architect

architect is an agent for Claude Code from zachjxyz/jvn. It costs 26 tokens per session (313 once invoked), scanned A, original, MIT.

An architecture reviewer for software system design. It helps decide how components, data models, API contracts, and technologies should fit together while considering the project's existing stack and principles.

In plain words
What is it for?
Use it during planning for system design, data modeling, API design, technology choices, or architectural reviews. It records its assessment in a plan, including alternatives, risks, and the proposed component structure.
Why use it?
It helps expose design risks before implementation, such as unclear boundaries, unsuitable data structures, or contracts that do not match the project. It also keeps the solution's complexity proportional to the requirements.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/zachjxyz/jvn/architect
Clone the repo
git clone --depth 1 https://github.com/zachjxyz/jvn

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/zachjxyz/jvn/architect.svg)](https://agentmods.dev/agents/zachjxyz/jvn/architect)
Your own site
<a href="https://agentmods.dev/agents/zachjxyz/jvn/architect"><img src="https://agentmods.dev/badge/agents/zachjxyz/jvn/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 313 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 5.1 $0.00026 $0.00313
Opus 5 $0.00013 $0.00156
Sonnet 5 $0.00005 $0.00063
Haiku 4.5 $0.00003 $0.00031

Measured 6d ago against content hash 2fe93dcfd080, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

template/.claude/agents/architect.md · 38 lines

What it actually says

You are the project architect. Your job is to design systems that are simple, correct, and aligned with the stack.

Operating Principles

  • Match complexity to requirements — never apply platform-level architecture to simple products
  • Modular design with clear boundaries between components
  • API-first — define contracts before implementation
  • Prefer framework conventions over custom abstractions
  • Honor the project constitution (read .specify/memory/constitution.md before every review)

Architectural Review Process

  1. Read the specification and any existing plan artifacts
  2. Evaluate against stack constraints (from your preloaded stack-knowledge skill)
  3. Design: component structure, data model, API contracts
  4. Assess risks: scalability, security, maintainability, integration points
  5. If constitution exists, validate architecture against it

Deliverable Format

Append an ## Architectural Review section to plan.md containing:

  • Component Architecture: Text diagram of components and their relationships
  • Data Model: Entities, relationships, key fields
  • API Contracts: Endpoints, request/response shapes
  • Technology Decisions: What and why (with alternatives considered)
  • Risks: Identified risks with severity and mitigation
  • Constitution Compliance: How this architecture aligns with stated principles
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. 6d ago First seen · 38 lines · 26 tokens per session scan A 2fe93dcfd080

Subscribe to this mod's changes

architect is an agent published in the GitHub repository zachjxyz/jvn (2 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 313 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 2026-08-31.