Skills bmad-code-org bmad-method BMad Method

bmad-code-review

Use it when:: You want a change reviewed: a PR, branch, commit range, or staged or uncommitted work.
It does:: Sends the diff to up to four reviewer subagents with different lenses, then checks every finding against the code before keeping it.
You get:: Findings sorted into decisions for you, patches and deferred items, with each rejected finding listed and why.
Then:: You apply every patch, walk through them one by one, or keep them as action items in the plan file.
Modes:: Thorough by default or quick with one reviewer; a no-code review edits nothing and writes a fix handoff for a coding agent.
Needs:: uv and BMad set up in the project: run the bmad skill's setup first; subagents for the reviewers.

Skill 14 of 24 in the BMad Method bundle, after bmad-build-auto and before bmad-walkthrough.

Only works inside its bundle: Its workflow is printed by a script in the _bmad/ folder that the bmad skill's setup creates, so it does nothing without that setup. Install BMad Method instead.

Needs uv and BMad set up in the project: it runs scripts from the _bmad/ folder that the bmad skill's setup creates.

TL;DR

BMad's code review finds what to review from your request, a ticket in review in BMad's ticket tree, or the current branch, writes the diff to a temp file, and collects the commit messages as the change's own claims. A thorough review launches its reviewers at once, each without the others' findings: a blind hunter that sees only the diff, an edge-case hunter, a verification-gap reviewer that looks for behavior no test checks, and, when an intent is available, an intent-alignment auditor that compares the diff with it. The agent then checks every finding at its file and line, grades the real ones high, medium or low, rejects false ones with the evidence, and merges findings with the same root cause. Each survivor becomes a decision for you, a patch, or a deferral for problems this change didn't cause, which also go to deferred-work.md. With a plan file, the findings are written into it. A non-interactive run, such as from CI or another workflow, applies the patches without asking.

Summarizes the skill at e734d3a.

npx skills add https://github.com/bmad-code-org/bmad-method --skill bmad-code-review

skills.sh page Source on GitHub All skills from bmad-code-org/bmad-method

Total Downloads: 15,200 on skills.sh, Nov 9, 2026
Repo stars: 55,140 bmad-code-org/bmad-method
First seen: Mar 14, 2026 on skills.sh

Weekly Downloads

1.5K

+53% over the 8 weeks to Nov 9

Weekly values

Week to	Installs
Sep 21	987
Sep 28	1,254
Oct 5	2,417
Oct 12	2,699
Oct 19	1,536
Oct 26	1,706
Nov 2	1,452
Nov 9	1,514

Category	category:debugging category:software-engineering Find root causes, review code and test what you built. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type	type:workflow A multi-step process the agent follows: interview, debug, run a TDD loop, review.
Effect	effect:local Its own steps create or change files, git state or local tools.
Needs	needs:cli needs:subagents A specific command-line tool or desktop app must be installed, such as gh, agent-browser, LibreOffice, Obsidian or a vendor CLI. Relies on the agent being able to spawn subagents.
Publisher	by:community Everyone else. Unverified vendor claims default to community.
Topics	code-review multi-agent verification

SKILL.md

From bmad-code-org/bmad-method at e734d3a. Checked daily, last changed Nov 6, 2026.

Frontmatter

name: bmad-code-review
description: 'Review code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code"'

Run the following command exactly once without changing the current working directory.

Replace {project-root} with the nearest folder containing _bmad/, from the working directory upward. Replace {skill-root} with the absolute path to this skill's directory.

If the invocation asks for a quick or thorough review, append --set workflow.review=<value> to the command. If the invocation asks for a no-code review, append --set workflow.fixes=handoff to the command.

If the invocation is clearly non-interactive -- it says not to ask questions, or a bot, a CI job or another workflow is running the review -- append --set workflow.interactive=false. When in doubt, don't.

uv run --no-cache "{project-root}/_bmad/scripts/render_skill.py" --project-root "{project-root}" --skill "{skill-root}"

The command prints the skill's workflow: follow it. HALT: <reason>: report the reason and stop.
If the script does not exist, BMad is not set up in this project yet. Offer to set it up using bmad skill, then run the command again. If you do not have the bmad skill, offer to install it first.
On any other output or failure, including uv being unavailable, report the command output and stop. Do not run any workflow source directly.