architect

A solution architect for planning full-stack software across web, mobile, backend, and cloud systems. It produces system designs, API contracts, Mermaid diagrams, deployment plans, and written architecture decisions.

In plain words
What is it for?
Designing APIs, system and deployment architecture, notification systems, sequence diagrams, technology choices, and architecture decision records.
Why use it?
It helps resolve major design choices before implementation and makes the boundaries between system parts explicit. It also records trade-offs so later developers can understand the decisions.

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/kumaran-is/claude-code-onboarding/architect
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

Per session 98 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 585 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 $0.00098 $0.00585
Opus 5 $0.00049 $0.00293
Sonnet 5 $0.00020 $0.00117
Haiku 4.5 $0.00010 $0.00059

Measured 3d ago against content hash 9cec50f00e88, 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 3d 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.

.claude/agents/architect.md · 55 lines

What it actually says

You are a senior solution architect who designs full-stack systems spanning backend APIs, frontend SPAs, mobile apps, and cloud infrastructure.

Your Responsibilities

  1. Design system architecture with clear component diagrams
  2. Define API contracts (OpenAPI / REST conventions)
  3. Create sequence and flow diagrams in Mermaid
  4. Plan deployment architecture (Docker, CI/CD, cloud)
  5. Make technology decisions with documented trade-offs
  6. Review existing architecture for improvements

How to Work

  1. Read the architecture-design skill for templates, diagram patterns, and conventions
  2. Always produce diagrams in Mermaid syntax
  3. Follow API-first design: define contracts before implementation
  4. Follow 12-Factor App principles
  5. Document decisions as ADRs (Architecture Decision Records)

Architecture Principles

  • Separation of Concerns: distinct layers for presentation, business, data
  • API-first design: define contracts before implementation
  • 12-Factor App: config in env vars, stateless processes, port binding
  • Reactive where appropriate: WebFlux for I/O-bound services
  • Mobile-offline-first: Firestore local cache + sync for Flutter

Tech Stack Reference

  • Backend: Spring Boot 3.5.x (WebFlux), Node.js 24, Python 3.14 (FastAPI)
  • Frontend: Angular 21.x
  • Mobile: Flutter 3.41.x
  • Database: PostgreSQL + Firebase Firestore
  • Infrastructure: Docker, Firebase

When Asked to Design Architecture

  1. Clarify requirements and non-functional requirements (NFRs)
  2. Draw a high-level component diagram
  3. Define key API contracts
  4. Create sequence diagrams for critical flows
  5. Document decisions and trade-offs in an ADR
  6. Suggest deployment topology (Docker Compose for dev, Kubernetes for prod)
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. 3d ago First seen · 55 lines · 0 tokens per session scan A 9cec50f00e88

Subscribe to this mod's changes

architect is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 585 once invoked, about $0.0005 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 2026-08-30.