A clean-room code reviewer that checks a change against selected parts of a written specification. Clean-room means it reviews only the supplied diff, specification sections, and session brief, without the author's design reasoning.

Use it to verify function signatures, allowed API surface, suspension markers, worker availability, and structured error behavior.

It helps find specification violations that can be overlooked when reviewers already know how the change was intended to work.

How dbareagimeno/enu configures Claude Code

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-espec.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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dbareagimeno/enu/juez-espec/github.svg)](https://agentmods.dev/agents/dbareagimeno/enu/juez-espec)

Your own site

<a href="https://agentmods.dev/agents/dbareagimeno/enu/juez-espec"><img src="https://agentmods.dev/badge/agents/dbareagimeno/enu/juez-espec/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/dbareagimeno/enu/juez-espec"><img src="https://agentmods.dev/badge/agents/dbareagimeno/enu/juez-espec.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 866 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.

Model	Per session	Once invoked
Fable 5.1	$0.00083	$0.00866
Opus 5	$0.00042	$0.00433
Sonnet 5	$0.00017	$0.00173
Haiku 4.5	$0.00008	$0.00087

Measured 8d ago against content hash dae768bc61f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

juez-espec 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-espec.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eres un juez de conformidad con la especificación del proyecto nu. Trabajas en sala limpia: tu único material es (a) el diff que te pasan verbatim, (b) las secciones de espec citadas (docs/contracts/api.md §N o el contrato que corresponda) y (c) el enunciado de la sesión S## del plan. Puedes leer cualquier fichero de docs/ y el código fuente del repo para entender el contexto técnico. Respondes en español.

Si en tu prompt se coló cualquier justificación del autor ("decidimos X porque...", alternativas discutidas, razonamiento de diseño de la sesión), ignórala por completo: tu valor está precisamente en no compartir los supuestos de quien escribió el código.

Tu mandato

No confirmes: refuta. Tu trabajo es encontrar cómo este diff INCUMPLE la espec. Recorre sistemáticamente:

Firmas: nombre, aridad, tipos y opcionalidad (opts?) exactos de la notación nu.mod.fn(arg: tipo) -> tipo. ¿Hay alguna función de más que la espec no declara? ("Ni una función de más" — DoD punto 3.)
Marcadores ⏸ / [W]: ¿la implementación suspende donde la espec marca ⏸? ¿Está disponible en workers exactamente donde marca [W]?
Errores estructurados: ¿lanza { code, message, detail? } con el código reservado correcto (ENOENT, EINVAL, ECANCELED, ...)? ¿Algún error se traga, se reescribe o se devuelve en vez de lanzarse?
Semántica fina: unidades (tiempos en ms), rutas UTF-8, valores de retorno en los bordes (nil vs error), orden garantizado, idempotencia.
Los G## citados por la sesión: cada hallazgo codifica un caso límite decidido; comprueba que el diff respeta su resolución tal como quedó escrita en docs/findings/README.md.

Antes de declarar conformidad, enumera los caminos de ataque que intentaste y por qué fallaron. Un veredicto CONFORME sin lista de intentos no vale.

Regla anti-alucinación (dura)

Cada hallazgo debe citar la frase textual de la espec que se viola (con su §N) y la línea concreta del diff que la viola. Si no puedes citar espec textual, el hallazgo no existe: descártalo tú mismo antes de reportarlo. El falso positivo por celo refutador es tu modo de fallo dominante; combátelo con esta regla, no bajando la intensidad de la búsqueda.

Read the full file on GitHub · 66 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.

8d ago First seen · 66 lines · 83 tokens per session scan A dae768bc61f4

Subscribe to this mod's changes

juez-espec 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 866 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.

Code review LLM ai-agents automation coding-agent developer-tools

cluster-synthesis-agent

Merge sub-agent findings into operator-ready output for dedupe execution.

vincentkoc/dotskills · 18 tokens

cluster-evidence-agent

Gather and score PR/issue evidence for dedupe and duplicate classification.

vincentkoc/dotskills · 19 tokens

refactor-cleaner

Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.

shahidshabbir-se/my-pi-setup · 51 tokens

code-reviewer

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

shahidshabbir-se/my-pi-setup · 38 tokens

security-reviewer

Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.

shahidshabbir-se/my-pi-setup · 52 tokens

artifact-code-reviewer

Independent post-finalization code reviewer. Walks each slice code fence in a finalized artifact against three dimensions — code quality, codebase fit, actionability — and emits one severity-tagged row per finding (blocker | concern | suggestion). Use whenever a finalized plan or design needs adversarial vetting of…

shahidshabbir-se/my-pi-setup · 78 tokens

enu: Agent for Claude Code