architecture-review

architecture-review is a skill for Claude Code from okeefeco/pyeye-mcp. It costs 96 tokens per session (3,468 once invoked), scanned A, original, MIT.

A review guide for finding where a Python codebase follows different architectural rules, such as error handling, validation, or layering. It produces an evidence-backed, prioritised list for human decisions.

In plain words
What is it for?
Use it to audit a Python project’s internal consistency and investigate where packages or layers handle similar concerns differently.
Why use it?
It makes inconsistent design choices visible and ordered by impact, so developers can decide which pattern to keep. It does not detect copied code or make the changes automatically.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the pyeye plugin — 5 skills, 2 agents, 1 hook, 1 MCP server shipped together

Good fit Use it to audit a Python project’s internal consistency and investigate where packages or layers handle similar concerns differently.

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

Made for: Claude Code.

Or install pyeye, the plugin that ships this one along with the rest of its 5 skills, 2 agents, 1 hook, 1 MCP server.

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/okeefeco/pyeye-mcp/architecture-review/github.svg)](https://agentmods.dev/skills/okeefeco/pyeye-mcp/architecture-review)
Your own site
<a href="https://agentmods.dev/skills/okeefeco/pyeye-mcp/architecture-review"><img src="https://agentmods.dev/badge/skills/okeefeco/pyeye-mcp/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/okeefeco/pyeye-mcp/architecture-review"><img src="https://agentmods.dev/badge/skills/okeefeco/pyeye-mcp/architecture-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,468 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 $0.00096 $0.03468
Opus 5 $0.00048 $0.01734
Sonnet 5 $0.00019 $0.00694
Haiku 4.5 $0.00010 $0.00347

Measured 10d ago against content hash 5d5d2c9f3b93, 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 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/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Review

Surface and prioritise how a Python codebase's architectural conventions diverge from each other, with cited evidence and honest grades — so a human can decide which convention to keep. This skill is the single source of truth for how to run the audit; it orchestrates a fresh-context auditor over a supplied scope and drives the human review loop.

What This Is (and Is NOT) — Read First

Honest expectation. This tool produces a ranked queue of "here are N ways your code does X — you decide." Many entries will carry no recommendation by design (see the honesty invariants). It makes unknown divergences visible and ordered by impact — it does not remove the work, and it is emphatically not "the AI cleans up its own mess." You still make the architectural calls; this just stops you from making them blind.

Hard scope caveat — divergence, NOT duplication. This audits convention divergence ("your code does X seven different ways"). It does NOT detect semantic duplication ("the same code copy-pasted in many places"). Duplication is a content-similarity problem this skill structurally cannot do; it is carved out to issue #495. Do not run this expecting duplication detection — you will not get it.

Scope is caller-supplied and REQUIRED. You must hand this a scope — a package, module, or directory. Bounded-scope auto-iteration over a whole large repo is deferred; this skill audits exactly the scope it is given.

The Seven Seed Axes

The auditor sweeps (at minimum) these seven convention axes. The keys are the single source of truth in pyeye.architecture_review.taxonomy.SEED_AXES; the auditor may also surface other axes it finds.

Axis key What it covers
layering Layering / dependency direction: which layers/packages may import which.
module_boundaries Module & placement boundaries: where a kind of thing lives.
dependency_acquisition Dependency acquisition: constructor-injection vs import vs global/singleton.
error_handling Error handling: raise vs return-sentinel vs result-type; exception types; where caught.
validation_placement Validation placement: at the boundary vs in core vs scattered.
naming_api_shape Naming & API shape: naming patterns, return-type conventions, sync/async split.
cross_cutting Cross-cutting access: logging, config, path handling.

Read the full file on GitHub · 260 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 260 lines · 96 tokens per session scan A 5d5d2c9f3b93

Subscribe to this mod's changes

architecture-review is a skill published in the GitHub repository okeefeco/pyeye-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 96 tokens to every session and 3,468 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

python-design-pattern

Python design patterns and anti-patterns. Use when designing new components, refactoring, reviewing code for common mistakes, choosing abstractions, or evaluating pull requests for structural issues like tight coupling, leaking internal types, or error handling problems.

AI-Riksarkivet/ra-mcp · 51 tokens

vibeue

Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…

kevinpbuckley/VibeUE · 82 tokens

plankton-code-quality

Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.

loulanyue/awesome-claude-notes · 34 tokens

code-review-python

Provides Python-specific code review rules for the dh code-reviewer agent. Activates on pyproject.toml or .py file detection — enforces uv, ruff, ty, pytest, type annotation, error handling, and Python 3.11+ idioms including pathlib, match statements, and modern union syntax.

Jamie-BitFlight/claude_skills · 68 tokens

python-services

Python patterns for CLI tools, async parallelism, and backend services. Use when building CLI apps, async/parallel Python, FastAPI services, background jobs, or configuring Python project tooling (uv, ruff, ty).

iliaal/whetstone · 48 tokens

adversarial-python

Use this skill to gate Python code (floors 3.10+, rules verified through 3.14) with a pass/fail adversarial review — a single blind reviewer subagent judges a diff or file set against 20 decidable rules hunting two failure modes. First, code modern Python makes unnecessary — branch ladders over match/registries…

pproenca/dot-skills · 224 tokens