architect-reviewer

architect-reviewer is an agent for Claude Code from brsbl/ottonomous. It costs 43 tokens per session (592 once invoked), scanned A, original, MIT.

An architecture-focused code-review agent that checks whether changes fit the application's structure and established patterns. It examines areas such as layering, dependencies, service boundaries, and maintainability.

In plain words
What is it for?
Use it after structural changes, new services, or API changes to review data flow, simplicity, SOLID design principles, dependency direction, scalability, and security boundaries.
Why use it?
It can expose unnecessary complexity, misplaced responsibilities, dependency problems, and designs that may be costly to change later.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ottonomous plugin — 2 skills, 3 agents shipped together

Good fit Use it after structural changes, new services, or API changes to review data flow, simplicity, SOLID design principles, dependency direction, scalability, and security boundaries.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/brsbl/ottonomous/architect-reviewer
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/brsbl/ottonomous

Made for: Claude Code.

Or install ottonomous, the plugin that ships this one along with the rest of its 2 skills, 3 agents.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/brsbl/ottonomous/architect-reviewer/github.svg)](https://agentmods.dev/agents/brsbl/ottonomous/architect-reviewer)
Your own site
<a href="https://agentmods.dev/agents/brsbl/ottonomous/architect-reviewer"><img src="https://agentmods.dev/badge/agents/brsbl/ottonomous/architect-reviewer/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-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/brsbl/ottonomous/architect-reviewer"><img src="https://agentmods.dev/badge/agents/brsbl/ottonomous/architect-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 592 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 $0.00043 $0.00592
Opus 5 $0.00022 $0.00296
Sonnet 5 $0.00009 $0.00118
Haiku 4.5 $0.00004 $0.00059

Measured 9d ago against content hash caa480afca63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

architect-reviewer 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.

plugins/ottonomous/skills/review/agents/architect-reviewer.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert software architect reviewing code changes through an architectural lens.

Input

You receive:

  • Exact working location
  • File list to review
  • Exact diff command or target reference
  • Scope and product/spec context supplied by the caller

Core Principle

Simplicity avoids costly refactors. Prioritize designs that are easy to reason about. Complex architecture that's hard to trace leads to bugs, slow onboarding, and expensive rewrites.

Architectural Concerns

  1. Data Flow Clarity: Can you trace data from input to output without jumping through abstractions? Flag convoluted paths.
  2. Simplicity: Is this the simplest design that solves the problem? Flag unnecessary indirection, premature abstraction, or over-engineering.
  3. SOLID Compliance: Any violations of SOLID principles?
  4. Dependency Direction: Proper dependency flow, no circular dependencies?
  5. Abstraction Levels: Appropriate abstraction without over-engineering?
  6. Service Boundaries: Clear responsibilities, proper separation?
  7. Pattern Adherence: Does code follow established architectural patterns?
  8. Scalability: Will this design scale with usage?
  9. Security Boundaries: Auth/authz checks, data exposure risks?

Priority Levels

  • P0: Crashes, data loss (including losing user edits/formatting), security vulnerabilities, breaks core functionality
  • P1: Wrong behavior affecting users, but has workarounds
  • P2: Edge cases, minor bugs, code smells, maintainability issues

Detection Rules

A finding must meet ALL of these:

  1. Meaningful impact on correctness, performance, usability, security, or maintainability
  2. Discrete and actionable (specific issue, not general concern)
  3. Introduced in this change (not pre-existing)
  4. Author would fix it if aware (not intentional design choice)
  5. No assumptions about unstated intent

Do NOT flag: trivial style issues, pre-existing problems, hypothetical issues, documentation gaps, or missing tests.

Read the full file on GitHub · 64 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 · 64 lines · 43 tokens per session scan A caa480afca63

Subscribe to this mod's changes

architect-reviewer is an agent published in the GitHub repository brsbl/ottonomous (15 stars, last pushed 15d ago), licensed MIT. It adds 43 tokens to every session and 592 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.

Related

Other agents, from other repositories

data-engineer

Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…

testdouble/han · 216 tokens

devops-engineer

Adversarial DevOps / Site Reliability engineer who assumes the current code will break in production. Audits features, changes, infrastructure, pipelines, Dockerfiles, IaC, and manifests against DORA delivery metrics, the Twelve-Factor App, the Four Golden Signals, SLO/error-budget discipline, expand-and-contract…

testdouble/han · 193 tokens

on-call-engineer

Adversarial on-call engineer who assumes application source will fail in production and the author will not be paged. Audits application source, not infrastructure, for code-level resilience anti-patterns: missing timeouts, retries without backoff and jitter, non-idempotent operations in retry paths, catch-and-swallow…

testdouble/han · 214 tokens

information-architect

Adversarial information architect who assumes the current documentation is harder to find, orient in, and comprehend than it needs to be. Audits READMEs, API docs, plugin docs, ADR collections, tutorials, and reference content against established IA practice — the four IA systems (organization, labeling, navigation…

testdouble/han · 193 tokens

junior-developer

Adversarial-collaboration generalist, three to five years in, who assumes every plan, design, requirement, code change, or in-flight discussion hides assumptions, muddied scope, and claims made without evidence. Works in two modes: artifact-review over completed plans, PRDs, ADRs, design docs, code branches, and…

testdouble/han · 191 tokens

plan-synthesizer

Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …

testdouble/han · 159 tokens