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/plugins/closedloop-ai/claude-plugins/judges)<a href="https://agentmods.dev/plugins/closedloop-ai/claude-plugins/judges"><img src="https://agentmods.dev/badge/plugins/closedloop-ai/claude-plugins/judges.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
judges 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- platform — 86% identical, 6 lines differ
What it actually says
{
"name": "judges",
"description": "LLM Judges plugin",
"version": "1.7.1",
"author": {
"name": "ClosedLoop",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 3 skills, 22 agents travel with it, and installing the plugin installs all of them — 724 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill artifact-type-tailored-context A 47 tokens
- Skill eval-cache A 82 tokens
- Skill run-judges C 99 tokens
- Agent goal-alignment-judge A 24 tokens
- Agent solid-liskov-substitution-judge A 27 tokens
- Agent custom-best-practices-judge A 18 tokens
- Agent dry-judge A 17 tokens
- Agent feature-completeness-judge A 17 tokens
- Agent readability-judge A 20 tokens
- Agent solid-isp-dip-judge A 33 tokens
- Agent solid-open-closed-judge A 23 tokens
- Agent ssot-judge A 19 tokens
- Agent test-judge A 19 tokens
- Agent verbosity-judge A 16 tokens
- Agent code-organization-judge A 16 tokens
- Agent kiss-judge A 17 tokens
- Agent prd-auditor A 12 tokens
- Agent technical-accuracy-judge A 25 tokens
- Agent context-manager-for-judges A 30 tokens
- Agent prd-dependency-judge A 15 tokens
- Agent prd-testability-judge A 17 tokens
- Agent prd-scope-judge A 16 tokens
- Agent brownfield-accuracy-judge A 38 tokens
- Agent codebase-grounding-judge A 42 tokens
- Agent convention-adherence-judge A 35 tokens
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 · 10 lines scan A 514b4c211dc8
judges is a plugin published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
agent-skills
Skills for the parts of shipping that code review never covers: the loading states, the type scale, and whether half the diff is AI slop.
vision-powers
Analyze Claude Code plugins and visualize text artifacts (markdown docs, git diffs, plugins) as interactive HTML or diagram-enhanced markdown reports. On a capable account, HTML reports publish as claude.ai Artifacts by default (doc-visual, diff-visual, plugin-visual, context-health-visual); add --local for a local…
claw-mux
cmux terminal integration: terminal I/O, topology control, browser automation, markdown viewer, notifications.
skill-creator-pro
Create, test, and iteratively improve Claude Code skills with the official lean coaching loop, an eval harness for benchmarking with variance analysis, and automated description-trigger optimization.
foundry
Governed, spec-driven delivery for agent-built software: spec → operator authorization → governed build → an honestly-tiered merge floor → certification against the running app → human sign-off.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.