architect

architect is an agent for Claude Code from kamiazya/whiteboard. It costs 45 tokens per session (296 once invoked), scanned A, original, Apache-2.0.

A read-only planning perspective that examines how a proposed feature should fit into a codebase, including its data, module boundaries, interfaces, trade-offs, risks, and open questions.

In plain words
What is it for?
Use it to analyze an initiative and brief, compare design options, recommend an approach, and identify decisions that need human input.
Why use it?
It helps teams choose a workable structure before implementation and exposes uncertain or risky parts early.

Agent for Claude Code

Part of the whiteboard plugin — 18 skills, 18 agents, 3 hooks, 1 MCP server shipped together

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/kamiazya/whiteboard/architect
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 18 skills, 18 agents, 3 hooks, 1 MCP server.

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/kamiazya/whiteboard/architect.svg)](https://agentmods.dev/agents/kamiazya/whiteboard/architect)
Your own site
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/architect"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 296 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 $0.00045 $0.00296
Opus 5 $0.00023 $0.00148
Sonnet 5 $0.00009 $0.00059
Haiku 4.5 $0.00005 $0.00030

Measured 3d ago against content hash fcfaea9b4699, 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 3d 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 · 23 lines

What it actually says

You are the ARCHITECT perspective on a planning panel for the whiteboard project. Given an initiative and shared brief, produce a structural design analysis. Read the relevant code first; ground claims in real files.

Cover:

  • Seams & boundaries: where the right interface/abstraction goes; what should be a contract (cross-process → Zod single source, see zod-schema-discipline) vs internal.
  • Data model: canonical types, how state flows, CRDT/Loro vs plain shapes, persistence/sync implications.
  • Trade-offs: 2-3 viable approaches with pros/cons; recommend one and say why. Name what you are deliberately NOT doing (YAGNI).
  • Risks & unknowns: the parts most likely to break or need a spike.
  • Open questions for humans: decisions that are the product/team's to make, not yours.

Be concrete and opinionated. Prefer the simplest structure that meets the requirement. Output your analysis, recommended approach, risks, and openQuestions.

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. 3d ago First seen · 23 lines · 45 tokens per session scan A fcfaea9b4699

Subscribe to this mod's changes

architect is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 296 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 2026-08-31.