output-eval-judge-prompt

output-eval-judge-prompt is a skill for Claude Code from growthxai/output. It costs 42 tokens per session (2,951 once invoked), scanned A, original, Apache-2.0.

A guide for writing prompts for an AI judge that evaluates workflow outputs. An AI judge is a language model asked to check one specific quality or failure condition.

In plain words
What is it for?
Use it when creating or fixing prompts for verdict, score, or label evaluators after completing error analysis and gathering labeled examples.
Why use it?
It helps make judge results more reliable by requiring a clearly defined failure, enough labeled examples, and a focused evaluation criterion.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Run [`output-dev-model-selection`](../output-dev-model-selection/SKILL.md) to resolve each tier below to a current model ID..

Part of the outputai plugin — 50 skills, 5 agents, 1 hook shipped together

Good fit Use it when creating or fixing prompts for verdict, score, or label evaluators after completing error analysis and gathering labeled examples.

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/growthxai/output
agentmods
npx agentmods add skills/growthxai/output/output-eval-judge-prompt

Made for: Claude Code.

Or install outputai, the plugin that ships this one along with the rest of its 50 skills, 5 agents, 1 hook.

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 output-eval-judge-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/growthxai/output/output-eval-judge-prompt/github.svg)](https://agentmods.dev/skills/growthxai/output/output-eval-judge-prompt)
Your own site
<a href="https://agentmods.dev/skills/growthxai/output/output-eval-judge-prompt"><img src="https://agentmods.dev/badge/skills/growthxai/output/output-eval-judge-prompt/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 output-eval-judge-prompt

Your own site · 80×15
<a href="https://agentmods.dev/skills/growthxai/output/output-eval-judge-prompt"><img src="https://agentmods.dev/badge/skills/growthxai/output/output-eval-judge-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,951 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 pass 7 Sept 2026
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 $0.00042 $0.02951
Opus 5 $0.00021 $0.01476
Sonnet 5 $0.00008 $0.00590
Haiku 4.5 $0.00004 $0.00295

Measured 8d ago against content hash bf5873a33889, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

output-eval-judge-prompt 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 8d 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.

coding_assistants/claude/plugins/outputai/skills/output-eval-judge-prompt/SKILL.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Designing LLM Judge Prompts

Overview

An LLM judge evaluates workflow output for a single, specific failure mode identified during error analysis. This skill covers how to design the .prompt file that powers judgeVerdict(), judgeScore(), or judgeLabel() calls. For the file format basics, see output-dev-prompt-file. For error analysis, see output-eval-error-analysis.

Prerequisites

Before writing a judge prompt:

  1. Error analysis is complete — You have identified the specific failure mode this judge targets (from output-eval-error-analysis)
  2. 20+ labeled examples — At least 20 pass and 20 fail traces for this failure mode, with ground_truth labels in dataset YAML files
  3. Code-based check ruled out — Confirmed that Verdict.* helpers (contains, matches, gte, etc.) cannot reliably detect this failure

The Four Components

Every effective judge prompt has exactly four components.

1. Task and Criterion

State the single failure mode being evaluated. Be specific and observable.

Good criteria (specific, observable):

  • "Does the blog post maintain a formal tone throughout, or does it slip into casual language?"
  • "Does the output contain any URLs that are fabricated rather than drawn from the input?"
  • "Does the summary faithfully represent the source material without adding claims not present in the original?"

Bad criteria (vague, holistic):

  • "Is this output high quality?"
  • "Rate the overall effectiveness of this response"
  • "How good is this content?"

2. Pass/Fail Definitions

Define exactly what constitutes pass and fail. Always binary — no Likert scales, no 1-5 ratings, no "partially meets criteria."

PASS: The blog post uses formal language throughout. Professional vocabulary,
complete sentences, no slang, no contractions, no first-person casual asides.

FAIL: The blog post contains one or more instances of casual language: slang,
contractions ("don't", "can't"), informal asides ("pretty cool", "super important"),
or conversational filler ("honestly", "basically").

Read the full file on GitHub · 340 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. 8d ago Changed bf5873a33889
  2. 13d ago First seen · 340 lines · 42 tokens per session scan A a242e05ac18c

Subscribe to this mod's changes

output-eval-judge-prompt is a skill published in the GitHub repository growthxai/output (435 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 2,951 once invoked, about $0.0002 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

ax-ai

This skill helps an LLM generate correct AI provider setup and configuration code using @ax-llm/ax. Use when the user asks about ai(), providers, models, routing, adaptive balancing, presets, embeddings, batch audio with ai.transcribe() or ai.speak(), extended thinking, context caching, or mentions…

ax-llm/ax · 100 tokens

ax-agent-rlm

This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions…

ax-llm/ax · 88 tokens

ax-flow

This skill helps an LLM generate correct AxFlow workflow code using @ax-llm/ax. Use when the user asks about flow(), AxFlow, workflow orchestration, parallel execution, DAG workflows, conditional routing, map/reduce patterns, or multi-node AI pipelines.

ax-llm/ax · 59 tokens

ax-gen

This skill helps an LLM generate correct AxGen code using @ax-llm/ax. Use when the user asks about ax(), AxGen, generators, forward(), streamingForward(), validation, assertions, streaming assertions, field processors, step hooks, self-tuning, or structured outputs. For MCP clients, transports, prompts, resources…

ax-llm/ax · 86 tokens

ax-cpp-ai

Use when writing C++ code with axllm for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.

ax-llm/ax · 47 tokens

ax-signature

This skill helps an LLM generate correct DSPy signature code using @ax-llm/ax. Use when the user asks about signatures, s(), f(), field types, string syntax, fluent builder API, validation constraints, or type-safe inputs/outputs.

ax-llm/ax · 57 tokens