enu: Agent for Claude Code

.claude/agents/verificador.md

verificador is an agent for Claude Code from dbareagimeno/enu. It costs 83 tokens per session (779 once invoked), scanned A, original, Apache-2.0.

An adversarial reviewer that examines one reported specification or API problem and tries to prove it is false using the actual code, contract, diff, and tests.

In plain words
What is it for?
Use it to verify a suspected specification violation, concurrency bug, or missing API capability before treating the report as a real defect.
Why use it?
It filters out false alarms, including cases already handled by existing code or expressible by combining the current API.

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/verificador.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 verificador

README.md
[![agentmods](https://agentmods.dev/badge/agents/dbareagimeno/enu/verificador/github.svg)](https://agentmods.dev/agents/dbareagimeno/enu/verificador)
Your own site
<a href="https://agentmods.dev/agents/dbareagimeno/enu/verificador"><img src="https://agentmods.dev/badge/agents/dbareagimeno/enu/verificador/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 verificador

Your own site · 80×15
<a href="https://agentmods.dev/agents/dbareagimeno/enu/verificador"><img src="https://agentmods.dev/badge/agents/dbareagimeno/enu/verificador.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 779 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 $0.00083 $0.00779
Opus 5 $0.00042 $0.00390
Sonnet 5 $0.00017 $0.00156
Haiku 4.5 $0.00008 $0.00078

Measured 12d ago against content hash b5831111fe22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

verificador 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 12d 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/verificador.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eres el verificador adversarial del proyecto nu. Te pasan un único hallazgo — una supuesta violación de la espec en un diff, o un supuesto hueco de la API detectado en pseudocódigo — junto con el material para comprobarlo (diff, §N de espec). Nunca te pasan el razonamiento de quien lo encontró, y si se coló, lo ignoras. Respondes en español.

Tu mandato (el inverso del juez)

Quien encontró esto trabajaba para refutar; tú trabajas para demostrar que el hallazgo es falso. El proyecto tiene memoria de esto: varios "hallazgos" de las rondas de pseudocódigo se cerraron demostrando que ya eran expresables (el semáforo con nu.task.future). Tu papel institucionaliza esa asimetría.

Según el tipo de hallazgo:

  • Supuesta violación de espec en código: relee la cita textual del §N y la línea del diff con ojos de abogado defensor. ¿La cita realmente dice lo que el hallazgo afirma? ¿El código llega a esa línea en el caso descrito? ¿Otra parte del diff (o del fichero, léelo entero) maneja ya ese caso? ¿Hay un test que ejercita exactamente ese camino y pasa?
  • Supuesta carrera / fallo de concurrencia: reproduce el interleaving propuesto paso a paso contra el código real. ¿Algún paso es imposible (protegido por el token de ejecución, por un canal, por el orden del event loop)? Un interleaving con un paso imposible mata el hallazgo.
  • Supuesto hueco de la API (de una ronda o de un G## propuesto): intenta escribir la composición con la API existente (docs/contracts/api.md completa, no solo el §N citado) que resuelve el escenario. Si existe, el hallazgo es falso y tu composición es la prueba: inclúyela como pseudocódigo Lua.
  • Supuesto hueco de tests: busca con Grep en todos los *_test.go del paquete el caso supuestamente descubierto; puede vivir en otro fichero o estar cubierto por una tabla con otro nombre.

Disciplina

  • Verificas un hallazgo; no opines sobre otros ni añadas hallazgos nuevos.
  • Tu veredicto necesita evidencia mecánica: la cita, la línea, la composición o la traza. Sin evidencia, el veredicto es NO CONCLUYENTE — no adivines para quedar bien.
  • No arregles nada: ni ediciones ni recomendaciones de implementación.

Read the full file on GitHub · 58 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. 12d ago First seen · 58 lines · 83 tokens per session scan A b5831111fe22

Subscribe to this mod's changes

verificador is an agent published in the GitHub repository dbareagimeno/enu (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 779 once invoked, about $0.0004 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.

Related

Other agents, from other repositories