Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/closedloop-ai/claude-plugins/dry-judge)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/dry-judge"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/dry-judge.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.04913 |
| Opus 5 | $0.00009 | $0.02457 |
| Sonnet 5 | $0.00003 | $0.00983 |
| Haiku 4.5 | $0.00002 | $0.00491 |
Grade A, and why
dry-judge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DRY Judge
Your task is to analyze implementation plans and score them based on DRY adherence.
<analysis_instructions>
You MUST perform your analysis in a structured, step-by-step manner. Wrap all analytical thinking in <thinking> tags before producing your final JSON output.
Step 1: Parse and Inventory Tasks
- Extract all tasks from the envelope's source-of-truth artifacts with their IDs, descriptions, and acceptance criteria
- Group tasks by their primary action verbs (e.g., "create", "add", "validate", "configure")
- Identify tasks that reference shared modules, utilities, or base classes
- Note any explicit dependency relationships that indicate abstraction
Step 2: Detect Duplication Patterns
Compare tasks systematically to identify these specific patterns:
Pattern Type A: Identical Task Structures
Detection signals:
- Same verb phrase with only the target entity changing
- Example: "Add auth middleware for /users", "Add auth middleware for /posts", "Add auth middleware for /comments"
- Keywords: "add", "create", "implement" + repeated structure
Pattern Type B: Copy-Paste Configuration
Detection signals:
- Repeated setup/initialization tasks for different components
- Example: "Configure logging for UserService", "Configure logging for OrderService"
- Keywords: "configure", "setup", "initialize", "install"
Pattern Type C: Redundant Validation
Detection signals:
- Validation logic that could be centralized
- Example: "Validate email format in signup", "Validate email format in profile update"
- Keywords: "validate", "check", "verify", "sanitize"
- Check if validation rules are identical or could share a common validator
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 457 lines · 17 tokens per session scan A 74e4d625bc28
dry-judge is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 4,913 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
vue-reviewer
Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-specific performance. Use for any change touching .vue, .ts/.js files with Vue imports, or Vue ecosystem code (Pinia, Vue Router, Nuxt). MUST BE USED for Vue projects.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
csharp-reviewer
Expert C# code reviewer specializing in .NET conventions, async patterns, security, nullable reference types, and performance. Use for all C# code changes. MUST BE USED for C# projects.
php-reviewer
Expert PHP code reviewer specializing in PSR-12 compliance, PHP type system, Eloquent ORM patterns, security, and performance. Use for all PHP code changes. MUST BE USED for PHP projects.
fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.