adversarial-review

name	adversarial-review
description	Use when the user asks for an adversarial review, opposing-model review, hostile review, red-team review, or extra critical review of a plan, branch, implementation, or large diff.
schedule	After cook sessions that produce large diffs (200+ lines), implement plan phases, or complete a planning session

Adversarial Review

Spawn reviewers on the opposite model to challenge work. Reviewers attack from distinct lenses grounded in the bundled review lens definitions. The deliverable is a synthesized verdict; do not make changes.

Hard constraint: Reviewers MUST run via the opposite model's CLI (codex exec or claude -p). Do NOT use subagents, the Agent tool, or any internal delegation mechanism as reviewers — those run on your own model, which defeats the purpose.

Step 1 — Load Review Lenses

Read references/reviewer-lenses.md. These bundled lens definitions govern reviewer judgments and are the only required local reference material for this skill.

Step 2 — Determine Scope and Intent

Identify what to review from context (recent diffs, referenced plans, user message).

Determine the intent — what the author is trying to achieve. This is critical: reviewers challenge whether the work achieves the intent well, not whether the intent is correct. State the intent explicitly before proceeding.

Assess change size:

Size	Threshold	Reviewers
Small	< 50 lines, 1–2 files	1 (Skeptic)
Medium	50–200 lines, 3–5 files	2 (Skeptic + Architect)
Large	200+ lines or 5+ files	3 (Skeptic + Architect + Minimalist)

Step 3 — Detect Model and Spawn Reviewers

Create a temp directory for reviewer output:

REVIEW_DIR=$(mktemp -d /tmp/adversarial-review.XXXXXX)

Determine which model you are, then spawn reviewers on the opposite:

If you are Claude → spawn Codex reviewers via codex exec:

codex exec --skip-git-repo-check -o "$REVIEW_DIR/skeptic.md" "prompt" 2>/dev/null

Use --profile edit only if the reviewer needs to run tests. Default to read-only. Run reviewer commands concurrently with your environment's available shell background mechanism and wait for every output file before synthesis.

If you are Codex → spawn Claude reviewers via claude CLI:

claude -p "prompt" > "$REVIEW_DIR/skeptic.md" 2>/dev/null

Run reviewer commands concurrently with your environment's available shell background mechanism and wait for every output file before synthesis.

Name each output file after the lens: skeptic.md, architect.md, minimalist.md.

Reviewer prompt template

Each reviewer gets a single prompt containing:

1. The stated intent (from Step 2)
2. Their assigned lens (full text from references/reviewer-lenses.md)
3. The code or diff to review
4. Instructions: "You are an adversarial reviewer. Your job is to find real problems, not validate the work. Be specific — cite files, lines, and concrete failure scenarios. Rate each finding: high (blocks ship), medium (should fix), low (worth noting). Write findings as a numbered markdown list to your output file."

Spawn all reviewers in parallel.

Step 4 — Verify and Synthesize Verdict

Before reading reviewer output, log which CLI was used and confirm the output files exist:

echo "reviewer_cli=codex|claude"
ls "$REVIEW_DIR"/*.md

If any output file is missing or empty, note the failure in the verdict — do not silently skip a reviewer.

Read each reviewer's output file from $REVIEW_DIR/. Deduplicate overlapping findings. Produce a single verdict:

## Intent
<what the author is trying to achieve>

## Verdict: PASS | CONTESTED | REJECT
<one-line summary>

## Findings
<numbered list, ordered by severity (high → medium → low)>

For each finding:

- **[severity]** Description with file:line references
- Lens: which reviewer raised it
- Lens principle: which bundled review lens principle it maps to
- Recommendation: concrete action, not vague advice

## What Went Well
<1–3 things the reviewers found no issue with — acknowledge good work>

Verdict logic:

• PASS — no high-severity findings
• CONTESTED — high-severity findings but reviewers disagree on them
• REJECT — high-severity findings with reviewer consensus

Step 5 — Render Judgment

After synthesizing the reviewers, apply your own judgment. Using the stated intent and bundled review lenses as your frame, state which findings you would accept and which you would reject and why. Reviewers are adversarial by design; not every finding warrants action. Call out false positives, overreach, and findings that mistake style for substance.

Append to the verdict:

## Lead Judgment
<for each finding: accept or reject with a one-line rationale>