sams-architecture

sams-architecture is a skill for Claude Code from sam-dumont/claude-skills. It costs 102 tokens per session (12,811 once invoked), scanned B, original, MIT.

A set of standards for designing software systems and reviewing codebases. It favors starting with a simple monolithic application with clear module boundaries and adding abstractions only when repeated use justifies them.

In plain words
What is it for?
Use it when planning a project, choosing technologies, designing APIs or infrastructure, reviewing architecture, or checking an existing codebase for consistency.
Why use it?
It helps prevent unnecessary microservices, speculative features, and overly complex reusable frameworks.

Skill for Claude Code

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

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/sam/Code/perso/ev-consumption-api/ARCHITECTURE_REFACTORING_STATUS.md.

Part of the sams-architecture plugin — 1 skill shipped together

Good fit Use it when planning a project, choosing technologies, designing APIs or infrastructure, reviewing architecture, or checking an existing codebase for consistency.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add sam-dumont/claude-skills
Claude Code
/plugin install sams-architecture

Made for: Claude Code.

Or install sams-architecture, the plugin that ships this one along with the rest of its 1 skill.

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 sams-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/sam-dumont/claude-skills/sams-architecture/github.svg)](https://agentmods.dev/skills/sam-dumont/claude-skills/sams-architecture)
Your own site
<a href="https://agentmods.dev/skills/sam-dumont/claude-skills/sams-architecture"><img src="https://agentmods.dev/badge/skills/sam-dumont/claude-skills/sams-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.

agentmods 80×15 button for sams-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/sam-dumont/claude-skills/sams-architecture"><img src="https://agentmods.dev/badge/skills/sam-dumont/claude-skills/sams-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,811 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00102 $0.12811
Opus 5 $0.00051 $0.06406
Sonnet 5 $0.00020 $0.02562
Haiku 4.5 $0.00010 $0.01281

Measured 12d ago against content hash e06458b58049, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

sams-architecture scanned grade B with 2 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 12d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

&& rm -rf /var/lib/apt/lists/*

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

CMD python -c "import requests; requests.get('http://localhost:8000/health')"
plugins/sams-architecture/skills/sams-architecture/SKILL.md · 2,013 lines

How it starts

The opening of the file, as written. The whole thing — 2,013 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sam's Architecture Standards

This skill codifies Sam's mature architectural patterns developed across 31+ personal projects and several client projects. It automatically applies during project planning, architecture reviews, and codebase audits.


CRITICAL: Zero-Tolerance Anti-Patterns

These are NEVER acceptable in Sam's personal projects. Flag immediately if detected:

Over-Engineering Anti-Patterns

Premature Microservices: Breaking into microservices before you understand the domain boundaries

  • Sam's rule: Start monolithic with clear module boundaries, split only when you have operational pain
  • Example: Don't create separate services for "user-service", "auth-service", "notification-service" in a new project

YAGNI Violations: Building features "because we might need them later"

  • Sam's rule: Build what you need now, refactor when you need more
  • Example: Don't add multi-tenancy support to a single-user API

Abstraction Astronauts: Creating generic frameworks when specific solutions work

  • Sam's rule: Three uses before abstracting. Copy-paste twice, abstract on third use
  • Example: Don't create a "BaseAPIClient" with complex inheritance when you have one API client

Configuration Complexity: Making everything configurable "for flexibility"

  • Sam's rule: Hard-code sensible defaults, make configurable only when you need to change it
  • Example: Don't create config files for things that never change per environment

Under-Engineering Anti-Patterns

No Tests: "We'll add tests later" (narrator: they never did)

  • Sam's rule: 80% coverage minimum on personal projects, tests written with code

Missing CI/CD: Manual deployments, no automation

  • Sam's rule: CI/CD setup is part of project initialization, not a "nice to have"

Security as Afterthought: No authentication, secrets in code, no input validation

  • Sam's rule: Security is non-negotiable from day one

No Documentation: "The code is self-documenting"

  • Sam's rule: CLAUDE.md + README.md are mandatory for all personal projects

Read the full file on GitHub · 2,013 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. 12d ago First seen · 2,013 lines · 102 tokens per session scan B e06458b58049

Subscribe to this mod's changes

sams-architecture is a skill published in the GitHub repository sam-dumont/claude-skills (39 stars, last pushed 6mo ago), licensed MIT. It adds 102 tokens to every session and 12,811 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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