mcpField
B
bmad-code-review

bmad-code-review

github.com/bmad-code-orgTesting & quality54.7k12.8k installsUpdated 1w ago
Repository

About bmad-code-review

A BMad skill that renders a code-review workflow using the project’s `render_skill.py` script. It directs the agent to run the command once, pass applicable review or interaction settings, and follow the generated workflow.

Key features

  1. 01Locate the project root containing `_bmad/`
  2. 02Render the review workflow once
  3. 03Set quick or thorough review options
  4. 04Configure fixes and interaction mode when requested
  5. 05Stop if setup is missing or execution fails

Use cases

  1. 01Start a BMad code review in a project
  2. 02Run a quick or thorough review
  3. 03Hand off fixes after a no-code review
  4. 04Run review workflows non-interactively

Install

Copy the command and run it in a terminal.

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

After installing, type/bmad-code-reviewin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

bmod.toml
customize.toml
step-01-gather-context.md
step-02-review.md
step-03-triage.md
step-04-route.md
step-05-present.md
workflow.md
references/
claims-check.md
deletion-check.md
review-prompts/
edge-case-hunter.md
verification-gap.md

Details

From the project README

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.

Comments

Markdown supported