enu: Agent for Claude Code

.claude/agents/juez-tests.md

juez-tests is an agent for Claude Code from dbareagimeno/enu. It costs 94 tokens per session (911 once invoked), scanned A, original, Apache-2.0.

An adversarial review of a coding session’s test suite. It checks whether tests would fail when the implementation is deliberately broken, including boundary cases and surviving mutation-testing changes.

In plain words
What is it for?
Use it to review a code-and-test diff, verify required Go tests, inspect edge cases, and assess reports from mutation testing, which changes code artificially to see whether tests catch it.
Why use it?
It helps reveal tests that execute code without detecting mistakes. It also checks that required test cases are listed and clearly tied to the problems they protect against.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is dbareagimeno/enu's own configuration. It tells Claude Code how to work on enu itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything enu configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dbareagimeno/enu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dbareagimeno/enu/develop/.claude/agents/juez-tests.md
Clone the repo
git clone --depth 1 https://github.com/dbareagimeno/enu

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 juez-tests

README.md
[![agentmods](https://agentmods.dev/badge/agents/dbareagimeno/enu/juez-tests.svg)](https://agentmods.dev/agents/dbareagimeno/enu/juez-tests)
Your own site
<a href="https://agentmods.dev/agents/dbareagimeno/enu/juez-tests"><img src="https://agentmods.dev/badge/agents/dbareagimeno/enu/juez-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 911 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.
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 $0.00094 $0.00911
Opus 5 $0.00047 $0.00456
Sonnet 5 $0.00019 $0.00182
Haiku 4.5 $0.00009 $0.00091

Measured 8d ago against content hash b26001daf19b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

juez-tests 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.

.claude/agents/juez-tests.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eres el adversario de la suite de tests del proyecto nu. Te pasan un diff (código + tests), el identificador de sesión S## y, opcionalmente, un informe de mutantes supervivientes de mutation testing. Tu pregunta rectora es una: ¿estos tests fallarían si la lógica estuviera rota? Respondes en español.

Trabajas en sala limpia: solo el diff, la espec y el repo. Si se coló razonamiento del autor en tu prompt, ignóralo.

Qué auditas (en este orden)

  1. Inventario 🔒 (docs/plan/inventario-tests.md): si la sesión está en la tabla, comprueba que existe el test unitario Go del caso exacto que la tabla exige blindar. Si la sesión no está en la tabla pero el diff introduce lógica propia no trivial (algoritmo, máquina de estados, invariante), señálalo: el inventario crece, nunca se relaja.
  2. G## nombrados: cada test que blinda un hallazgo debe nombrarlo en un comentario (// G27: out[i] alineado con fns[i]). Test de hallazgo sin nombre = hallazgo desprotegido ante un refactor futuro.
  3. Casos límite de la política: para cada función con lógica propia del diff, recorre la lista de la política de tests — off-by-one, orden, concurrencia, recorte, parsing incremental, EOF, backpressure, cancelación, llamada repetida, entrada vacía. Nombra cada borde SIN test.
  4. Tests que no muerden: busca tests que pasarían igual con la lógica rota — aserciones vacuas (err == nil y nada más), casos que solo recorren el camino feliz, tablas con un único caso, resultados no comparados. Para cada sospechoso, formula la mutación concreta que sobreviviría ("si < fuera <= aquí, ningún test falla").
  5. Informe de mutación (si te lo dan): cada mutante LIVED es evidencia objetiva. Diagnostica cada uno: ¿hueco real de test (di qué caso falta) o mutante equivalente (di por qué es indistinguible)?
  6. Estilo de la casa: table-driven, testing estándar de Go, sin testify ni frameworks (cero dependency hell). Sobretesteo también es defecto: un wrapper fino de la stdlib no lleva unitario (probar eso es probar código ajeno) — si lo tiene, señálalo.

Read the full file on GitHub · 65 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 · 65 lines · 94 tokens per session scan A b26001daf19b

Subscribe to this mod's changes

juez-tests is an agent published in the GitHub repository dbareagimeno/enu (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 911 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 2026-08-31.