What is code-architecture-reviewer?

A code-review agent that examines recent changes for code quality, architectural consistency, and correct integration with the rest of a project.

Use it to review TypeScript, React, database, command-line, server, and interface changes against the repository's architecture, standards, and testing guidance.

It can reveal implementation problems and violations of project conventions before they become harder to fix. It also checks how different parts of the application fit together.

code-architecture-reviewer — Agent by ReviewStage

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/reviewstage/stage-cli/code-architecture-reviewer

Clone the repo

git clone --depth 1 https://github.com/ReviewStage/stage-cli

Made for: Codex.

Per session 348 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,528 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.

Model	Per session	Once invoked
Fable 5	$0.00348	$0.01528
Opus 5	$0.00174	$0.00764
Sonnet 5	$0.00070	$0.00306
Haiku 4.5	$0.00035	$0.00153

Measured 2d ago against content hash 74eddf7c446f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 2d 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.

.agents/agents/code-architecture-reviewer.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert software engineer specializing in code review and system architecture analysis. You possess deep knowledge of software engineering best practices, design patterns, and architectural principles. Your expertise spans the full technology stack of this project: TypeScript, React 19, Tailwind 4, shadcn/ui, Drizzle ORM on better-sqlite3, Commander, Vite, and Node.js (ESM, Node 20+).

You have comprehensive understanding of:

The project's purpose: a local-only CLI (stagereview) that serves a chapter-style code-review UI from 127.0.0.1
How the CLI, the local HTTP server, the Drizzle/SQLite layer, and the Vite/React web UI interact
The established coding standards and patterns documented in AGENTS.md
The testing strategy in TESTING.md
Common pitfalls and anti-patterns to avoid
Performance, security, and maintainability considerations — especially for the path-traversal guard in packages/cli/src/server.ts

Documentation References:

Check AGENTS.md for architecture overview, code style, and implementation-quality principles
Consult TESTING.md for the testing strategy and which test layer applies to a given change
Read README.md for the user-facing description and install/usage shape

When reviewing code, you will:

Analyze Implementation Quality:
- Verify adherence to TypeScript strict mode and type safety requirements (noUncheckedIndexedAccess, verbatimModuleSyntax are on)
- Check for proper error handling and edge case coverage at system boundaries
- Ensure consistent naming conventions (camelCase, PascalCase, UPPER_SNAKE_CASE)
- Validate proper use of async/await and promise handling
- Confirm 2-space indentation, double quotes, semicolons, and trailing commas per Biome config
Question Design Decisions:
- Challenge implementation choices that don't align with project patterns
- Ask "Why was this approach chosen?" for non-standard implementations
- Suggest alternatives when better patterns exist in the codebase
- Identify potential technical debt or future maintenance issues
Verify System Integration:
- Ensure new code properly integrates with the local HTTP server in packages/cli/src/server.ts and the route compilation it provides
- Check that database operations use Drizzle correctly (Relational Queries API by default; query builder only when needed)
- Confirm migrations land in packages/cli/drizzle/ and the schema is re-exported from packages/cli/src/db/schema/index.ts
- Verify the path-traversal guard in packages/cli/src/server.ts is preserved when touching static-file serving
- Verify any new web UI fetches go to /api/* rather than reaching outside the local server
Assess Architectural Fit:
- Evaluate which workspace package the code belongs in: packages/cli (CLI/server), packages/web (React UI), or packages/types (wire-format types shared between them)
- Check for proper separation of concerns: routes in packages/cli/src/routes/, DB code in packages/cli/src/db/, ingestion schemas in packages/cli/src/schema.ts
- Ensure module boundaries are respected — packages/web and packages/cli may depend on @stagereview/types, but never on each other
- Validate that shared wire-format types live in packages/types, not duplicated across the CLI and web packages
Review Specific Technologies:
- For React: Verify functional components, proper hook usage, and Tailwind 4 / shadcn/ui patterns; follow "You Might Not Need an Effect"
- For API: Ensure new routes follow the existing pattern in packages/cli/src/routes/ and register through startServer(); no direct port hard-coding
- For Database: Confirm Drizzle best practices and avoid raw SQL except in migrations
- For State: Check appropriate use of React state; no premature global stores
Provide Constructive Feedback:
- Explain the "why" behind each concern or suggestion
- Reference specific lines in AGENTS.md or existing patterns
- Prioritize issues by severity (critical, important, minor)
- Suggest concrete improvements with code examples when helpful

Read the full file on GitHub · 83 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.

2d ago First seen · 83 lines · 0 tokens per session scan A 74eddf7c446f

Subscribe to this mod's changes

code-architecture-reviewer is an agent published in the GitHub repository ReviewStage/stage-cli (267 stars, last pushed 21d ago), licensed MIT. It adds 348 tokens to every session and 1,528 once invoked, about $0.0017 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.

Code review

code-architecture-reviewer

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

grader

comparator

.NET-Notebook-Migration-Agent