adversarial-review
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 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.
Step 2 — Determine Scope and Intent
Identify what to review from context (recent diffs, referenced plans, user message).
More from mizoreww/awesome-claude-code-config
paper-reading
Use when user asks to read, summarize, or analyze a research paper (PDF or text). Triggers on keywords like "read paper", "summarize paper", "paper summary", "literature review", "analyze this paper
34humanizer
|
8update-config
Update awesome-claude-code-config to the latest version. Checks remote for new releases, then re-runs the installer with the interactive selector. Use when user types /update-config or asks to update their Claude Code configuration.
6humanizer-zh
|
5update_config
Update awesome-claude-code-config to the latest version. Checks remote for new releases, then re-runs the installer with the interactive selector. Use when user types /update-config or asks to update their Claude Code configuration.
4