Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →bilal140202/adversarial-review
Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review".
Passed 11 of 19 test cases with the skill, and 5 of 19 without it.
and 12 more in the full report
12 fixed3 passed either way7 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Assume you are executing as Claude and need to spawn a read-only Codex reviewer for the Skeptic lens outputting to `/tmp/adversarial-review.123456/skeptic.md`. What command line flag is required to bypass git repository checks?
| Checked | Without skill | With skill |
|---|---|---|
| Includes the --skip-git-repo-check flag in the codex exec invocation. | Missed | Passed |
The instructions your model reads when the skill loads.
Spawn reviewers on the opposite model to challenge work. Reviewers attack from distinct lenses grounded in brain principles. 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.
Read references/reviewer-lenses.md. The three lenses (Skeptic, Architect, Minimalist) and
their mapped principles govern reviewer judgments. If a brain/principles.md file exists,
also read it and follow any [[wikilink]] references for additional principles.
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) |
Read references/reviewer-lenses.md for lens definitions.
Create a temp directory for reviewer output:
REVIEW_DIR=$(mktemp -d /tmp/adversarial-review.XXXXXX)
test cases passed, vs 5 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.