architect

architect is a command for Claude Code from TheWayWithin/agent-11. It costs 12 tokens per session (11,129 once invoked), scanned A, original, MIT.

A command that writes an architecture.md file describing a software system's design decisions. It takes foundation documents such as a product requirements document and records choices about technologies, integrations, data, security, and scaling.

In plain words
What is it for?
Use it to define a system design before creating an implementation plan, including its technology choices, data model, integrations, and trade-offs.
Why use it?
Requirements documents describe what to build but often leave out how it should work. Writing these decisions down before task planning reduces uncertainty and conflicting assumptions.

Command for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool; positional $N argument.

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/thewaywithin/agent-11/architect
Clone the repo
git clone --depth 1 https://github.com/TheWayWithin/agent-11

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for architect

README.md
[![agentmods](https://agentmods.dev/badge/commands/thewaywithin/agent-11/architect.svg)](https://agentmods.dev/commands/thewaywithin/agent-11/architect)
Your own site
<a href="https://agentmods.dev/commands/thewaywithin/agent-11/architect"><img src="https://agentmods.dev/badge/commands/thewaywithin/agent-11/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,129 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 5.1 $0.00012 $0.11129
Opus 5 $0.00006 $0.05565
Sonnet 5 $0.00002 $0.02226
Haiku 4.5 $0.00001 $0.01113

Measured today against content hash d7c7027fb3c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

architect 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 today.

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.

project/commands/architect.md · 1,371 lines

How it starts

The opening of the file, as written. The whole thing — 1,371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/architect Command

PURPOSE

Generate a comprehensive architecture.md document that captures all system design decisions before project planning begins. This bridges the gap between "what to build" (PRD) and "how to build it" (project-plan.md).

Why This Matters: PRDs define features but often hand-wave technical decisions. Architecture documentation ensures:

  • Tech stack decisions are explicit and justified
  • Integration patterns are defined before coding
  • Data models are designed before implementation
  • Security and scalability are addressed upfront
  • Trade-offs are documented for future reference

WORKFLOW POSITION

/foundations init → /architect → /bootstrap → /coord continue
       ↓                ↓              ↓              ↓
   Extract PRD    Design System    Create Plan    Build It

/architect is REQUIRED before /bootstrap - you can't plan tasks without knowing the architecture.

PREREQUISITES

Before running /architect, ensure:

  1. /foundations init has completed successfully

    • .context/structured/prd.yaml exists (REQUIRED)
    • .context/structured/vision.yaml exists (recommended)
    • .context/structured/roadmap.yaml exists (optional - provides strategic context)
  2. PRD contains tech stack hints

    • Frontend framework mentioned
    • Database preference indicated
    • Key integrations identified

Context Sources Used:

  • prd.yaml → Features, tech stack preferences, integrations
  • vision.yaml → Hedgehog concept, value proposition (informs architectural priorities)
  • roadmap.yaml → Keystone products, implementation framework (informs build sequence)

EXECUTION PROTOCOL

CRITICAL: This command MUST prompt for mode selection before doing any work (unless --mode flag is provided).

Step 1: Check for --mode Flag

If --mode auto → Skip to AUTO MODE section If --mode engaged → Skip to ENGAGED MODE section If no --mode flag → Continue to Step 2

Step 2: Present Mode Selection (MANDATORY)

Read the full file on GitHub · 1,371 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. today First seen · 1,371 lines · 12 tokens per session scan A d7c7027fb3c7

Subscribe to this mod's changes

architect is a command published in the GitHub repository TheWayWithin/agent-11 (15 stars, last pushed 13d ago), licensed MIT. It adds 12 tokens to every session and 11,129 once invoked, about $0.0001 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 2026-09-04.