architecture-review-framework

architecture-review-framework is a skill for Claude Code from volodchenkov/claude-sdlc-agents. It costs 90 tokens per session (2,475 once invoked), scanned A, original, MIT.

A checklist and workflow for reviewing software architecture documents and proposed changes. It checks whether a specification is ready to implement, whether its decisions are recorded, and whether it traces back to the requirements.

In plain words
What is it for?
Use it to review a system specification or later code changes, assess architecture decisions, verify links to requirements, and issue an approved or changes-required verdict.
Why use it?
It helps catch design problems before coding begins and leaves a documented review record. It also checks that implementation follows the approved architecture.

Skill for Claude Code

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

Part of the sdlc-agents plugin — 12 skills, 13 agents shipped together

Good fit Use it to review a system specification or later code changes, assess architecture decisions, verify links to requirements, and issue an approved or changes-required verdict.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/volodchenkov/claude-sdlc-agents/architecture-review-framework
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.

Any agent
npx skills add volodchenkov/claude-sdlc-agents --skill architecture-review-framework
Clone the repo
git clone --depth 1 https://github.com/volodchenkov/claude-sdlc-agents

Made for: Claude Code.

Or install sdlc-agents, the plugin that ships this one along with the rest of its 12 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-review-framework

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/volodchenkov/claude-sdlc-agents/architecture-review-framework"><img src="https://agentmods.dev/badge/skills/volodchenkov/claude-sdlc-agents/architecture-review-framework.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,475 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 $0.00090 $0.02475
Opus 5 $0.00045 $0.01238
Sonnet 5 $0.00018 $0.00495
Haiku 4.5 $0.00009 $0.00248

Measured 10d ago against content hash 34477cc86139, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

architecture-review-framework 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 10d 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/architecture-review-framework/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Review Framework

This skill defines how the architect reviews SPECs and CHANGES. Goal: produce a verifiable, professional ARCH_REVIEW that catches problems early and leaves a paper trail. Inspired by:

  • C4 Model review at Context and Container levels
  • SOLID principles (Robert C. Martin) — for code review
  • DDD bounded context discipline — service boundary checks
  • ADR pattern (Michael Nygard) — for capturing and approving architectural decisions
  • Code review best practices (Google eng-practices, Smartbear)

Two review modes

Mode A: SPEC review (most common)

Triggered after the system-analyst posts SPEC. The architect reads SPEC + REQUIREMENTS, evaluates against 7 review areas (Area 0 implementation-readiness + 6 technical areas), evaluates each ADR, validates traceability matrix. Output: ARCH_REVIEW comment in SPEC sub-issue + SPEC_APPROVED marker (when all green).

Mode B: CHANGES review (less common — assist the reviewer)

After coders post CHANGES. The architect cross-checks that implementation respects the architectural decisions in SPEC. Output: ARCH_REVIEW iteration comment in coder's sub-issue. Note: the reviewer is the canonical reviewer for CHANGES; the architect intervenes only when architectural drift is suspected.

This skill focuses on Mode A; Mode B uses the same 7-area lens.


The 7 Review Areas

Every ARCH_REVIEW iteration covers all 7 — even if some are N/A for the given SPEC, explicitly state why N/A. Silent skipping is the most common architecture review failure mode.

Area 0: Implementation-readiness (ATAM-style concrete scenarios)

A formally correct SPEC that leaves implementation to guesswork is not APPROVED. For every affected backend service and frontend, verify:

  • Every model field has explicit type, constraints, and on_delete semantics (coder doesn't extrapolate from "similar models").
  • Every endpoint has request shape, response shape, and ALL error codes (not just success).
  • Every user-facing screen has explicit loading / empty / error / partial / success states.
  • Every business rule (§4 BRs) is a testable invariant with explicit inputs and expected outputs — not an aspiration ("handle X gracefully", "good UX").

Read the full file on GitHub · 200 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. 10d ago First seen · 200 lines · 90 tokens per session scan A 34477cc86139

Subscribe to this mod's changes

architecture-review-framework is a skill published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 2,475 once invoked, about $0.0005 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens