# Cross Modal Review

> Control de calidad mediante un segundo modelo: hace que otro modelo revise el trabajo antes de darlo por bueno, con enrutamiento de negativas y opción de derivar a Codex para revisión de diffs.

Fuente: https://skillsagentes.com/skills/garrytan/gbrain/cross-modal-review
Markdown: https://skillsagentes.com/skills/garrytan/gbrain/cross-modal-review.md

Repositorio: https://github.com/garrytan/gbrain
Autor: garrytan
Licencia: MIT
Actualizado: hace 3 meses
Coste de contexto: 76 tok instalada, 1.7k tok al activarse, 1.7k tok con todos los archivos del bundle
Bundle: 1 archivo, 7 KB
Permisos que pide: search, query, get_page

## Instalación

Un skill son archivos markdown: los mismos archivos valen para cualquier agente y lo único que cambia es el directorio de destino, es decir la bandera `--agent`. Añade `-g` para instalarlo en todos los proyectos de la máquina.

```bash
# Claude Code
npx -y skills add garrytan/gbrain --skill cross-modal-review --agent claude-code
# Cursor
npx -y skills add garrytan/gbrain --skill cross-modal-review --agent cursor
# Codex
npx -y skills add garrytan/gbrain --skill cross-modal-review --agent codex
# Gemini CLI
npx -y skills add garrytan/gbrain --skill cross-modal-review --agent gemini
# Windsurf
npx -y skills add garrytan/gbrain --skill cross-modal-review --agent windsurf
# Cline
npx -y skills add garrytan/gbrain --skill cross-modal-review --agent cline
```

## Qué hace

- Envía el trabajo a un modelo distinto para revisarlo antes de darlo por definitivo
- Compara el resultado contra el Contract de la skill original, no contra impresiones
- Si el modelo se niega, cambia en silencio al siguiente de la cadena definida en cross-modal.yaml
- Reporta acuerdos y desacuerdos, pero nunca aplica sugerencias del revisor sin aprobación
- Reconoce cuándo recomendar `/codex review` para revisión de diffs independiente

## Cuándo usarla

- Commits significativos: 5+ archivos o 100+ líneas, refactors, cambios de API
- Cambios sensibles a seguridad: auth, límites de confianza de brain-write, webhooks
- Cuando hay estancamiento: 2+ iteraciones sin progreso en el mismo problema
- Antes de operaciones masivas (bulk enrichment, migraciones, escrituras en lote) o al crear/modificar skills

## Cuándo no

- Escrituras simples de memoria o actualizaciones de brain-page
- Corrección de typos en un solo archivo
- Git commit/push de trabajo que ya fue revisado

## Qué la activa

- "Dame una segunda opinión sobre este código"
- "Haz una revisión cross-modal de este diff"
- "Revisa esto de forma adversarial antes de mergear"
- "Dobla la revisión de este refactor con otro modelo"

## Antes de instalar

- Requiere acceso a un modelo AI distinto para la revisión y, para el modo de código, la skill /codex de gstack.

## Archivos

- SKILL.md — 7 KB

## SKILL.md

Reproducido tal cual desde garrytan/gbrain bajo MIT. Esta sección es el documento original y está en inglés.

# Cross-Modal Review

> **Convention:** see [conventions/cross-modal.yaml](../conventions/cross-modal.yaml)
> for the review pairs and refusal routing chain.

> **Relationship to `gbrain eval cross-modal`:** This skill is the manual
> mid-flow gate (one model reviews work product before commit, with refusal
> routing). The `gbrain eval cross-modal` command (v0.27.x) is a sibling
> surface: 3 different-provider frontier models score-and-iterate on a
> documented dimension list *before* tests cement behavior. Use this skill
> for ad-hoc second opinions; use `gbrain eval cross-modal` for the
> skillify Phase 3 quality gate. The two are complementary, not redundant.

## Contract

This skill guarantees:

- Work product is reviewed by a different model before finalizing.
- The review is graded against the originating skill's Contract section
  (what was promised), not vibes.
- Agreement and disagreement are reported transparently.
- Refusal from one model triggers a silent switch to the next in chain.
- The user always makes the final decision (user sovereignty).

## When to invoke (v0.25.1 gating)

Invoke this skill when:

- **Significant code changes** — any commit touching 5+ files or 100+
  lines. Architecture decisions, refactors, API changes.
- **Security-sensitive changes** — auth flows, brain-write trust boundaries,
  webhook transforms, cross-skill data passing.
- **Stuck or churning** — 2+ iterations on the same problem without
  progress.
- **Pre-bulk-operation** — before running batch enrichment, migrations,
  or bulk writes (see [conventions/test-before-bulk.md](../conventions/test-before-bulk.md)).
- **Skill creation / modification** — new or rewritten skills that
  affect operational behavior.
- **Brain-page quality concerns** — when brain writes need validation
  against the originating skill's Contract.

Do NOT invoke for:

- Simple memory writes or brain-page updates
- Single-file typo fixes
- Routine cron output or heartbeat operations
- Git commit / push of already-reviewed work

## Phases

1. **Capture the work product.** The brain page, analysis, code diff,
   or decision to be reviewed.
2. **Load the Contract.** Read the originating skill's Contract section
   (what was promised).
3. **Spawn review model.** Send the work + Contract to a different
   model. Use [conventions/model-routing.md](../conventions/model-routing.md)
   for model selection.
4. **Grade.** Model evaluates: did the output follow the Contract?
   Pass / fail with specific citations.
5. **Report.** Present agreement / disagreement to the user. Never
   auto-apply the reviewer's suggestions.

