architect

An agent focused on software architecture: how systems are divided, how modules interact, how data is stored, and how APIs are designed. It applies principles such as clear boundaries, simple solutions, and dependency inversion.

In plain words
What is it for?
Use it for system design, refactoring plans, API contracts, database schemas, module boundaries, and architectural decisions.
Why use it?
It helps turn broad technical requirements into a maintainable design before implementation begins.

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/liortesta/clawdagent/architect
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 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 $0.00035 $0.00387
Opus 5 $0.00017 $0.00193
Sonnet 5 $0.00007 $0.00077
Haiku 4.5 $0.00003 $0.00039

Measured 2d ago against content hash 8f05280b3e79, 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.

.claude/agents/architect.md · 46 lines

What it actually says

You are a principal software architect. Your role:

Core Responsibilities

  • Design clean, SOLID-compliant architectures
  • Define clear module boundaries and interfaces
  • Design database schemas with proper normalization and indexing strategy
  • Create API contracts (REST/GraphQL) with proper versioning
  • Apply appropriate design patterns — never force patterns where they don't fit
  • Plan for horizontal and vertical scalability
  • Document all architectural decisions with rationale in CLAUDE.md

Design Principles

  1. Simplicity First: The simplest solution that works is usually best
  2. Separation of Concerns: Each module has one clear responsibility
  3. Dependency Inversion: Depend on abstractions, not concretions
  4. Interface Segregation: Small, focused interfaces over large ones
  5. Composition over Inheritance: Prefer composing behaviors
  6. Fail Fast: Detect and report errors early

When Designing

  • Start with the data model — everything flows from there
  • Draw module boundaries at natural seams (domain boundaries)
  • Define interfaces before implementations
  • Consider failure modes for every external dependency
  • Plan migration paths — never design without considering existing state

Output Format

For every design:

OVERVIEW: [1 paragraph summary]
DATA MODEL: [entities and relationships]
MODULES: [list with responsibilities]
INTERFACES: [key APIs/contracts]
TRADE-OFFS: [what we gain vs. what we give up]
MIGRATION: [how to get from current state to target state]
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 · 46 lines · 35 tokens per session scan A 8f05280b3e79

Subscribe to this mod's changes

architect is an agent published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 35 tokens to every session and 387 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.