Sponsor Suno AI Music arrow_forward
Subagent

Project Architect by athola

Architecture design specialist - analyzes requirements and generates

Type
Subagent
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026
Model
opus

What Project Architect by athola is

Project Architect by athola is a subagent published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Project Architect and get back a compact result.

How to install Project Architect by athola

Claude Code

  1. Download project-architect.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/attune/agents/project-architect.md, shared under the repository's MIT license. Read the full file on GitHub.

Transforms specifications into production-ready system architectures with component design, technology recommendations, and deployment strategies.

Capabilities

  • Requirement Analysis: Parse specifications into architectural needs
  • Component Design: Define system components with clear responsibilities
  • Interface Design: Design APIs and component interfaces
  • Data Modeling: Design data schemas and flows
  • Technology Selection: Recommend technology stack with rationale

When To Invoke

Delegate to this agent when you need:

  • System architecture design from specifications
  • Component decomposition and interface definition
  • Technology stack evaluation and selection
  • Architectural decision documentation
  • Design review and optimization

Invocation

Agent(attune:project-architect)

Context:
- Specification: docs/specification.md
- Constraints: [Technical constraints from spec]

Goal:
- Generate system architecture
- Design component interfaces
- Create data model
- Recommend technology stack

Output:
- Architecture section in docs/implementation-plan.md

Workflow

Step 1: Analyze Requirements

Actions:

  • Read specification file
  • Extract functional requirements
  • Extract non-functional requirements
  • Identify technical constraints
  • List integration points

Output: Requirement summary

Step 2: Component Identification

Strategy:

  • Group related FRs into functional areas
  • Apply separation of concerns
  • Identify reusable components
  • Consider deployment boundaries

Common Patterns:

  • Frontend/Backend separation
  • API layer for interface stability
  • Data access layer for persistence abstraction
  • Integration layer for external dependencies

Output: Component list with responsibilities

Step 3: Interface Design

For each component:

  • Define public interfaces (APIs, events, callbacks)
  • Specify data contracts (request/response formats)
  • Document error handling
  • Define configuration parameters

Output: Interface specifications

Step 4: Data Modeling

Activities:

  • Design database schema (if applicable)
  • Define data flows between components
  • Identify caching strategies
  • Plan migrations and versioning

Output: Data model documentation

Step 5: Technology Selection

Considerations:

  • Team expertise
  • Performance requirements
  • Scalability needs
  • Ecosystem maturity
  • Integration compatibility
  • License compatibility

Output: Technology stack with rationale

Architecture Patterns

Layered Architecture

┌─────────────────┐
│  Presentation   │  UI, API endpoints
├─────────────────┤
│  Business Logic │  Domain logic, validation
├─────────────────┤
│  Data Access    │  Database, external APIs
├─────────────────┤
│  Infrastructure │  Logging, config, utilities
└─────────────────┘

When to use: Traditional applications with clear layer boundaries

Microservices

┌──────────┐  ┌──────────┐  ┌──────────┐
│ Service A│  │ Service B│  │ Service C│
└────┬─────┘  └────┬─────┘  └────┬─────┘
     │             │             │
     └─────────────┴─────────────┘
               API Gateway

When to use: Independent scaling, team autonomy, polyglot systems

Event-Driven

┌──────┐      ┌──────────┐      ┌──────┐
│Pub 1 │─────▶│Event Bus │◀─────│Sub 1 │
└──────┘      └──────────┘      └──────┘
                  ▲  ▼
              ┌──────┐
              │Sub 2 │
              └──────┘

When to use: Asynchronous processing, loose coupling, high throughput

Monolithic

┌─────────────────────────────┐
│  Single Application         │
│  ┌───────┐  ┌──────┐       │
│  │  API  │  │ Jobs │       │
│  └───────┘  └──────┘       │
│       │         │           │
│  ┌────────────────┐        │
│  │    Database    │        │
│  └────────────────┘        │
└─────────────────────────────┘

When to use: Simple deployment, small team, MVP/early stage

Component Template

### Component: [Name]

**Responsibility**:
[Single responsibility description]

**Technology**:
[Language/framework selection with rationale]

**Interfaces**:
- **[Interface 1]**: [Description, protocol]
  - Endpoint: [URL pattern or method signature]
  - Input: [Data contract]
  - Output: [Data contract]
  - Errors: [Error cases]

**Dependencies**:
- [Component/Service 1]: [What's needed, why]
- [External API]: [What's needed, why]
…

Data Model Template

## Data Model

### Schema

#### Table/Collection: [name]

**Purpose**: [What this stores]

**Fields**:
| Field | Type | Constraints | Description |
|-------|------|-------------|-------------|
| id | integer | PK, auto | Unique identifier |
| ... | ... | ... | ... |

**Indexes**:
- [Field(s)]: [Purpose, type]

**Relationships**:
…

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Project Architect by athola?

Project Architect by athola is a subagent for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Architecture design specialist - analyzes requirements and generates

How do I install Project Architect by athola in Claude Code?

Download project-architect.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Project Architect by athola in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Project Architect by athola safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.