bmad-code-review

Reviews code changes adversarially using parallel review layers with structured triage into actionable categories.

Updated Apr 9, 2026

Search Tags:#code review #subagents #acceptance criteria #triage #git diff #adversarial review #sprint tracking

Ready to run

npx skills add https://github.com/5onyy/essential-ai-agent-skills --skill bmad-code-review-5onyy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/5onyy/essential-ai-agent-skills/tree/main/.cursor/skills/bmad-code-review
Command: npx skills add https://github.com/5onyy/essential-ai-agent-skills --skill bmad-code-review-5onyy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often miss edge cases, acceptance criteria violations, or subtle bugs because a single reviewer perspective is limited. This Skill runs adversarial multi-layer reviews of git diffs and triages every finding into clear, actionable categories. ## Core Features & Use Cases - Parallel Adversarial Review Layers: Runs a Blind Hunter (diff only), Edge Case Hunter (diff plus project access), and Acceptance Auditor (diff plus spec) to catch different classes of issues. - Structured Triage: Normalizes, deduplicates, and classifies findings into decision-needed, patch, defer, or dismiss buckets. - Sprint Integration: Writes findings into story files, updates story status, and syncs sprint-status.yaml tracking. - Use Case: After finishing a feature branch, ask for a review of the branch diff against main; the Skill gathers the diff, launches the review layers, and walks you through fixing or deferring each finding. ## Quick Start Ask the agent to run a code review on your current uncommitted changes or a branch diff against main.

Frequently Asked Questions about bmad-code-review

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

FAQPage Schema

How do I run an adversarial code review on my changes?▼

Trigger the workflow by asking to run a code review, then choose a diff source such as uncommitted changes, staged changes, a branch diff, or a commit range. The Skill constructs the git diff, launches parallel review layers, and triages the findings.

What review layers does this code review workflow use?▼

It uses three parallel layers: a Blind Hunter that sees only the diff, an Edge Case Hunter with project read access, and an Acceptance Auditor that checks the diff against a spec file. The Acceptance Auditor is skipped when no spec is provided.

Can I review a branch diff against main?▼

Yes, select the branch diff option and specify the base branch. The Skill verifies the base branch exists before running git diff, and halts to ask for a valid branch if it does not.

What happens to findings after the code review triage?▼

Findings are classified as decision-needed, patch, defer, or dismiss. Decision-needed items require your input, patches can be auto-applied or left as action items, and deferred items are logged to a deferred-work file.

Does the review update sprint status tracking?▼

Yes, when a story file and story key are available, the Skill updates the story status to done or in-progress and syncs the matching entry in sprint-status.yaml. If no story key exists, only the story file is updated.

What happens if a review subagent fails or returns empty results?▼

The failed layer is recorded in a failed_layers list and the review proceeds with the remaining layers. If zero findings remain and any layer failed, the Skill warns that the review may be incomplete instead of declaring it clean.