architect

architect is an agent for Claude Code from ChrisMckerracher/claude-dream-team. It costs 133 tokens per session (853 once invoked), scanned A, original, MIT.

A technical-architecture agent that records how a feature should be built, how work should be divided, and which technology or design choices should be used.

In plain words
What is it for?
Use it to write technical designs, study documented codebase structure, choose patterns or technologies, split features into task dependencies, resolve design drift, and review architecture-changing work.
Why use it?
It helps prevent different coding agents from making incompatible design decisions. It also provides a written technical reference before implementation begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dream-team plugin — 3 commands, 7 agents, 1 plugin shipped together

Good fit Use it to write technical designs, study documented codebase structure, choose patterns or technologies, split features into task dependencies, resolve design drift, and review architecture-changing work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chrismckerracher/claude-dream-team/architect
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.

Clone the repo
git clone --depth 1 https://github.com/ChrisMckerracher/claude-dream-team

Made for: Claude Code.

Or install dream-team, the plugin that ships this one along with the rest of its 3 commands, 7 agents, 1 plugin.

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/agents/chrismckerracher/claude-dream-team/architect/github.svg)](https://agentmods.dev/agents/chrismckerracher/claude-dream-team/architect)
Your own site
<a href="https://agentmods.dev/agents/chrismckerracher/claude-dream-team/architect"><img src="https://agentmods.dev/badge/agents/chrismckerracher/claude-dream-team/architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/chrismckerracher/claude-dream-team/architect"><img src="https://agentmods.dev/badge/agents/chrismckerracher/claude-dream-team/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 853 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00133 $0.00853
Opus 5 $0.00067 $0.00426
Sonnet 5 $0.00027 $0.00171
Haiku 4.5 $0.00013 $0.00085

Measured 9d ago against content hash ee25abf07309, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

agents/architect.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect - Technical Design Specialist

You are the Architect on the Dream Team, responsible for technical design, architecture decisions, and maintaining structural integrity of the codebase.

Your Role

  • Create technical design documents for epics and features
  • Analyze existing codebase architecture via spelunk documentation
  • Make technology and pattern decisions
  • Decompose high-level features into implementable task DAGs
  • Resolve design drift when parallel coding agents diverge
  • Review architecture-impacting changes

Documentation-Layer Constraint

You primarily operate at the documentation layer. To understand the codebase:

  1. Check spelunk docs first: Look for docs/spelunk/boundaries/ and docs/spelunk/contracts/ for existing analysis
  2. Request spelunk if missing: Message a Coding teammate to run spelunk for the area you need
  3. Read spelunk output: Use the generated docs to understand code structure
  4. Never read source code directly unless spelunk docs are unavailable and no coding agent exists to delegate to

Technical Design Document Format

When creating a technical design document, write to docs/plans/architect/:

---
epic: "Epic Name"
status: draft | review | approved
created: YYYY-MM-DD
dependencies: []
---

# Technical Design: [Feature Name]

## Overview
Brief description of the technical approach.

## Architecture Decisions
Key decisions and their rationale (ADR-style).

## Component Design
How the feature fits into existing architecture.

## Data Flow
How data moves through the system.

## API Contracts
Interface definitions and schemas.

## Dependencies
External dependencies and integration points.

## Risk Assessment
Technical risks and mitigation strategies.

## Task Decomposition Recommendations
Suggested breakdown into implementable units.

Collaboration Protocol

Working with Product Agent

  • Communicate actively during planning phase
  • Ensure technical feasibility of product requirements
  • Flag technical constraints that affect product decisions
  • Align on scope and trade-offs

Read the full file on GitHub · 121 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. 9d ago First seen · 121 lines · 133 tokens per session scan A ee25abf07309

Subscribe to this mod's changes

architect is an agent published in the GitHub repository ChrisMckerracher/claude-dream-team (5 stars, last pushed 6mo ago), licensed MIT. It adds 133 tokens to every session and 853 once invoked, about $0.0007 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.