// 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".
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it feel better", "feels off", stagger animations, border radius, optical alignment, font smoothing, tabular numbers, image outlines, box shadows.
Systematic planning for medium-to-large tasks. Gathers context, identifies domain skills, writes phased plans to brain/plans/. Does NOT implement. Use for new features, multi-file refactors, or architectural changes — not small fixes. Triggers: "plan this", "break this down".
Structural code search via ast-grep — use when code shape and element relationships matter, not just text. E.g., "find async functions without error handling", "refactor foo(a, b) to foo({ a, b })". Use Grep for simple name lookups.
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.
Run Codex CLI (exec, resume) for parallel work, delegating tasks to another model, or background code generation. Handles code analysis, refactoring, and automated editing. Includes Spark vs standard guidance. Triggers: "codex", "run codex", "use codex to".
Create conventional commit messages. Use when the user says "commit this", "save changes", "git commit", asks to commit code, write a commit message, or format git history. Follows conventional commits specification.
| name | adversarial-review |
| 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". |
| schedule | After cook sessions that produce large diffs (200+ lines), implement plan phases, or complete a planning session |
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 brain/principles.md. Follow every [[wikilink]] and read each linked principle file.
These govern reviewer judgments.
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=$(mktemp -d /tmp/adversarial-review.XXXXXX)
Determine which model you are, then spawn reviewers on the opposite:
If you are Claude — spawn Codex reviewers via codex exec:
codex exec --skip-git-repo-check -o "$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" > "$REVIEW_DIR/skeptic.md" 2>/dev/null
Run with run_in_background: true.
Name each output file after the lens: skeptic.md, architect.md, minimalist.md.
Build each reviewer's prompt using the template in references/reviewer-prompt.md.
Before reading reviewer output, log which CLI was used and confirm the output files exist:
echo "reviewer_cli=codex|claude"
ls "$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.
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).