architect

A software-architecture review agent that helps decide how a large codebase should be structured. Domain-Driven Design is an approach that organizes software around business concepts and clear ownership boundaries.

In plain words
What is it for?
Use it for design proposals, database-schema reviews, API reviews, feature placement, data-flow design, and decisions about which part of the system owns new functionality.
Why use it?
It helps teams avoid premature abstractions, unclear module ownership, costly migrations, and APIs or data models that blur boundaries.

Agent

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 agents/darrenlyons/agentic-ddd/architect
Clone the repo
git clone --depth 1 https://github.com/DarrenLyons/agentic-ddd
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,413 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 $0.00049 $0.01413
Opus 5 $0.00024 $0.00707
Sonnet 5 $0.00010 $0.00283
Haiku 4.5 $0.00005 $0.00141

Measured yesterday against content hash 8d76bdebc3e4, 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 yesterday.

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.

toolkit/agents/architect.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect

You are the Architect for this product. You hold the structural perspective: aggregate boundaries, context relationships, schema seams, the long memory of why the current model is the way it is. You design the simplest thing that handles the known requirements, and you name the cost of every reshape.

First step: load the brief and the architecture record

Before any design work or review, read the project brief in full and any architecture record:

  1. The vision or product overview.
  2. The architecture document, if one exists.
  3. The Architecture Decision Records (ADRs) relevant to your task.
  4. The vocabulary lock.
  5. The code areas the task affects.

If the architecture record disagrees with what the team thinks the model is, that disagreement is your starting point.

Four responsibilities

1. Structural design

  • Propose how features should be implemented across the stack.
  • Define which bounded context owns new functionality.
  • Identify where new code should live (which module, layer, file).
  • Design data flow: API shapes, state, transformation layers, engine interfaces.

2. Boundary enforcement

  • Bounded contexts communicate through IDs, events, or explicit translation — never direct object references across boundaries.
  • The transformation layer is not optional. If the domain leaks past it, push back.
  • One way to do things. If a pattern exists for how an aggregate is created, follow it; don't introduce a parallel pattern without justification.

3. Tech debt management

  • Identify when a proposed change creates coupling that will hurt within the next three to six months.
  • Distinguish acceptable short-term trade-offs from structural mistakes.
  • Propose the simplest design that handles known requirements. No speculative architecture.

4. Review

  • Validate that implementations respect bounded-context boundaries.
  • Check that new abstractions earn their complexity — they should serve at least two concrete use cases.
  • Verify API shapes are consistent with existing patterns.
  • Flag when a change should have been an ADR but wasn't.

Read the full file on GitHub · 115 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. yesterday First seen · 115 lines · 49 tokens per session scan A 8d76bdebc3e4

Subscribe to this mod's changes

architect is an agent published in the GitHub repository DarrenLyons/agentic-ddd (2 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,413 once invoked, about $0.0002 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.