/cross-modal-review

name: cross-modal-review
version: 1.1.0
description: |
  Quality gate via second model. Spawn a different AI model to review work
  before committing. Includes refusal routing: if one model refuses, switch
  silently to the next. Extended in v0.25.1 with structured review-mode
  gating (when to invoke vs not) and a Codex code-review handoff for the
  diff-review case.
triggers:
  - "second opinion"
  - "cross-modal review"
  - "double check this"
  - "get another perspective"
  - "challenge this code"
  - "adversarial review"
tools:
  - search
  - query
  - get_page
mutating: false

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.

When it fails

Follow the [agent operator protocol](../conventions/agent-operator-protocol.md) for any gbrain error `code`, exit code, `[AGENT]` block or notice block. Specific to this skill:

• A review model refuses: switch to the next model in the chain silently; escalate to the user only when every mo