architecture-review

architecture-review is a skill for Claude Code, Codex from Arroyo-Gonzalo/codex-devkit. It costs 43 tokens per session (616 once invoked), scanned A, original, MIT.

A structured review of how a feature, module, integration, or whole system should be designed before coding begins. It considers requirements, existing code structure, dependencies, deployment, testing, and future growth.

In plain words
What is it for?
Use it for major feature designs, refactoring plans, integrations, scalability questions, and changes affecting APIs, data storage, permissions, events, deployment, or testing.
Why use it?
It helps reveal design risks and compare simpler alternatives before implementation makes them expensive to change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for major feature designs, refactoring plans, integrations, scalability questions, and changes affecting APIs, data storage, permissions, events, deployment, or testing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arroyo-gonzalo/codex-devkit/architecture-review
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 Arroyo-Gonzalo/codex-devkit --skill architecture-review
Clone the repo
git clone --depth 1 https://github.com/Arroyo-Gonzalo/codex-devkit

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/arroyo-gonzalo/codex-devkit/architecture-review/github.svg)](https://agentmods.dev/skills/arroyo-gonzalo/codex-devkit/architecture-review)
Your own site
<a href="https://agentmods.dev/skills/arroyo-gonzalo/codex-devkit/architecture-review"><img src="https://agentmods.dev/badge/skills/arroyo-gonzalo/codex-devkit/architecture-review/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/arroyo-gonzalo/codex-devkit/architecture-review"><img src="https://agentmods.dev/badge/skills/arroyo-gonzalo/codex-devkit/architecture-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 616 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 $0.00616
Opus 5.5 $0.00017 $0.00246
Sonnet 5.5 $0.00009 $0.00123
Haiku 4.5 $0.00004 $0.00062

Measured 2mo ago against content hash 9089df77767e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architecture-review 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 2mo 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/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Review

Purpose

Evaluate architectural decisions before implementation.

Prioritize simplicity, maintainability, consistency, and long-term evolution over unnecessary complexity.

Do not implement code unless explicitly requested.

Workflow

1. Understand the objective

Identify:

  • business objective;
  • functional requirements;
  • non-functional requirements;
  • constraints;
  • expected growth;
  • deployment model;
  • affected systems.

Clarify assumptions before evaluating solutions.


2. Inspect the existing architecture

Understand:

  • repository structure;
  • module boundaries;
  • dependency graph;
  • persistence strategy;
  • communication patterns;
  • deployment architecture;
  • existing conventions.

Respect existing architecture unless there is evidence that it should change.


3. Identify architectural impact

Determine whether the proposal affects:

  • public APIs;
  • persistence;
  • authentication;
  • authorization;
  • integrations;
  • event flow;
  • transactions;
  • scalability;
  • observability;
  • deployment;
  • testing.

Document affected areas.


4. Evaluate alternatives

For each reasonable option:

  • advantages;
  • disadvantages;
  • implementation complexity;
  • migration complexity;
  • operational complexity;
  • scalability;
  • maintainability.

Prefer the simplest solution that satisfies current requirements.

Avoid solving problems that do not yet exist.


5. Evaluate technical risks

Review:

  • coupling;
  • cohesion;
  • dependency direction;
  • cyclic dependencies;
  • hidden complexity;
  • transaction boundaries;
  • race conditions;
  • deployment risks;
  • migration risks;
  • rollback strategy.

Identify assumptions that could become future problems.


6. Evaluate operational concerns

Consider:

  • monitoring;
  • logging;
  • observability;
  • configuration;
  • environment management;
  • scaling strategy;
  • recovery strategy;
  • failure modes.

Operational simplicity is part of architecture.


7. Recommendation

Recommend a single preferred approach.

Read the full file on GitHub · 177 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. 2mo ago First seen · 177 lines · 43 tokens per session scan A 9089df77767e

Subscribe to this mod's changes

architecture-review is a skill published in the GitHub repository Arroyo-Gonzalo/codex-devkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 616 once invoked, about $0.0002 per session on Opus 5.5. 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

architecture-review compared with skills from other repositories

architecture-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
architecture-reviewArroyo-Gonzalo/codex-devkitSkill23mo agoMITA43Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code