Skip to content
Agentmart
Submit a tool

adversarial-code-review

Adversarially review a diff/PR against its requirements, in any language — hunts for code that isn't justified by any acceptance criterion (dead code…

Skill by jonzenor

IndexedLicense unknown
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jonzenor-adversarial-code-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Adversarially review a diff/PR against its requirements, in any language — hunts for code that isn't justified by any acceptance criterion (dead code, speculative generality, scope creep) AND for acceptance criteria the diff doesn't actually satisfy (untraced edge cases, API misuse, lifecycle bugs). Produces a findings report only; does not fix anything. Use when the user wants an adversarial/hard-pass code review, wants to check code against a PRD/issue's acceptance criteria, or when /auto-process-prd runs its code-review step (alongside or instead of CodeRabbit, per the project's ai/PIPELINE.md).

Use cases: documents, backend, data

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/adversarial-code-review

What's inside

Skill name
adversarial-code-review
Description
Adversarially review a diff/PR against its requirements, in any language — hunts for code that isn't justified by any acceptance criterion (dead code, speculative generality, scope creep) AND for acceptance criteria the diff doesn't actually satisfy (untraced edge cases, API misuse, lifecycle bugs). Produces a findings report only; does not fix anything. Use when the user wants an adversarial/hard-pass code review, wants to check code against a PRD/issue's acceptance criteria, or when /auto-process-prd runs its code-review step (alongside or instead of CodeRabbit, per the project's ai/PIPELINE.md).
License
unknown
Instructions
82 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • lua-wow.md · checklists/
  • php.md · checklists/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from jonzenor/dotagents-spellbook

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 28, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/jonzenor/dotagents-spellbook
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from jonzenor

Cite this page

adversarial-code-review skill. Agent Mart. https://agentmart.dev/skills/jonzenor-adversarial-code-review (last updated 2026-10-24)