## Code-review handoff (v0.25.1 extension)

For diff review specifically, gstack ships a `/codex` skill that wraps
the OpenAI Codex CLI. Two modes:

### Codex Review

Independent diff review from a different AI system. The user invokes
`/codex review` (gstack-shipped); cross-modal-review's job is to
RECOGNIZE when this is the right tool and recommend it explicitly.

**When to recommend `/codex review`:**
- After a substantive diff lands and before merge
- When the user wants a second opinion that's NOT another Claude

**Output framing (when cross-modal-review surfaces Codex output):**

```
CODEX REVIEW (independent second opinion):
══════════════════════════════════════════
<full codex output, verbatim>
══════════════════════════════════════════

CROSS-MODEL ANALYSIS:
  Both found:    [overlapping findings]
  Only Codex:    [findings unique to Codex]
  Only Claude:   [findings unique to my analysis]
  Agreement:     X% (N/M findings overlap)
```

User decides what to act on. Cross-model agreement is signal, not
permission.

### Adversarial Challenge

Same shape, different prompt. Used on security-sensitive changes:
the reviewer is asked to find injection vectors, race conditions,
auth bypasses, data leaks, privilege escalation paths.

Output adds an exploitability rating (CRITICAL / HIGH / MEDIUM / LOW)
and recommended mitigations.

## Refusal routing

If the primary review model refuses:

1. Switch silently to the next model in the chain (see
   `conventions/cross-modal.yaml`).
2. Don't show the refusal to the user.
3. Don't announce the switch.
4. If ALL models in the chain refuse, escalate to the user.

## Output format

### Standard review

```
Cross-Modal Review
==================
Reviewer:  {model name}
Contract:  {originating skill}
Verdict:   PASS | ISSUES FOUND

Findings:
- {finding with evidence}

Agreement with primary: {X}%
```

### Code review

```
Cross-Modal Review (code)
==========================
Mode:           Codex Review | Adversarial Challenge
Files changed:  N
Lines changed:  +N / -N

{mode-specific output above}
```

## User-sovereignty rule (Iron Law)

Reviewer findings are INFORMATIONAL until the user explicitly approves
each one. Do NOT incorporate reviewer recommendations into the work
product without presenting each finding and getting explicit approval.
This applies even when the reviewer is correct. Cross-model consensus
is a strong signal — present it as such — but the user makes the
decision.

## Anti-Patterns

- ❌ Auto-applying reviewer suggestions without user approval
- ❌ Showing model refusals to the user
- ❌ Using the same model for review and generation
- ❌ Skipping the Contract reference (reviewing vibes, not guarantees)
- ❌ Code-reviewing trivial changes (typos, formatting)
- ❌ Running code review without git-diff context

## Related skills

- gstack `/codex` — the actual Codex CLI wrapper this skill hands off
  to for diff-review mode. Cross-modal-review knows WHEN to invoke;
  /codex knows HOW.
- `skills/testing/SKILL.md` — runs the project test suite; complementary
  signal for "is this commit safe to land"
- `skills/conventions/cross-modal.yaml` — review pairs + refusal routing

## Output Format

The skill's output shape is documented inline in the body sections above (see "Output", "Brain page format", or equivalent). The literal section header here exists for the conformance test (`test/skills-conformance.test.ts`).

## Dónde encaja

- Categoría: [Testing y QA](https://skillsagentes.com/categorias/testing-qa.md) — Flujos de testing unitario, de integración y end-to-end.
- Creador: [garrytan](https://skillsagentes.com/creators/garrytan.md) — 134 skills en el directorio
- [Todas las skills](https://skillsagentes.com/skills.md)
- [Ranking de instalaciones](https://skillsagentes.com/ranking.md)

## Otras skills del mismo repositorio

- [Setup](https://skillsagentes.com/skills/garrytan/gbrain/setup.md): Configura GBrain con auto-aprovisionamiento de Supabase o PGLite, inyección en AGENTS.md y primera importación.
- [Maintain](https://skillsagentes.com/skills/garrytan/gbrain/maintain.md): Chequeos de salud del brain: aplicación de back-links, auditoría de citas, validación de filing, detección de info obsoleta, páginas huérfanas y benchmarks.
- [Schema Unify](https://skillsagentes.com/skills/garrytan/gbrain/schema-unify.md): Migra un brain de gbrain-base a la taxonomía de 14 tipos canónicos de gbrain-base-v2 usando gbrain onboard --check y el handler Minion unify-types.
- [Retrieval Reflex](https://skillsagentes.com/skills/garrytan/gbrain/retrieval-reflex.md): Cuándo y qué recuperar: abre la página del brain de una entidad relevante antes de responder desde memoria.
- [Minion Orchestrator](https://skillsagentes.com/skills/garrytan/gbrain/minion-orchestrator.md): Skill unificado de Minions para jobs deterministas de shell y orquestación de subagentes LLM: cola durable, observable y controlable, más la doctrina de ejecución durable para operaciones largas.

---

Skills Agentes · [Índice de páginas en markdown](https://skillsagentes.com/sitemap.md) · [Inicio](https://skillsagentes.com/index.md)