangerousRulePrefixes": ["AUTH", "CYBER", "DATA"],
    "outputPath": "reports/vscode-judges-report.md"
  }
}

Typical response summary includes:

• overall verdict and average score
• analyzed file count and total findings
• per-judge score table
• highest-risk findings and lowest-scoring files

Sample report snippet:

# Public Repository Full Judges Report

Generated from https://github.com/microsoft/vscode on 2026-02-21T12:00:00.000Z.

## Executive Summary
- Overall verdict: WARNING
- Average file score: 78/100
- Total findings: 412 (critical 3, high 29, medium 114, low 185, info 81)

get_judges

List all available judges with their domains and descriptions.

evaluate_code

Submit code to the full judges panel. all 45 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
includeAstFindings	boolean	no	Include AST/code-structure findings (default: true)
minConfidence	number	no	Minimum finding confidence to include (0-1, default: 0)
config	object	no	Inline configuration (see Configuration)

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 below
context	string	no	Additional context
minConfidence	number	no	Minimum finding confidence to include (0-1, default: 0)
config	object	no	Inline configuration (see Configuration)

evaluate_project

Submit multiple files for project-level analysis. all 45 judges evaluate each file, plus cross-file architectural analysis detects code duplication, inconsistent error handling, and dependency cycles.

Parameter	Type	Required	Description
files	array	yes	Array of { path, content, language } objects
context	string	no	Optional project context
includeAstFindings	boolean	no	Include AST/code-structure findings (default: true)
minConfidence	number	no	Minimum finding confidence to include (0-1, default: 0)
config	object	no	Inline configuration (see Configuration)

evaluate_diff

Evaluate only the changed lines in a code diff. Runs all 45 judges on the full file but filters findings to lines you specify. Ideal for PR reviews and incremental analysis.

Parameter	Type	Required	Description
code	string	yes	The full file content (post-change)
language	string	yes	Programming language
changedLines	number[]	yes	1-based line numbers that were changed
context	string	no	Optional context about the change
includeAstFindings	boolean	no	Include AST/code-structure findings (default: true)
minConfidence	number	no	Minimum finding confidence to include (0-1, default: 0)
config	object	no	Inline configuration (see Configuration)

analyze_dependencies

Analyze a dependency manifest file for supply-chain risks, version pinning issues, typosquatting indicators, and dependency hygiene. Supports package.json, requirements.txt, Cargo.toml, go.mod, pom.xml, and .csproj files.

Parameter	Type	Required	Description
manifest	string	yes	Contents of the dependency manifest file
manifestType	string	yes	File type: package.json, requirements.txt, etc.
context	string	no	Optional context

evaluate_git_diff

Evaluate only changed lines from a git diff. Provide either repoPath for a live git diff or diffText for a pre-computed unified diff.

Parameter	Type	Required	Description
repoPath	string	conditional	Absolute path to the git repository
base	string	no	Git ref to diff against (default: HEAD~1)
diffText	string	conditional	Pre-computed unified diff text
confidenceFilter	number	no	Minimum confidence threshold for findings (0–1)
autoTune	boolean	no	Apply feedback-driven auto-tuning (default: false)
maxPromptChars	number	no	Max character budget for LLM prompts (default: 100000, 0 = unlimited)
config	object	no	Inline configuration

re_evaluate_with_context

Re-run the tribunal with prior findings as context for iterative refinement. Supports dispute resolution, developer context injection, and focus-area filtering.

Parameter	Type	Required	Description
code	string	yes	Source code to re-evaluate
language	string	yes	Programming language
disputedRuleIds	string[]	no	Rule IDs the developer disputes as false positives
acceptedRuleIds	string[]	no	Rule IDs the developer accepts
developerContext	string	no	Free-form explanation of developer intent
focusAreas	string[]	no	Specific areas to focus on (e.g., ["security"])
confidenceFilter	number	no	Minimum confidence threshold (default: 0.5)
filePath	string	no	File path for context-aware evaluation
deepReview	boolean	no	Include LLM deep-review prompt section
relatedFiles	array	no	Cross-file context { path, snippet, relationship? }[]
maxPromptChars	number	no	Max character budget for LLM prompts (default: 100000, 0 = unlimited)

Additional MCP Tools

| Tool | Description | |-----