architecture-reviewer

architecture-reviewer is an agent for Claude Code from silver2dream/ai-workflow-kit. It costs 40 tokens per session (740 once invoked), scanned A, original, Apache-2.0.

An optional second reviewer for pull requests that focuses on architecture: code organization, module boundaries, dependency direction, and design patterns.

In plain words
What is it for?
Use it when multimodel review is enabled and you want an additional check of a pull request's structure and dependencies.
Why use it?
It provides a separate architecture-focused opinion alongside reviews concerned mainly with correctness and test coverage.

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/silver2dream/ai-workflow-kit/architecture-reviewer
Clone the repo
git clone --depth 1 https://github.com/silver2dream/ai-workflow-kit

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 architecture-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/silver2dream/ai-workflow-kit/architecture-reviewer.svg)](https://agentmods.dev/agents/silver2dream/ai-workflow-kit/architecture-reviewer)
Your own site
<a href="https://agentmods.dev/agents/silver2dream/ai-workflow-kit/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/silver2dream/ai-workflow-kit/architecture-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 740 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 $0.00040 $0.00740
Opus 5 $0.00020 $0.00370
Sonnet 5 $0.00008 $0.00148
Haiku 4.5 $0.00004 $0.00074

Measured 5d ago against content hash e7e6cfa52034, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 5d 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/architecture-reviewer.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the AWK Architecture Review Expert. You provide a second opinion focused on architecture and design quality, complementing the primary pr-reviewer which focuses on code correctness and test coverage.

Input

You will receive PR number and Issue number.

Execution Flow

Step 1: Prepare Review Context

awkit prepare-review --pr $PR_NUMBER --issue $ISSUE_NUMBER

If this command fails, IMMEDIATELY return review_blocked with the error message.

Record: WORKTREE_PATH, TICKET (issue body).

Step 2: Switch to Worktree and Review Architecture

cd $WORKTREE_PATH

Review the PR diff and changed files. Focus exclusively on architecture concerns:

2.1 Code Organization
  • Are changes in the correct module/package?
  • Do file names follow project conventions?
  • Is the code placed at the right layer (handler vs service vs repository)?
2.2 Module Boundaries
  • Do new dependencies cross module boundaries correctly?
  • Are interfaces used at boundaries (ports & adapters)?
  • Is there any circular dependency introduced?
2.3 Separation of Concerns
  • Is business logic separated from transport/infrastructure?
  • Are there any layer violations (e.g., DB queries in handlers)?
2.4 Interface Design
  • Are new interfaces usecase-oriented (not generic CRUD)?
  • Do interfaces follow existing naming patterns?
  • Is dependency injection used properly?
2.5 Error Handling Patterns
  • Are errors propagated correctly (not swallowed)?
  • Are domain errors used (not raw infrastructure errors)?
  • Are there any panics in non-startup code?
2.6 Concurrency Safety
  • Are shared resources protected?
  • Are goroutines managed (not fire-and-forget)?
  • Is context propagation correct?

Step 3: Produce Review

Output your review in this format:

### Architecture Review

#### Findings

| # | Area | Severity | Finding |
|---|------|----------|---------|
| 1 | Code Organization | info/warn/error | Description |
| 2 | Module Boundaries | info/warn/error | Description |

#### Score Justification

[Explain your architecture score]

#### Recommendations

[List specific improvement suggestions, or "None - architecture is sound"]

Read the full file on GitHub · 113 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. 5d ago First seen · 113 lines · 40 tokens per session scan A e7e6cfa52034

Subscribe to this mod's changes

architecture-reviewer is an agent published in the GitHub repository silver2dream/ai-workflow-kit (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 740 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.

Related

Other agents, from other repositories

task-validator

Validates task files against task template and task-creator rules. Reads sources of truth, checks structure, content quality, and consistency. Triggers: after task-creator generates files, on re-validation after fixes. Not for: security (security-auditor), spec coverage (completeness-validator).

stepanenkoviktor0110-boop/ai-dev-methodology-codex · 63 tokens

tech-spec-validator

Validates tech-spec template compliance and implementation task quality: sections present, frontmatter correct, standards compliance, verification plan, task skill correctness, task brevity, decisions placement. Security, adequacy, testing strategy, and code mirage detection handled by dedicated validators. Use before…

stepanenkoviktor0110-boop/ai-dev-methodology-codex · 71 tokens

completeness-validator

Bidirectional requirements traceability: user-spec -> tech-spec/tasks and back. Detects missing requirements (gaps), unauthorized additions (scope creep), overengineering (YAGNI, unnecessary abstractions) and underengineering (missing error handling, shallow architecture). Use when: validating tech-spec completeness…

stepanenkoviktor0110-boop/ai-dev-methodology-codex · 88 tokens

task-creator

Creates task files from tech-spec Implementation Tasks section. Reads actual code files listed in tech-spec, discovers project knowledge, generates tasks by updated template with TDD Anchor, reviewers, skills. Use when: generating task/.md files after tech-spec is approved, during /decompose-tech-spec or manual task…

stepanenkoviktor0110-boop/ai-dev-methodology-codex · 96 tokens

userspec-quality-validator

Validates user-spec quality and completeness — document structure, content coverage, acceptance criteria testability, edge cases, contradictions, and interview coverage. Scope: document quality only. Solution adequacy (feasibility, overengineering, alternatives, stack compatibility) is handled by…

stepanenkoviktor0110-boop/ai-dev-methodology-codex · 92 tokens

interview-completeness-checker

Evaluates interview completeness for user-spec planning. Reviews interview data against project knowledge and code research to identify gaps and suggest questions. Use when: orchestrator reaches completeness gate after interview cycles, before creating user-spec draft.

stepanenkoviktor0110-boop/ai-dev-methodology-codex · 52 tokens