bmad-build

Implements code changes through a spec-driven plan, implement, and review workflow.

6|Updated Aug 29, 2026
One-click install
npx skills add https://github.com/HordRicJr/Akomagni --skill bmad-build-hordricjr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-build
Source: https://github.com/HordRicJr/Akomagni/tree/main/bmad-core/.agents/skills/bmad-build
Command: npx skills add https://github.com/HordRicJr/Akomagni --skill bmad-build-hordricjr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning a feature request, bug fix, or refactor into working code often skips planning and review, producing inconsistent changes that ignore project conventions. This Skill enforces a disciplined pipeline that converts user intent into a reviewed, tested, and committed code change. ## Core Features & Use Cases - Spec-driven planning: Clarifies intent, investigates the codebase, and writes a token-bounded implementation spec with tasks, acceptance criteria, and a code map before any code changes. - Subagent implementation and multi-layer review: Dispatches implementation to a context-free subagent, then runs parallel review layers (blind hunter, edge-case hunter, verification-gap) with triage into patch, defer, or spec-fix loopbacks. - Epic and sprint integration: Compiles epic context from planning artifacts and syncs story status in sprint-status.yaml for teams working from epics. - Use Case: Ask to add a new API endpoint; the Skill drafts a spec for your approval, implements it via a subagent, reviews the diff for edge cases and missing tests, commits the result, and presents a suggested review order. ## Quick Start Ask the assistant to implement a feature or fix a bug, for example: implement password reset functionality following the project's existing patterns.

Frequently Asked Questions about bmad-build

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

FAQPage Schema
How do I implement a feature using a spec-driven workflow?

Describe your intent in plain language and the workflow clarifies it, investigates the codebase, and writes an implementation spec with tasks and acceptance criteria. After you approve the spec, a subagent implements it and the change goes through automated review before commit.

How does automated code review work after implementation?

The workflow constructs a diff from the baseline commit and runs parallel review layers: a blind hunter for missing logic, an edge-case hunter for unguarded paths, and a verification-gap reviewer for untested behavior. Findings are triaged into auto-fixes, deferred items, or spec-correction loopbacks.

Can I use this workflow with epic and sprint planning?

Yes. When the intent is an epic story, the workflow compiles a focused epic context file from planning artifacts like the PRD and architecture docs, and syncs the story's status in sprint-status.yaml as it moves through in-progress, review, and done states.

What happens if the implementation spec is too large?

Specs exceeding 1600 tokens trigger a checkpoint where you choose to split the work into multiple goals or keep the full spec. Split goals are recorded in a deferred-work file so nothing is lost.

When should I use the one-shot route instead of full planning?

Use the one-shot route only for changes with zero blast radius: clear intent, no architectural decisions, and no plausible side effects elsewhere. When uncertain, the workflow defaults to the full plan-code-review path.