AGENT SKILL

adversarial-review

Adversarial code review using cross-model approach. Spawns reviewers on the opposing model (Claude uses Codex, Codex uses Claude) to challenge work from distinct critical lenses. Produces a synthesized verdict with findings and lead judgment. Triggers: "adversarial review".

License 许可
MIT
最近更新
2026-11-04
Stars
★ 0
Forks
0

01 前言 Front Matter

name
adversarial-review
metadata
{ "source_path": ".agents/skills/adversarial-review/SKILL.md", "source_commit": "82d2921c52370f23f29086de81ccfb600939c037", "source_repository": "poteto/noodle", "upstream_frontmatter": { "schedule": "After cook sessions that produce large diffs (200+ lines), implement plan phases, or complete a planning session" } }
description
Adversarial code review using cross-model approach. Spawns reviewers on the opposing model (Claude uses Codex, Codex uses Claude) to challenge work from distinct critical lenses. Produces a synthesized verdict with findings and lead judgment. Triggers: "adversarial review".

02 资源文件 299

03 SKILL.md 正文

On Windows, if claude is not yet on the running process PATH, use ~/.local/bin/claude.exe. Complete account sign-in before attempting an opposite-model review.

Codex packaging

Resolve brain/ and references/ from this skill directory. The opposite-model review requires an authenticated Claude CLI. Translate shell and task-monitoring examples to the host tools; keep reviewers read-only.

Adversarial Review

All 16 required principles and the available transitive context are bundled in brain/. Track visited wiki links to avoid cycles. Historical links absent from the pinned source are listed in references/upstream-missing-links.md; report missing relevant context instead of inventing it.

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.

Step 1 — Load Principles

Read brain/principles.md. Follow every [[wikilink]] and read each linked principle file. These govern reviewer judgments.

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)

Read references/reviewer-lenses.md for lens definitions.

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 with run_in_background: true, monitor via TaskOutput with block: true, timeout: 600000.

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

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

Run with run_in_background: true.

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

Build each reviewer's prompt using the template in references/reviewer-prompt.md.

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 using the format in references/verdict-format.md.

Step 5 — Render Judgment

After synthesizing the reviewers, apply your own judgment. Using the stated intent and brain principles 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 the Lead Judgment section to the verdict (see references/verdict-format.md).

04 同仓库更多 Skills