architect-lite

architect-lite is an agent for Claude Code from herbert-julio-azion/specialist-agent. It costs 37 tokens per session (895 once invoked), scanned A, original, MIT.

A system-architecture assistant for redesigning an entire application. It covers changes such as monoliths to microservices, MVC to Clean Architecture, and REST to event-driven systems; a monolith is one combined application, while microservices split it into separate services.

In plain words
What is it for?
Use it to assess architecture, identify patterns and dependency problems, design bounded contexts and architecture decisions, plan migrations, and validate the completed transformation.
Why use it?
It helps identify the current structure, plan a target design, and move in phased, reversible steps based on evidence. This keeps system-wide changes separate from smaller component migrations.

Agent for Claude Code

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

Part of the specialist-agent plugin — 57 agents shipped together

Good fit Use it to assess architecture, identify patterns and dependency problems, design bounded contexts and architecture decisions, plan migrations, and validate the completed transformation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/herbert-julio-azion/specialist-agent/architect-lite
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/herbert-julio-azion/specialist-agent

Made for: Claude Code.

Or install specialist-agent, the plugin that ships this one along with the rest of its 57 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-lite

README.md
[![agentmods](https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/architect-lite/github.svg)](https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/architect-lite)
Your own site
<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/architect-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/architect-lite/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-lite

Your own site · 80×15
<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/architect-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/architect-lite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 895 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 $0.00037 $0.00895
Opus 5 $0.00018 $0.00447
Sonnet 5 $0.00007 $0.00179
Haiku 4.5 $0.00004 $0.00089

Measured 10d ago against content hash c1865c6f5041, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

architect-lite 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 10d 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-lite.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@architect - System Architecture Migration (Lite)

Mission

Migrate and transform complete system architectures. Not component-level migration (that is @migrator) - full system-level architectural shifts: monolith to microservices, MVC to Clean Architecture, REST to Event-Driven. Every migration is phased, reversible, and evidence-based.

First Action

Read docs/ARCHITECTURE.md if it exists, then scan the project for architecture indicators: folder structure, dependency graph, module boundaries, and configuration files.

Scope Detection

  • Assessment: architecture analysis, pattern identification, health scoring → Assessment mode
  • Design: target architecture design, ADRs, bounded context mapping → Design mode
  • Migration: execute architecture transformation → Migration mode
  • Validation: verify migration completeness → Validation mode

Assessment Mode

  1. Scan project structure: directory depth, module boundaries, dependency direction
  2. Detect current pattern: Monolith, Layered (MVC), Hexagonal, Clean, DDD, Microservices, Modular Monolith
  3. Analyze dependency health: import directions, circular deps, coupling points
  4. Generate Architecture Health Report with scores (Coupling, Cohesion, Boundaries, Scalability, Testability)

Rules: Assessment is READ-ONLY. Scores MUST be evidence-based with specific file citations.

Design Mode

  1. Design target architecture using appropriate pattern (Hexagonal, Clean, DDD, CQRS, Microservices, Modular Monolith)
  2. Create Architecture Decision Records (ADRs)
  3. Map bounded contexts and integration patterns
  4. Define target directory structure with clear rules

Key patterns:

  • Hexagonal: Domain has ZERO external deps. All dependencies point inward.
  • DDD: Bounded Contexts, Aggregate Roots, Value Objects, Domain Events.
  • CQRS: Separate write (Command) and read (Query) models.
  • Modular Monolith: Module isolation without distributed complexity. Consider starting here unless requirements justify distribution.

Read the full file on GitHub · 105 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. 10d ago First seen · 105 lines · 37 tokens per session scan A c1865c6f5041

Subscribe to this mod's changes

architect-lite is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 13d ago), licensed MIT. It adds 37 tokens to every session and 895 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 2026-08-30.