architect

architect is a command for coding agents from MadAppGang/claude-code. It costs 12 tokens per session (2,803 once invoked), scanned A, original, MIT.

An architecture-planning command that examines a project, compares possible designs, and documents the chosen technical approach. It is meant to guide decisions rather than write the implementation.

In plain words
What is it for?
Use it to plan systems, features, or services across different technology stacks. It helps gather requirements, compare alternatives, define a detailed design, and validate the plan.
Why use it?
It helps turn vague requirements into a considered design and makes trade-offs explicit before coding begins. It also checks the existing project structure and technology choices.

Command

Part of the dev plugin — 47 skills, 12 commands, 14 agents shipped together

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/madappgang/claude-code/architect
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code

Or install dev, the plugin that ships this one along with the rest of its 47 skills, 12 commands, 14 agents.

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/madappgang/claude-code/architect.svg)](https://agentmods.dev/commands/madappgang/claude-code/architect)
Your own site
<a href="https://agentmods.dev/commands/madappgang/claude-code/architect"><img src="https://agentmods.dev/badge/commands/madappgang/claude-code/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 2,803 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 $0.00012 $0.02803
Opus 5 $0.00006 $0.01401
Sonnet 5 $0.00002 $0.00561
Haiku 4.5 $0.00001 $0.00280

Measured 2d ago against content hash d1a2dbf90900, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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/dev/commands/architect.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<user_request> $ARGUMENTS </user_request>

  Before starting, create todo list with all 7 phases:
  0. Initialize (detect stack)
  1. Requirements Analysis
  2. Alternative Designs
  3. Trade-off Analysis
  4. Detailed Design
  5. Validation (optional, if Claudish available)
  6. Finalization

  Update continuously as you progress.
</todowrite_requirement>

<orchestrator_role>
  **You are an ORCHESTRATOR, not IMPLEMENTER.**

  **You MUST:**
  - Delegate architecture work to architect agent
  - Produce comprehensive documentation
  - Consider multiple alternatives
  - Analyze trade-offs

  **You MUST NOT:**
  - Write implementation code
  - Skip trade-off analysis
  - Ignore existing patterns
</orchestrator_role>

</critical_constraints>

      Detect ALL technology stacks in this project.
      Save to: ${SESSION_PATH}/context.json
      ```
    </step>
    <step>Gather context on existing architecture via Read/Grep</step>
    <step>Mark PHASE 0 as completed</step>
  </steps>
  <quality_gate>Context gathered, stack detected</quality_gate>
</phase>

<phase number="1" name="Requirements Analysis">
  <objective>Understand and document requirements</objective>
  <steps>
    <step>Mark PHASE 1 as in_progress</step>
    <step>
      Launch architect agent:
      ```
      SESSION_PATH: ${SESSION_PATH}
      DETECTED_STACK: {stack}

      Analyze requirements for: {architecture_request}

      Document:
      1. Functional requirements
      2. Non-functional requirements (performance, security, scalability)
      3. Constraints (tech stack, budget, timeline)
      4. Assumptions
      5. Dependencies

      Save to: ${SESSION_PATH}/requirements.md
      ```
    </step>
    <step>
      **User Confirmation** (AskUserQuestion):
      "Please review the requirements analysis. Are these accurate?"
      1. Approve requirements
      2. Request revisions
      3. Add missing requirements
    </step>
    <step>Mark PHASE 1 as completed</step>
  </steps>
  <quality_gate>Requirements documented and confirmed</quality_gate>
</phase>

<phase number="2" name="Alternative Designs">
  <objective>Generate multiple design alternatives</objective>
  <steps>
    <step>Mark PHASE 2 as in_progress</step>
    <step>
      Launch architect agent:
      ```
      SESSION_PATH: ${SESSION_PATH}

      Based on requirements: ${SESSION_PATH}/requirements.md

      Generate 2-3 design alternatives:

      For each alternative, document:
      1. Overview and approach
      2. Component/module structure
      3. Data flow
      4. Technology choices
      5. Pros and cons
      6. Estimated complexity
      7. Risk assessment

      Save to: ${SESSION_PATH}/alternatives.md
      ```
    </step>
    <step>Present alternatives summary to user</step>
    <step>Mark PHASE 2 as completed</step>
  </steps>
  <quality_gate>Multiple alternatives documented</quality_gate>
</phase>

Read the full file on GitHub · 392 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 · 392 lines · 12 tokens per session scan A d1a2dbf90900

Subscribe to this mod's changes

architect is a command published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 2,803 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 2026-09-03.