judge

judge is a skill for Claude Code, Codex from sattyamjjain/proofloop. It costs 22 tokens per session (4,292 once invoked), scanned A, original, MIT.

A skill that reviews how well another skill or agent performed. It scores seven areas, such as correctness and completeness, and can run automatically after an execution or manually with a command.

In plain words
What is it for?
Evaluating agent runs, producing scorecards, comparing results over time, and reviewing a selected skill on demand.
Why use it?
It provides a consistent way to find errors, missing requirements, and areas for improvement instead of judging the result informally.

Skill for Claude CodeCodex

Part of the proofloop plugin — 1 skill, 6 commands, 1 agent, 3 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/sattyamjjain/proofloop/judge
Any agent
npx skills add sattyamjjain/proofloop --skill judge
Clone the repo
git clone --depth 1 https://github.com/sattyamjjain/proofloop

Made for: Claude Code, Codex.

Or install proofloop, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 1 agent, 3 hooks.

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 judge

README.md
[![agentmods](https://agentmods.dev/badge/skills/sattyamjjain/proofloop/judge.svg)](https://agentmods.dev/skills/sattyamjjain/proofloop/judge)
Your own site
<a href="https://agentmods.dev/skills/sattyamjjain/proofloop/judge"><img src="https://agentmods.dev/badge/skills/sattyamjjain/proofloop/judge.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.04292
Opus 5 $0.00011 $0.02146
Sonnet 5 $0.00004 $0.00858
Haiku 4.5 $0.00002 $0.00429

Measured 4d ago against content hash 5478cb7821a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d ago.

The scan reads SKILL.md. This mod also ships 18 executable files (adapters/__init__.py, adapters/claude_code.py, adapters/codex.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/judge/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proofloop — Universal Quality Evaluator

Overview

Proofloop is a universal quality evaluator for Claude Code skills and agents. It measures execution quality across 7 weighted dimensions, producing an evidence-based scorecard with letter grades, justifications, and actionable recommendations.

Proofloop operates in two modes:

  • Auto Mode: Hooks into skill/agent lifecycle events (e.g. Stop) and automatically evaluates every execution. No user intervention required. Scores are persisted to skills/judge/scores/ for trend analysis.
  • Manual Mode: Triggered explicitly via the /judge command. The user specifies a skill name and optionally a transcript path. Useful for on-demand evaluation, re-scoring, or benchmarking.

Both modes produce the same structured scorecard output.


Scoring Dimensions

Proofloop evaluates across 7 dimensions. Each dimension receives a score from 1.0 to 10.0. The weighted composite determines the final grade.

# Dimension Weight What It Measures
1 Correctness 25% Output is factually correct. Code compiles and runs. No logical errors or bugs.
2 Completeness 20% All requirements from the prompt/task are addressed. Nothing is missing or skipped.
3 Adherence 15% The skill/agent followed its own SKILL.md or agent definition instructions precisely.
4 Actionability 15% Output is immediately usable without further manual work, fixes, or interpretation.
5 Efficiency 10% Minimal token waste. Appropriate tool usage. No unnecessary steps or redundant calls.
6 Safety 10% No harmful outputs. No data leaks. No destructive or irreversible actions taken without confirmation.
7 Consistency 5% Quality matches or exceeds previous executions of the same skill/agent.

Read the full file on GitHub · 382 lines

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. 4d ago First seen · 382 lines · 22 tokens per session scan A 5478cb7821a5

Subscribe to this mod's changes

judge is a skill published in the GitHub repository sattyamjjain/proofloop (5 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 4,292 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 2026-08-31.