architecture-review

architecture-review is a skill for Claude Code, Codex from 0xranx/agentbrief. It costs 75 tokens per session (639 once invoked), scanned A, original, MIT.

A code-review method for checking major system design decisions, such as new services, data flows, database changes, and API boundaries.

In plain words
What is it for?
Reviewing architectural changes, tracing data from input to output, checking dependency direction, and identifying risky transformations.
Why use it?
It looks for problems that tests and linters may miss, including weak boundaries, incorrect abstractions, and scaling risks.

Skill for Claude CodeCodex

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

Good fit Reviewing architectural changes, tracing data from input to output, checking dependency direction, and identifying risky transformations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/0xranx/agentbrief/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 0xranx/agentbrief --skill architecture-review
Clone the repo
git clone --depth 1 https://github.com/0xranx/agentbrief

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/0xranx/agentbrief/architecture-review/github.svg)](https://agentmods.dev/skills/0xranx/agentbrief/architecture-review)
Your own site
<a href="https://agentmods.dev/skills/0xranx/agentbrief/architecture-review"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/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/0xranx/agentbrief/architecture-review"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/architecture-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 639 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 $0.00075 $0.00639
Opus 5 $0.00037 $0.00319
Sonnet 5 $0.00015 $0.00128
Haiku 4.5 $0.00007 $0.00064

Measured 9d ago against content hash 2fa1abde57f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

briefs/code-reviewer/skills/architecture-review/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Review

You are a staff-level engineer reviewing architectural decisions. Your job is to catch design issues that unit tests and linters cannot: wrong abstractions, leaky boundaries, missing edge cases, and scaling traps.

Review Process

1. Understand the Intent

Before reviewing code, understand what problem is being solved:

  • Read the PR description, linked issue, or spec
  • Identify the core requirement vs. incidental complexity
  • Ask: "Is this the simplest approach that solves the actual problem?"

2. Data Flow Analysis

Trace data from entry to exit:

  1. Input boundary — Where does data enter? Is it validated at the edge?
  2. Transformation chain — How many layers does data pass through? Each hop is a potential failure point
  3. Storage — What's persisted? Is the schema forward-compatible?
  4. Output boundary — What leaves the system? Is it sanitized?

Flag any case where data is transformed more than 3 times before reaching its destination.

3. Dependency Direction Check

  • Dependencies should point inward (domain ← application ← infrastructure)
  • Flag any case where domain logic imports from infrastructure
  • Flag circular dependencies between modules
  • Flag "god modules" that everything imports from

4. Error & Edge Case Audit

For each new code path, check:

  • What happens on timeout?
  • What happens on partial failure (e.g., DB write succeeds but cache update fails)?
  • What happens under concurrent access (race conditions)?
  • What happens when downstream services are unavailable?
  • What happens at scale (10x current load)?

5. API Contract Review

For any new or changed API:

  • Is it backwards-compatible? If not, is there a migration path?
  • Are error responses consistent with existing patterns?
  • Is the API idempotent where it should be?
  • Are there rate limits or abuse vectors?

6. Findings Format

For each architectural finding:

**[ARCH-NNN] Title**
Severity: Critical | High | Medium | Advisory
Category: Data Flow | Dependency | Concurrency | API Contract | Scalability
Issue: What's wrong and why it matters
Recommendation: Specific alternative approach

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 75 tokens per session scan A 2fa1abde57f2

Subscribe to this mod's changes

architecture-review is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 639 once invoked, about $0.0004 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.