bmad-code-review

Reviews code diffs adversarially using parallel review layers and structured triage.

Updated Jul 2, 2026
One-click install
npx skills add https://github.com/tuanpa-nhg-eng/nhg-ipms --skill bmad-code-review-tuanpa-nhg-eng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/tuanpa-nhg-eng/nhg-ipms/tree/main/.claude/skills/bmad-code-review
Command: npx skills add https://github.com/tuanpa-nhg-eng/nhg-ipms --skill bmad-code-review-tuanpa-nhg-eng

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 pass lacks diverse perspectives. This Skill runs multiple adversarial review layers in parallel over a git diff, then triages findings into actionable buckets so real issues get fixed and noise gets dismissed. ## Core Features & Use Cases - Parallel Review Layers: Runs Blind Hunter, Edge Case Hunter, Verification Gap, and Acceptance Auditor layers simultaneously against the diff, each with a distinct adversarial focus. - Structured Triage: Normalizes, deduplicates, and severity-rates findings by reading the actual source code, then routes each into decision-needed, patch, defer, or dismiss buckets. - Sprint Integration: Writes findings into story files, syncs sprint-status.yaml, and supports spec-based full reviews or spec-free reviews of uncommitted changes, branch diffs, or commit ranges. - Use Case: After finishing a story implementation, ask for a code review; the Skill gathers the diff, runs all review layers, presents triaged findings, applies approved patches, and updates the story status. ## Quick Start Run a code review on my current uncommitted changes against the story spec.

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 git changes?

Trigger the skill with a request like "run code review" and choose a diff source: uncommitted changes, staged changes, branch diff, commit range, or a pasted diff. The skill constructs the diff with git, runs parallel review layers, and presents triaged findings.

What review layers does this code review workflow use?

It runs four layers in parallel: Blind Hunter for general issues, Edge Case Hunter for unhandled paths and deletion regressions, Verification Gap for missing test coverage of changed behavior, and Acceptance Auditor for spec compliance in full review mode.

Can I review code without a spec or story file?

Yes, declare "no spec" explicitly or choose to continue without one when asked. The review runs in no-spec mode, the Acceptance Auditor layer is skipped, and findings that would need a decision are reclassified as patch or defer.

How are code review findings triaged and handled?

Findings are deduplicated, severity-rated by reading the actual source code, and routed into decision-needed, patch, defer, or dismiss buckets. You can apply all patches at once, walk through each, or leave them as action items in the story file.

Does the review update sprint status automatically?

Yes, when a story key is known from sprint-status.yaml, the skill updates the story file status to done or in-progress based on review outcome and syncs the sprint status file while preserving its structure and comments.

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 remaining layers. If zero findings survive triage while layers failed, the skill warns that the review may be incomplete instead of declaring it clean.