poteto/noodle

adversarial-review

Adversarial code review using cross-model approach.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/poteto/noodle --skill adversarial-review

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Adversarial Review

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:

SizeThresholdReviewers
Small< 50 lines, 1-2 files1 (Skeptic)
Medium50-200 lines, 3-5 files2 (Skeptic + Architect)
Large200+ lines or 5+ files3 (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:

sh
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:

sh
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:

sh
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:

sh
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).

同じリポジトリから

関連する Skills

すべての Skills
poteto
コミュニティ

debugging

Systematic root-cause debugging methodology. Use for any technical problem — errors, failures, unexpected behavior, or when stuck. Triggers: "debug", "fix this", "what's wrong", "investigate".

1時間の導入数
1
GitHub Stars
646
更新日
3月19日
poteto
コミュニティ

reflect

Reflect on the conversation and update the brain. Use when wrapping up, after mistakes or corrections, or when significant codebase knowledge was gained. Triggers: "reflect", "remember this".

1時間の導入数
1
GitHub Stars
646
更新日
3月19日
poteto
コミュニティ

unslop

Remove AI writing patterns from prose. Use for docs, READMEs, blog posts, any non-code text that should sound human. Triggers: "unslop", "humanize", "make this sound human", "clean up this writing", "edit for voice", "de-AI this text".

1時間の導入数
1
GitHub Stars
646
更新日
3月19日
poteto
コミュニティ

brain

Read/write brain files (Obsidian vault at brain/). Use for any task that persists knowledge — reflection, planning, or direct edits. Triggers after debugging sessions, mistakes, corrections, architectural decisions, or any insight worth preserving across sessions. Use on 'add to brain', 'remember this', 'write a note', or brain/ modifications.

1時間の導入数
1
GitHub Stars
613
更新日
3月19日