What is architecture?

A code-architecture review workflow that examines how a codebase is divided into modules and how its layers, interfaces, tests, and dependencies fit together. It includes checks for readability, duplication, outdated code, and common design principles.

Use it to review and improve boundaries between application layers, modularity, testability, naming, and maintainability. It can organise parallel review and follow-up implementation work across the codebase.

It helps find tangled responsibilities, inconsistent data shapes, hard-to-test code, and unnecessary complexity before they spread through the project.

architecture — Skill for Claude Code by nicograef/handbook

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 nicograef/handbook --skill architecture

Clone the repo

git clone --depth 1 https://github.com/nicograef/handbook

Made for: Claude Code.

Or install nico, the plugin that ships this one along with the rest of its 10 skills, 1 agent, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nicograef/handbook/architecture/github.svg)](https://agentmods.dev/skills/nicograef/handbook/architecture)

Your own site

<a href="https://agentmods.dev/skills/nicograef/handbook/architecture"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/architecture/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nicograef/handbook/architecture"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 510 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.00510
Opus 5.5	$0.00016	$0.00204
Sonnet 5.5	$0.00008	$0.00102
Haiku 4.5	$0.00004	$0.00051

Measured yesterday against content hash d975001735d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architecture 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 yesterday.

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.

plugin/skills/architecture/SKILL.md · 38 lines

What it actually says

Architecture

Enable ultracode and use workflows.
Sweep the codebase and separate it into areas/modules to work at in parallel.
Run a multi-expert review on code architecture considering clean code, modularity, readability
- Clean Architecture: layer boundaries, domain code free of framework and infrastructure types
- Cross-layer consistency: shapes, nullability, validation and enums agree from frontend to database
- Clean Code
- Modularity, Cohesion and Coupling
- KISS, YAGNI, Overengineering and Simplifications
- Testability and test cost: suite time per module, duplicate and fan-out tests, own-module mocks, tests above the cheapest failing level
- Readability and Understandability
- SOLID Principles
- Outdated, unused or deprecated fields, interfaces, functions, ...
- Unification, best practices and consistency
Reviewers apply these decision tests:
- Deletion test: delete the module. Complexity that reappears in its callers means it earns its place.
- One adapter is a hypothetical seam; two make it real.
- The interface is the test surface.
Thresholds come from the project's own gates: its linter config (ruff max-complexity, max-statements) and its structure tests. Structure tests hold the module line cap, the name length and thin __init__ files. Where a project sets none: complexity ≤ 15, ≤ 50 statements per function, module ≤ 600 lines. Names have ≥ 3 characters; internals sit behind a package's __init__. Reviewers report each violation as a finding.
Run as many Opus reviewers on as many areas of the codebase you think is suitable.
Run Sonnet verifiers and refuters on the findings.
Run Opus fixers and implementers.
Keep the workflows lean and efficient.
- Bundle reviews, tests and gates on the main branch or a common base branch.
- You may even use just one branch or one worktree for all of this.
- Choose the codebase split accordingly.

If you find any bugs or issues along the way, fix them directly as part of the workflow.

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.

yesterday Changed · +35 tokens per session d975001735d0
12d ago Changed · +2 lines 927a8fbe462c
16d ago Changed · +6 lines 54ccd6a5345d
18d ago First seen · 30 lines · 5 tokens per session scan A 14fa06813d86

Subscribe to this mod's changes

architecture is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 510 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 2026-10-20.

Code review Debugging

architecture next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
architecturenicograef/handbook	Skill	2	2d ago	MIT	A	40	Claude Code
sync-bridgechromium/chromium	Skill	25k	yesterday	BSD-3-Clause	A	109	Claude Code, Codex
sync-model-processorchromium/chromium	Skill	25k	yesterday	BSD-3-Clause	A	98	Claude Code, Codex
adversarial-revieweremdash-cms/emdash	Skill	14k	yesterday	MIT	A	72	Claude Code, Codex
gsd-ns-reviewopen-gsd/gsd-core	Skill	11k	yesterday	MIT	A	16	Claude Code
gitnexushashgraph-online/awesome-codex-plugins	Skill	1.5k	yesterday	Apache-2.0	A	58	Codex
issuejeremylongshore/tons-of-skills-marketplace	Skill	2.9k	yesterday	MIT	A	115	Claude Code