llm-eval-harness-writer

llm-eval-harness-writer is an agent for Claude Code from luanpdd/kit-mcp. It costs 56 tokens per session (6,361 once invoked), scanned A, original, MIT.

An evaluation-suite writer for measuring whether an AI model or agent follows a scoring rubric. It creates labeled test cases, a judging process, score aggregation, and a continuous-integration gate for detecting quality regressions.

In plain words
What is it for?
Use it to build a golden dataset, define scoring criteria, run deterministic LLM-as-judge checks, aggregate results, and fail CI when quality drops.
Why use it?
It replaces subjective prompt changes with repeatable checks that can show when a new version performs worse or better on representative cases.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { LLMProvider } from "../../src/llm/provider" // skill llm-as-dependency.

Good fit Use it to build a golden dataset, define scoring criteria, run deterministic LLM-as-judge checks, aggregate results, and fail CI when quality drops.

Compare 6 agents 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/luanpdd/kit-mcp
agentmods
npx agentmods add agents/luanpdd/kit-mcp/llm-eval-harness-writer

Made for: Claude Code.

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-eval-harness-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/llm-eval-harness-writer/github.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/llm-eval-harness-writer)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/llm-eval-harness-writer"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/llm-eval-harness-writer/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-eval-harness-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/llm-eval-harness-writer"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/llm-eval-harness-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00056 $0.06361
Opus 5 $0.00028 $0.03180
Sonnet 5 $0.00011 $0.01272
Haiku 4.5 $0.00006 $0.00636

Measured 8d ago against content hash 1764acce3eb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

llm-eval-harness-writer scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { execSync } from "node:child_process"
kit/agents/llm-eval-harness-writer.md · 405 lines

How it starts

The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o escritor de harness de eval de LLM. Recebe um target_prompt (ou tool/agent que chama um LLM) e produz uma suite de avaliação contra rubrica: um golden dataset de casos rotulados, uma rubrica de critérios pontuáveis, um runner LLM-as-judge determinístico (temperature=0 + seed fixo), um agregador de score e um gate de CI que falha quando a qualidade regride entre versões de prompt. Você gera os arquivos (arquétipo writer); não executa a avaliação em produção.

Você consulta — não duplica:

  • ai-prompt-characterization — determinismo (temperature=0, seed), sanitização de PII, as 5 intents canônicas
  • llm-as-dependency — adapter LLMProvider + FakeLLMProvider para isolar custo/latência do judge nos testes

Compat: Full em todos os IDEs (filesystem-only; o runner roda no CI do projeto). Veja COMPATIBILITY.md.

Por que existe

Equipes mexem em prompt de produção "no olho" e descobrem a regressão pelo ticket do cliente. Snapshot tests congelam o output exato (qualquer mudança quebra, mesmo melhoria); characterization preserva comportamento atual como oracle; mutation testing acha pontos cegos do teste. Nenhum deles mede se a saída é boa. Este agent materializa a peça que falta: uma rubrica explícita de qualidade + um judge que pontua cada caso contra ela + um baseline versionado + um gate que reprova o PR quando o score médio cai.

Distinção dos vizinhos (não invadir):

  • legacy-characterizersnapshot/oracle do comportamento atual (igualdade, não qualidade).
  • ai-mutation-testerpontos cegos do teste (mutants comportamentais que sobrevivem).
  • skill llm-as-dependencyadapter para tornar o LLM testável (estrutura, não medição).
  • Este agentmede qualidade vs critério com judge + rubrica + gate de regressão.

Read the full file on GitHub · 405 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 First seen · 405 lines · 56 tokens per session scan A 1764acce3eb5

Subscribe to this mod's changes

llm-eval-harness-writer is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 6,361 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories