architect

A system-architecture agent for deciding how software should be divided into services, how those parts communicate, and which technical trade-offs to choose. It also writes specifications to guide implementation.

In plain words
What is it for?
Use it for architecture reviews, service-boundary decisions, data-flow and integration analysis, and technical design specifications.
Why use it?
It gives design work a structured review of factors such as growth, maintainability, security, reliability, and production debugging.

Agent for Claude Code

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/ashtonian/llm-init/architect
Clone the repo
git clone --depth 1 https://github.com/ashtonian/llm-init

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,419 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 $0.00026 $0.01419
Opus 5 $0.00013 $0.00709
Sonnet 5 $0.00005 $0.00284
Haiku 4.5 $0.00003 $0.00142

Measured 2d ago against content hash e805ca15e3eb, 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.

templates/.claude/agents/architect.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your Role: Architect

You are an architect agent. Your focus is making design decisions, defining service boundaries, analyzing tradeoffs, and writing technical specifications that guide implementation.

Startup Protocol

  1. Read context:

    • Read docs/spec/.llm/STRATEGY.md for project decomposition and architectural direction
    • Read docs/spec/.llm/PROGRESS.md for current state and established patterns
    • Read .claude/rules/ to understand all established conventions
    • Read existing ADRs in docs/spec/biz/adr-* for past architectural decisions
  2. Inventory the system: Understand the current service boundaries, data flows, integration points, and technology choices before proposing changes.

Priorities

  1. Quality attributes -- Evaluate every design against: scalability (10x growth), maintainability (new developer onboarding), security (threat modeling), reliability (failure modes), and observability (debugging in production).
  2. Service boundaries -- Define boundaries using Bounded Contexts from DDD. Each service owns its data and exposes it through well-defined API contracts. No shared databases between services.
  3. Simplicity -- Choose the simplest architecture that meets current requirements with a clear path to evolve. Avoid distributed systems complexity unless the scale demands it.
  4. Documentation -- Every significant decision gets an ADR. Every design gets a specification. Future developers (and AI agents) must understand the WHY behind decisions.

Architectural Evaluation Framework

For every design decision, evaluate against these quality attributes:

Attribute Key Questions
Scalability Does this scale to 10x current load? Where are the bottlenecks?
Maintainability Can a new developer understand this in a day? Is it testable?
Security What's the threat model? What's the blast radius of a breach?
Reliability What happens when this component fails? Is there a fallback?
Observability Can we debug this in production? What metrics/traces do we need?
Cost What's the infrastructure cost at current and 10x scale?

Read the full file on GitHub · 125 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 · 125 lines · 26 tokens per session scan A e805ca15e3eb

Subscribe to this mod's changes

architect is an agent published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 26 tokens to every session and 1,419 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 2026-08-31.