Skip this step entirely if a reviewer agent was already named — by the user, or in the instruction that launched you (e.g. from polygraph session review --adversarial); in that case use that agent and do not ask. Otherwise, pick the agent: Ask which should review—claude, codex, or opencode for spawn_agent's agent parameter. If the user names a model, pass it via spawn_agent's optional model parameter; don't ask about models.
Get the session description.
Get each repo's plan.
Delegate one reviewer per repo in parallel, role: "reviewer". Ask to review, identify issues. Do the delegation even for the "initiator" repo.
Summarize and attach. Consolidate reviews into one consolidated Markdown review with per-repo sections and present it to the user. Then call upload_artifact once with sessionId, that review as content, kind: "review", format: "markdown", name adversarial-review-YYYY-MM-DDTHH-mm-ssZ.md. If the upload fails, report that separately without suppressing the review.
Ask what next. Address feedback or continue. Skip if the user already said.
If the user selects "address the feedback", pass each repo's feedback to the repo default agent (not the reviewer). The initiator should fix things itself without delegating.
1---2name: adversarial-review3description: Adversarial Review4---56# Adversarial Review781. Skip this step entirely if a reviewer agent was already named — by the user, or in the instruction that launched you (e.g. from `polygraph session review --adversarial`); in that case use that agent and do not ask. Otherwise, **pick the agent**: Ask which should review—`claude`, `codex`, or `opencode` for `spawn_agent`'s `agent` parameter. If the user names a model, pass it via `spawn_agent`'s optional `model` parameter; don't ask about models.92. **Get the session description.**103. **Get each repo's plan.**114. **Delegate one reviewer per repo** in parallel, `role: "reviewer"`. Ask to review, identify issues. Do the delegation even for the "initiator" repo.125. **Summarize and attach.** Consolidate reviews into one consolidated Markdown review with per-repo sections and present it to the user. Then call `upload_artifact` once with `sessionId`, that review as `content`, `kind: "review"`, `format: "markdown"`, name `adversarial-review-YYYY-MM-DDTHH-mm-ssZ.md`. If the upload fails, report that separately without suppressing the review.136. **Ask what next.** Address feedback or continue. Skip if the user already said.147. If the user selects "address the feedback", pass each repo's feedback to the repo default agent (not the reviewer). The initiator should fix things itself without delegating.
Run npx skillmds@latest add nrwl/adversarial-review in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Adversarial Review It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
nrwl (@nrwl) published this skill. Their other Agent Skills are listed on their SkillMD profile.
nrwl