Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From codex-advisor
Executes Codex adversarial review to skeptically challenge code changes for security and correctness issues, followed by Claude's verification of findings against actual code. Use on 'adversarial review' requests.
npx claudepluginhub leejuoh/claude-code-zero --plugin codex-advisorHow this skill is triggered — by the user, by Claude, or both
Slash command
/codex-advisor:codex-adversarialThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Invoke the Official Codex companion's adversarial review, then apply Claude's critical evaluation. Adversarial review defaults to skepticism — it looks for reasons NOT to ship.
Runs official Codex code review on code changes, diffs, branches, or commits, then double-checks each finding by reading source code and classifying agree/disagree/nuance.
Reviews code changes adversarially using parallel layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with triage into actionable categories. Invoke on 'run code review' or 'review this code'.
Performs adversarial verification with three agents (finder, adversary, judge) to identify and validate issues in security-sensitive code, data integrity, financial logic, and breaking changes.
Share bugs, ideas, or general feedback.
Invoke the Official Codex companion's adversarial review, then apply Claude's critical evaluation. Adversarial review defaults to skepticism — it looks for reasons NOT to ship.
CODEX_COMPANION=$("${CLAUDE_PLUGIN_ROOT}/scripts/resolve-companion.sh")
If resolve fails: direct to /codex-setup immediately. Do NOT fall back to a Claude-only solo review.
Use the $CODEX_COMPANION resolved in Step 1:
node "$CODEX_COMPANION" adversarial-review --wait $ARGUMENTS
Timeout: 300000ms (5 minutes).
| Error | Action |
|---|---|
| "not authenticated" in stderr | Auth required → suggest codex login |
| Other error | Show raw error, don't retry silently |
Read ${CLAUDE_PLUGIN_ROOT}/references/evaluation.md.
Adversarial findings are intentionally skeptical. For each finding:
Be especially rigorous here. Adversarial review produces more false positives by design.
Present to user:
mkdir -p "${CLAUDE_PLUGIN_DATA}/reviews"
Save to ${CLAUDE_PLUGIN_DATA}/reviews/adversarial-<YYYYMMDD-HHMMSS>.md.