bmad-architecture

A command that turns a product requirements document (PRD) into a technical architecture document using the BMAD planning method.

In plain words
What is it for?
Use it to create a technical plan covering a project’s structure and implementation approach from `bmad-backlog/prd/prd.md`, with optional research files.
Why use it?
It prevents architecture work from starting without the required product requirements and delegates the detailed planning work to an architect agent.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/webdevtodayjason/titanium-plugins/bmad-architecture
Clone the repo
git clone --depth 1 https://github.com/webdevtodayjason/titanium-plugins
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 874 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.00874
Opus 5 $0.00004 $0.00437
Sonnet 5 $0.00002 $0.00175
Haiku 4.5 $0.00001 $0.00087

Measured 2d ago against content hash e279bb635244, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bmad-architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/titanium-toolkit/commands/bmad-architecture.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BMAD Architecture - Generate Technical Architecture

Use the architect subagent to create comprehensive technical architecture for this project following BMAD methodology.

Task Delegation

First check if the PRD exists, then launch the architect subagent to handle the complete architecture generation workflow.

Process

Step 1: Verify Prerequisites

Check that PRD exists before delegating to architect:

ls bmad-backlog/prd/prd.md 2>/dev/null || echo "PRD not found"

If PRD NOT found:

❌ Error: PRD not found at bmad-backlog/prd/prd.md

Architecture generation requires a PRD to work from.

Please run: /titanium-toolkit:bmad-prd first
(Or /titanium-toolkit:bmad-start for complete guided workflow)

Stop here - do not launch architect without PRD.

If PRD exists: Continue to Step 2.

Step 2: Launch Architect Subagent

Use the Task tool to launch the architect subagent in its own context window:

Task(
  description: "Generate BMAD architecture",
  prompt: "Create comprehensive technical architecture document following BMAD methodology.

Input:
- PRD: bmad-backlog/prd/prd.md
- Research findings: bmad-backlog/research/*.md (if any exist)

Output:
- Architecture document: bmad-backlog/architecture/architecture.md

Requirements:
1. Read the PRD to understand requirements
2. Check for research findings and incorporate recommendations
3. Generate architecture using bmad_generator MCP tool
4. Review tech stack with user and get approval
5. Validate architecture using bmad_validator MCP tool
6. Run vibe-check to validate architectural decisions
7. Store result in Pieces for future reference
8. Present summary with next steps

**IMPORTANT**: Keep your summary response BRIEF (under 500 tokens). Just return:
- Confirmation architecture is complete
- Proposed tech stack (2-3 sentences)
- MVP cost estimate
- Any critical decisions made

DO NOT include the full architecture content in your response - it's already saved to the file.

Follow your complete architecture workflow from the bmad-methodology skill.

Project path: $(pwd)",
  subagent_type: "architect"
)

Read the full file on GitHub · 127 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 127 lines · 8 tokens per session scan A e279bb635244

Subscribe to this mod's changes

bmad-architecture is a command published in the GitHub repository webdevtodayjason/titanium-plugins (7 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 874 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.