architecture-reviewer

architecture-reviewer is an agent for Claude Code from carinyadigital/skills. It costs 61 tokens per session (684 once invoked), scanned A, original, MIT.

An architecture-review agent checks whether code changes fit the project’s existing structure and dependency patterns. Software architecture is how a codebase divides responsibilities and connects its parts.

In plain words
What is it for?
Use it when a change adds modules, layers, external calls, data paths, or state management. It compares the diff with architecture documents, project guidelines, and nearby code.
Why use it?
It finds misplaced responsibilities, unwanted boundary crossings, inconsistent module patterns, and dependencies that point in the wrong direction.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions AGENTS.md.

Part of the carinyaparc-agent-skills plugin — 24 skills, 13 agents shipped together

Good fit Use it when a change adds modules, layers, external calls, data paths, or state management. It compares the diff with architecture documents, project guidelines, and nearby code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/carinyadigital/skills/architecture-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/carinyadigital/skills

Made for: Claude Code.

Or install carinyaparc-agent-skills, the plugin that ships this one along with the rest of its 24 skills, 13 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 architecture-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/carinyadigital/skills/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/architecture-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 684 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 $0.00061 $0.00684
Opus 5 $0.00030 $0.00342
Sonnet 5 $0.00012 $0.00137
Haiku 4.5 $0.00006 $0.00068

Measured 11d ago against content hash 292ee9ffed56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

architecture-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 11d 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.

skills/code-review/agents/architecture-reviewer.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You check whether new code conforms to the codebase's architecture patterns — not generic architecture theory.

When to invoke

  • New module or boundary crossing — diff adds files, layers, or cross-component dependencies.
  • Structural change — new external calls, data-access paths, or state management.

Process

  1. Discover the intended architecture, in this order (treat each as a candidate to glob for — none is guaranteed to exist): a. Architecture docs and ADRs: **/solution.md, ARCHITECTURE.md, docs/architecture/**, **/decisions/**, **/adr/**, ADR-*.md. b. Contributing guidelines (CONTRIBUTING.md, AGENTS.md, CLAUDE.md). c. De-facto patterns: infer directory/layering conventions and dependency direction from neighbouring modules.
  2. Compare the diff against those patterns:
    • Layering and dependency direction (does inner depend on outer? domain importing infra?).
    • Module boundaries and cohesion (does the change fit where it lives, or leak concerns?).
    • Consistency with sibling modules (naming, file placement, wiring, DI vs direct construction).
    • New anti-patterns (god object, circular dependency, hardcoded config/secrets, missing abstraction for external services).
  3. Distinguish a genuine pattern violation from an acceptable local variation.

Budget

At most 20 files beyond the diff — the highest budget of any lens, because judging conformance requires reading the siblings the change should match. Spend it on representative examples, not exhaustive coverage.

Scoring

Classify each divergence with a Category, Severity, and a Confidence prior per ../references/finding-classification.md. Default category: Maintainability; use Data Integrity where the divergence concerns persistence or contract boundaries. Your confidence is a prior; finding-verifier rates it independently afterwards.

Cite the pattern source (architecture doc section, ADR, or the sibling file it should match). An uncited pattern claim is your own preference, not the codebase's architecture. Drop only Speculative findings; return the rest.

Read the full file on GitHub · 63 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. 11d ago First seen · 63 lines · 61 tokens per session scan A 292ee9ffed56

Subscribe to this mod's changes

architecture-reviewer is an agent published in the GitHub repository carinyadigital/skills (2 stars, last pushed 22d ago), licensed MIT. It adds 61 tokens to every session and 684 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

team-reviewer

Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.

wshobson/agents · 43 tokens

code-documentation-code-reviewer

Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.

wshobson/agents · 60 tokens

comprehensive-review-architect-review

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

wshobson/agents · 55 tokens

backend-development-security-auditor

Review code and architecture for security vulnerabilities, OWASP Top 10, auth flaws, and compliance issues. Use for security review during feature development.

wshobson/agents · 36 tokens

hive-reviewer

Honey hive subagent. Reviews a diff or file set for correctness bugs, over-engineering, and over-verbosity, then returns the findings to the orchestrator as a compact, id-keyed handoff (Honey Lever 3) — data, not human prose. Use when the orchestrator delegates a review and will machine-read the result. Read-only…

Green-PT/honey-for-devs · 81 tokens

reviewer

Reviews a completed task's implementation for correctness, security, and spec adherence. Returns a PASS/NEEDSCHANGES/REJECT verdict.

codecast-sh/codecast · 31 tokens