bmad-code-review

Reviews code changes with parallel independent reviewers, then triages and presents findings.

1|Updated Sep 18, 2026
One-click install
npx skills add https://github.com/PastaSus/egg-defender --skill bmad-code-review-pastasus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/PastaSus/egg-defender/tree/main/.agents/skills/bmad-code-review
Command: npx skills add https://github.com/PastaSus/egg-defender --skill bmad-code-review-pastasus

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Code reviews often miss edge cases, verification gaps, and spec deviations because a single reviewer cannot cover every angle. This Skill runs several independent reviewers in parallel against a diff, then triages their findings into actionable decisions, patches, and deferred work. ## Core Features & Use Cases - Parallel adversarial review layers: Launches independent reviewers (Blind Hunter, Edge Case Hunter, Verification Gap, Acceptance Auditor) against a unified diff, each with a distinct review mandate. - Structured triage and routing: Verifies every finding, assigns verdicts, groups by root cause, and routes results into decision-needed, patch, or defer buckets. - Sprint and story integration: Writes findings into story files, updates story status, and syncs sprint-status.yaml after the review completes. - Use Case: After finishing a feature branch, ask for a code review; the Skill diffs against the base branch, runs all review layers, and presents verified findings you can patch immediately or defer. ## Quick Start Ask the assistant to run a code review on your current branch changes 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 a code review on my current branch changes?

Ask the assistant to run a code review and choose branch diff against your base branch. The Skill generates the diff with git, launches parallel review layers, and presents triaged findings for you to patch or defer.

What review types does a multi-layer code review cover?

It covers blind gap hunting, exhaustive edge-case path tracing, verification gap analysis checking whether tests would catch regressions, and acceptance auditing against a spec. Each layer runs independently and findings are merged during triage.

Can I customize the review layers or add my own checks?

Yes, the customize.toml file defines review layers with instructions and optional when conditions. Team and user TOML overrides merge structurally, letting you disable layers, replace instructions, or add persistent facts and activation steps.

Does the code review work without a spec or story file?

Yes, you can explicitly choose no-spec mode when prompted. In that mode the Acceptance Auditor layer is skipped, and findings that would need a decision are reclassified as patch or defer since no spec exists to resolve ambiguity.

What happens if a review layer fails or returns nothing?

Failed or empty layers are recorded in a failed_layers list and the review continues with the remaining layers. If all findings are rejected but layers failed, the Skill warns that the review may be incomplete rather than declaring it clean.