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.
curl -O https://raw.githubusercontent.com/dbareagimeno/enu/develop/.claude/skills/juicio/SKILL.mdgit clone --depth 1 https://github.com/dbareagimeno/enuWrote 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.
[](https://agentmods.dev/skills/dbareagimeno/enu/juicio)<a href="https://agentmods.dev/skills/dbareagimeno/enu/juicio"><img src="https://agentmods.dev/badge/skills/dbareagimeno/enu/juicio/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.
<a href="https://agentmods.dev/skills/dbareagimeno/enu/juicio"><img src="https://agentmods.dev/badge/skills/dbareagimeno/enu/juicio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00080 | $0.01157 |
| Opus 5.5 | $0.00032 | $0.00463 |
| Sonnet 5.5 | $0.00016 | $0.00231 |
| Haiku 4.5 | $0.00008 | $0.00116 |
Grade A, and why
juicio 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Juicio clean-room
Los jueces valen porque no comparten tus supuestos. Todo este protocolo
existe para que sigan sin compartirlos: arrancan sin contexto de esta
conversación, reciben solo artefactos públicos (diff + espec) y su garantía
técnica es el frontmatter tools: sin Bash/Edit/Write (sin git log, sin
mensajes de commit, sin el razonamiento histórico del autor). No relajes
ninguna de las dos cosas.
Regla de secuencia
El juicio se ejecuta antes de escribir el worklog de la sesión y mover el
puntero ▶: el worklog contiene la racionalización del autor y, si existiera
ya, contaminaría a cualquier juez que lea implementacion.md.
Política de coste (cuándo montar qué)
| El diff... | Panel |
|---|---|
Es de una sesión 🔒, o toca docs/contracts/api.md/contratos, o toca scheduler/cancelación/eventos/workers |
Completo: juez-espec + juez-tests + juez-concurrencia (en paralelo) |
| Implementa lógica propia fuera de lo anterior | juez-espec + juez-tests |
| Es un wrapper fino sobre stdlib/librería | Solo juez-espec |
| Es glue de paso, docs o render visual | Ninguno (basta el DoD normal) |
Esta tabla es para no saltarse el juicio "porque es caro" justo cuando
importa. Para el panel completo puedes delegar la orquestación en el workflow
guardado revision-limpia (.claude/workflows/revision-limpia.js), que
implementa exactamente este protocolo de forma determinista.
Plantilla del prompt de juez (literal — prohibido desviarse)
Construye el prompt de CADA juez exactamente así, sin añadir nada más:
Sesión: S## — <enunciado de la sesión copiado verbatim del plan, o "cambio
fuera de plan: <una frase factual de QUÉ cambia, no por qué>">
Espec que gobierna este diff: <doc> §N, <doc> §M <(+ G## que la sesión cita)>
Diff a juzgar (verbatim):
<salida de `git diff` (o `git diff --staged`) completa, sin recortar>
Emite tu veredicto con tu formato de salida.
Prohibido incluir: el razonamiento del autor, "decidimos X porque...", alternativas discutidas, fragmentos de esta conversación, resultados de otros jueces, o el contenido del worklog. Si el orquestador puede improvisar el prompt, filtrará su propia justificación sin querer — por eso la plantilla es literal.
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.
- 2mo ago First seen · 86 lines · 80 tokens per session scan A 68b9e4d79b15
juicio is a skill published in the GitHub repository dbareagimeno/enu (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,157 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
review-harness
Use when reviewing implementation work that ran through a /tmp Pi task harness. Checks contract drift, unsafe shortcuts, validation evidence, and status honesty.
code-review
Review changed code for correctness bugs — logic errors, nil/error handling, concurrency, resource leaks, edge cases, broken invariants. Reports findings first, ordered by severity, then fixes on request. Scoped to correctness, not quality or style cleanups. Use when the user says "code review", "review my changes"…
refactor
Restructure existing code without changing its behavior — extract, rename, inline, split, deduplicate, reshape — with tests holding behavior fixed before and after. Scoped to structure only: no new features, no bug fixes, no behavior changes. Use when the user says "refactor", "clean up the structure", "extract this"…
simplify
Review changed code for reuse, quality, and efficiency, then clean up what you find — duplicated logic that could reuse an existing helper, hacky or redundant patterns, needless work on hot paths. Quality cleanup only: not bugs (that's code-review) and not behavior-preserving restructuring on request (that's…
omd-review
A structured review of code changes that looks for correctness, security, missing requirements, and edge cases. It can review everything changed in the current branch or a selected part of the codebase.