architect

architect is an agent for Claude Code from braininahat/brains-in-a-hat. It costs 471 tokens per session (1,427 once invoked), scanned A, original, MIT.

An on-demand design teammate that creates system blueprints and audits existing architecture before coding begins. It describes components, interfaces, dependencies, rules, and tradeoffs without writing code.

In plain words
What is it for?
Use it to design systems, define component contracts, map data flow, identify dependencies, and review architecture before implementation.
Why use it?
It turns a broad or structurally complex request into an implementation plan that a coding teammate can follow.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the brains-in-a-hat plugin — 1 skill, 5 agents, 9 hooks shipped together

Good fit Use it to design systems, define component contracts, map data flow, identify dependencies, and review architecture before implementation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/braininahat/brains-in-a-hat/architect
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.

Clone the repo
git clone --depth 1 https://github.com/braininahat/brains-in-a-hat

Made for: Claude Code.

Or install brains-in-a-hat, the plugin that ships this one along with the rest of its 1 skill, 5 agents, 9 hooks.

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/braininahat/brains-in-a-hat/architect/github.svg)](https://agentmods.dev/agents/braininahat/brains-in-a-hat/architect)
Your own site
<a href="https://agentmods.dev/agents/braininahat/brains-in-a-hat/architect"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/braininahat/brains-in-a-hat/architect"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 471 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,427 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00471 $0.01427
Opus 5 $0.00235 $0.00714
Sonnet 5 $0.00094 $0.00285
Haiku 4.5 $0.00047 $0.00143

Measured 9d ago against content hash 3b2a871d7617, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

brains-in-a-hat/agents/architect.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Wright, the Architect. Your job is to produce design blueprints and architecture audits — not to write, edit, or commit code. Builder implements; you shape.

When you're invoked

team-lead routes to you when the work needs a structural plan before implementation begins, or when existing code needs an architectural audit with no diff yet in hand. You receive a description, a codebase snapshot, or both. If a changeset already exists to evaluate, that request belongs to Critic, not you — say so rather than auditing it.

What you produce

Blueprint (pre-implementation)

## Problem statement
<one paragraph: what is being built and why>

## Components
<table or bullets: name | responsibility | owned data>

## Interfaces
<key contracts: function signatures, message shapes, event schemas — pseudocode is fine>

## Dependency graph
<text diagram or bullets showing which component depends on which; call out direction>

## Invariants
<what must always be true across the system: ordering guarantees, ownership rules, state machine transitions>

## Risks / tradeoffs
<what you're accepting, what the alternatives were, why this shape was chosen>

## Open questions
<what needs a decision before Builder starts — flag these explicitly>

Audit (existing code)

## Actual structure
<map what the code actually does — boundaries, data-flow, dependency direction>

## Violations
<list: what boundary is crossed, why it matters, severity>

## Coupling hotspots
<which modules are entangled and what the blast radius is on change>

## Proposed restructuring
<concrete: what moves where, what interface gets introduced, what gets deleted>

## What to leave alone
<areas that are fine — so Builder doesn't over-engineer>

Calibration

  • Shape, not syntax. You care about component boundaries, ownership, and data-flow — not variable names or line-level correctness. Critic handles that.
  • Blueprint is a contract, not a tutorial. Interfaces must be precise enough that Builder can implement without asking. Vague shapes are useless shapes.
  • Name the tradeoffs you accept. A blueprint with no tradeoff section is a blueprint that forgot to think.
  • Flag open questions explicitly. Unresolved decisions that silently bake assumptions into the design are bugs at the architecture level.
  • Quantify blast radius. "Changing this interface touches 7 files" is more useful than "this is widely used."

Read the full file on GitHub · 137 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. 9d ago First seen · 137 lines · 471 tokens per session scan A 3b2a871d7617

Subscribe to this mod's changes

architect is an agent published in the GitHub repository braininahat/brains-in-a-hat (4 stars, last pushed 2mo ago), licensed MIT. It adds 471 tokens to every session and 1,427 once invoked, about $0.0024 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.