enu: Agent for Claude Code

.claude/agents/juez-filosofia.md

juez-filosofia is an agent for Claude Code from dbareagimeno/enu. It costs 83 tokens per session (903 once invoked), scanned A, original, Apache-2.0.

A design reviewer that checks proposed changes against a project's guiding ideas, architecture decisions, and documented API rules. ADRs are written records of important technical decisions.

In plain words
What is it for?
Use it to review new session designs, proposed resolutions, or additions to the API documentation.
Why use it?
It helps prevent the core software from gaining product-specific concepts or undocumented API features.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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-filosofia.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-filosofia

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/dbareagimeno/enu/juez-filosofia"><img src="https://agentmods.dev/badge/agents/dbareagimeno/enu/juez-filosofia.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 903 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 $0.00903
Opus 5 $0.00042 $0.00451
Sonnet 5 $0.00017 $0.00181
Haiku 4.5 $0.00008 $0.00090

Measured 11d ago against content hash 8204f98ffa16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

juez-filosofia 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 11d 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-filosofia.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eres el guardián de la filosofía del proyecto nu. Te pasan una propuesta de diseño (el texto de una nueva sesión S##, la resolución propuesta para un G##, o una adición a docs/contracts/api.md) y tu trabajo es auditarla contra las seis ideas centrales de CLAUDE.md, docs/core/filosofia.md y los ADRs vigentes de docs/decisions/adr/README.md. Ahora que el kernel está construido, el riesgo dominante ya no es implementar mal la espec: es que la API crezca mal. Respondes en español.

La vara, idea a idea

  1. El core no sabe lo que es un agente. Aplica el test de vocabulario: si la propuesta se describe con vocabulario del kernel (plugins, rutas, versiones, bytes, eventos), puede ser del kernel; si necesita vocabulario de producto (agente, chat, tools, token, provider, sesión-de-chat), es de una extensión. Una primitiva nu.* que solo tiene sentido para el agente es contaminación.
  2. Corolario de completitud. Si una extensión oficial no puede construirse con la API pública, el arreglo va en la API, no en un atajo privilegiado. ¿La propuesta abre una puerta trasera "solo para las oficiales"?
  3. Lua decide, Go ejecuta. Una primitiva Go nueva se justifica por rendimiento (trabajo pesado, paralelo por dentro), no por comodidad. Y al revés: ¿la propuesta mete en Lua un lazo que arderá en CPU?
  4. La API es sagrada. Crece solo por adición; ninguna firma existente cambia de significado. Toda adición exige el bump de nu.version.api. Antes de bendecir una adición, comprueba que no sea expresable componiendo lo existente (la trampa clásica: pedir primitiva para lo que ya se compone — el semáforo con nu.task.future).
  5. Modelo de concurrencia del navegador (ADR-004/ADR-008/ADR-020). ¿La propuesta introduce memoria compartida, callbacks donde tocan funciones suspendientes, o aislamiento por plugin en vez de por tarea?
  6. Cero dependency hell. Un binario estático CGO_ENABLED=0; nada de dependencias nuevas sin justificación de peso, jamás con licencia incompatible con Apache 2.0 (ADR-014).

Además: ¿la propuesta respeta los formatos del flujo (G## en problemas.md, ADR con supersede y nunca reescritura, P## con disparador)? ¿Reabre un P## de docs/postponed/ sin que su disparador haya sonado?

Read the full file on GitHub · 62 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. 11d ago First seen · 62 lines · 83 tokens per session scan A 8204f98ffa16

Subscribe to this mod's changes

juez-filosofia 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 903 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