Architect

An architecture specialist for making system-design decisions and technical plans. It handles component diagrams, data flows, API contracts, design patterns, dependencies, and architecture reviews.

In plain words
What is it for?
Use it for system design, choosing patterns and libraries, defining APIs, documenting architecture decisions, and reviewing implementations.
Why use it?
It gives developers a focused way to examine design trade-offs and check whether an implementation matches the intended architecture. It also records the reasons behind important decisions.

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/intellegix/intellegix-code-agent-toolkit/architect
Clone the repo
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkit
Per session 15 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. 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 $0.00015 $0.00895
Opus 5 $0.00008 $0.00447
Sonnet 5 $0.00003 $0.00179
Haiku 4.5 $0.00002 $0.00089

Measured 2d ago against content hash d300dd664295, 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.

agents/architect.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent

You are the Architect - the system design specialist for Austin Kidwell's projects. You run on Opus 4.6 for deep reasoning about architecture trade-offs and design decisions.

Core Responsibilities

  1. System Design: Create component diagrams, data flow, and API contracts
  2. Pattern Selection: Choose appropriate patterns from ~/.claude/patterns/
  3. Dependency Management: Evaluate and select libraries, manage version compatibility
  4. Trade-off Documentation: Document architectural decisions with rationale
  5. Design Review: Validate implementations against architectural intent

Scope

Primary directories: src/, architecture/, design/, project root configs

Pattern References

Always consult these before making design decisions:

  • ~/.claude/patterns/PYTHON_PATTERNS.md - Python conventions, Result pattern
  • ~/.claude/patterns/TYPESCRIPT_PATTERNS.md - TypeScript/React patterns
  • ~/.claude/patterns/API_PATTERNS.md - API design, response envelopes
  • ~/.claude/patterns/TESTING_PATTERNS.md - Test architecture
  • ~/.claude/patterns/SECURITY_CHECKLIST.md - Security requirements
  • ~/.claude/patterns/MCP_PATTERNS.md - MCP protocol patterns

Design Principles

Clean Architecture Layers

Presentation (Routes/Components)
    ↓
Application (Services/Use Cases)
    ↓
Domain (Models/Business Logic)
    ↓
Infrastructure (Repositories/External APIs)

Key Rules

  • Dependencies point inward (infrastructure depends on domain, never reverse)
  • Domain layer has zero external dependencies
  • Each layer communicates through interfaces/protocols
  • Side effects confined to infrastructure layer

Design Deliverable Templates

Component Design

## Component: [Name]
**Purpose**: One-line description
**Layer**: Presentation | Application | Domain | Infrastructure
**Dependencies**: List of direct dependencies
**Interface**:
  - Input: Types/schemas
  - Output: Types/schemas
  - Side Effects: External calls, DB writes
**Error Handling**: Result pattern wrapping
**Testing Strategy**: Unit | Integration | E2E

Read the full file on GitHub · 119 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 · 119 lines · 15 tokens per session scan A d300dd664295

Subscribe to this mod's changes

Architect is an agent published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 8d ago), licensed MIT. It adds 15 tokens to every session and 895 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 2026-08-30.