ad-review

Automate adversarial code-review of diffs against governance standards.

728|16|Updated Mar 9, 2026

Search Tags:#workflow #codex #standards #diff #code-review #audit-trail

Ready to run

npx skills add https://github.com/alexandremendoncaalvaro/CorridorKey-Runtime --skill ad-review-alexandremendoncaalvaro

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ad-review
Source: https://github.com/alexandremendoncaalvaro/CorridorKey-Runtime/tree/main/.agents/skills/ad-review
Command: npx skills add https://github.com/alexandremendoncaalvaro/CorridorKey-Runtime --skill ad-review-alexandremendoncaalvaro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates adversarial code-review of diffs by comparing them against governance standards.

Core Features & Use Cases

Produces separate Standards Findings and Spec Findings in a single-session review.
Writes an audit trail to .agentic/reviews/ for traceability and future re-runs.
Reads core governance documents (AGENTS.md, ARCHITECTURE.md, GUIDELINES.md, CONTEXT.md) and relevant ADRs to ground assessments.
Explicitly avoids spawning subagents during the review workflow.

Quick Start

Review the current diff by running ad-review; it will read the diff, assemble binding context, and report findings.

Frequently Asked Questions about ad-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate code reviews against project governance standards?▼

Automated code review against governance standards is done by reading project diffs and comparing them to core documents like AGENTS.md, ARCHITECTURE.md, and GUIDELINES.md. This produces separate Standards Findings and Spec Findings in a single session.

What is adversarial code review for software diffs?▼

Adversarial code review is a single-pass process that audits software diffs against binding project context and architecture rules. It generates formal in-session findings and creates an audit trail for traceability without spawning subagents.

How do I generate an audit trail for code reviews?▼

Generating a code review audit trail is achieved by writing review results directly to the .agentic/reviews/ directory. This ensures traceability and provides a record for future re-runs of the software change assessment.

Does the code review workflow spawn subagents?▼

The code review workflow explicitly avoids spawning subagents during execution. It operates entirely in a single session to assess diffs and produce a formal handoff along with in-session findings.

Can I use architecture decision records to ground code change assessments?▼

Architecture decision records (ADRs) are read alongside CONTEXT.md and other governance documents to ground code change assessments. This binding context ensures the review evaluates diffs against established architectural decisions.

When do I need a formal handoff for code review findings?▼

A formal handoff for code review findings is needed when completing a single-session adversarial audit of software diffs. It finalizes the review by summarizing Standards Findings and Spec Findings for downstream traceability.