llm-judge

llm-judge is a skill for Claude Code from existential-birds/beagle. It costs 104 tokens per session (2,716 once invoked), scanned A, original, Apache-2.0.

A structured evaluator that compares two or more code repositories against a requirements document. It gathers facts, scores each solution, and ranks the results.

In plain words
What is it for?
Use it to compare competing implementations, pull requests, or vendor submissions, with optional labels, scoring weights, and branch comparisons.
Why use it?
It helps replace an informal code comparison with a repeatable review based on the same requirements and scoring rules.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is 3. Load the **llm-artifacts-detection** skill ([../../../beagle-core/skills/llm-artifacts-detection/SKILL.md](../../../beagle-core/skills/llm-artifacts-detectio.

Part of the beagle-analysis plugin — 14 skills shipped together

Good fit Use it to compare competing implementations, pull requests, or vendor submissions, with optional labels, scoring weights, and branch comparisons.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/existential-birds/beagle
agentmods
npx agentmods add skills/existential-birds/beagle/llm-judge

Made for: Claude Code.

Or install beagle-analysis, the plugin that ships this one along with the rest of its 14 skills.

Wrote 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.

agentmods badge for llm-judge

README.md
[![agentmods](https://agentmods.dev/badge/skills/existential-birds/beagle/llm-judge/github.svg)](https://agentmods.dev/skills/existential-birds/beagle/llm-judge)
Your own site
<a href="https://agentmods.dev/skills/existential-birds/beagle/llm-judge"><img src="https://agentmods.dev/badge/skills/existential-birds/beagle/llm-judge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for llm-judge

Your own site · 80×15
<a href="https://agentmods.dev/skills/existential-birds/beagle/llm-judge"><img src="https://agentmods.dev/badge/skills/existential-birds/beagle/llm-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,716 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 114
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 241
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.02716
Opus 5 $0.00052 $0.01358
Sonnet 5 $0.00021 $0.00543
Haiku 4.5 $0.00010 $0.00272

Measured 9d ago against content hash 70fce06f9fae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llm-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 9d ago.

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.

plugins/beagle-analysis/skills/llm-judge/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Judge

Compare code implementations across multiple repositories using structured evaluation.

Usage

llm-judge <spec> <repo1> <repo2> [repo3...] [--labels=...] [--weights=...] [--branch=...]

Arguments

Argument Required Description
spec Yes Path to spec/requirements document
repos Yes 2+ paths to repositories to compare
--labels No Comma-separated labels (default: directory names)
--weights No Override weights, e.g. functionality:40,security:30
--branch No Branch to compare against main (default: main)

Workflow

  1. Parse $ARGUMENTS into spec_path, repo_paths, labels, weights, and branch.
  2. Validate the spec file, each repo path, and the minimum repo count.
  3. Read the spec document into memory.
  4. Load this skill and the supporting reference files.
  5. Gather facts per repository (one Phase 1 unit per repo) — facts only, no scoring.
  6. Validate the repo-agent JSON results before proceeding.
  7. Score each dimension (one Phase 2 unit per dimension).
  8. Aggregate scores, compute weighted totals, rank repos, and write the report.
  9. Display the markdown summary and verify the JSON report.

Hard gates

Sequenced workflow: do not start the next phase until the current gate passes. Each pass condition must be checkable (file on disk, non-empty content, or json.load succeeds)—not “I reviewed internally.”

Gate Pass condition Unblocks
A — Inputs spec_path is a readable file and non-empty; len(repo_paths) ≥ 2; each path contains .git. Phase 1 repo agents
B — Phase 1 facts For each repo agent output: stdin/stdout parses as JSON; required keys/shape match references/fact-schema.md. Phase 2 judge agents
C — Phase 2 scores Five judge outputs (one per dimension) each parse as JSON; each includes a score (and justification) for every repo label. Aggregation
D — Report file .beagle/llm-judge-report.json exists; python3 -c "import json; json.load(open('.beagle/llm-judge-report.json'))" exits 0. Markdown summary to the user
E — Consistency Summary table and verdict use the same labels, weights, and per-dimension scores as the JSON report. Mark task complete

Read the full file on GitHub · 294 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 9d ago First seen · 294 lines · 104 tokens per session scan A 70fce06f9fae

Subscribe to this mod's changes

llm-judge is a skill published in the GitHub repository existential-birds/beagle (80 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 2,716 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories