architecture-principles

architecture-principles is a skill for Claude Code from sethdford/claude-skills. It costs 29 tokens per session (614 once invoked), scanned A, original, MIT.

A guide for defining the basic rules that shape software architecture decisions. These rules can cover priorities such as security, cost, speed, reliability, and how systems are built.

In plain words
What is it for?
Use it to create, update, and communicate architecture standards and decision rules across an organization.
Why use it?
It gives teams a consistent way to make technical choices and handle conflicts or exceptions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the architecture-governance plugin — 7 skills shipped together

Good fit Use it to create, update, and communicate architecture standards and decision rules across an organization.

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

Made for: Claude Code.

Or install architecture-governance, the plugin that ships this one along with the rest of its 7 skills.

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-principles

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sethdford/claude-skills/architecture-principles"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-principles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 614 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 $0.00029 $0.00614
Opus 5 $0.00015 $0.00307
Sonnet 5 $0.00006 $0.00123
Haiku 4.5 $0.00003 $0.00061

Measured 10d ago against content hash a3cf4585e015, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

architecture-principles 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.

architect/architecture-governance/skills/architecture-principles/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Principles

Establish foundational principles that guide architectural decisions and align organization.

Context

You are defining architecture principles for the organization. Create clear, memorable guidelines that inform decisions. Involve stakeholders from product, engineering, and operations.

Domain Context

Based on architecture governance frameworks (TOGAF, Gartner):

  • Guiding Principles: High-level philosophy (e.g., "Cloud-first", "Stateless services", "API-driven")
  • Decision Rules: Specific rules derived from principles (e.g., "Use managed databases not self-hosted" from "Minimize operational burden")
  • Trade-off Hierarchy: When principles conflict, which takes priority? Performance vs Cost? Consistency vs Availability?
  • Exemptions: Clear process to override principles; document why and remediation plan
  • Communication: Memorability matters; short, actionable, memorable

Instructions

  1. Identify Core Values: What matters to the organization? Speed of innovation? Cost efficiency? Security? Reliability? List top 3-5.

  2. Derive Principles: Turn values into principles. "Speed of innovation" → "Ship independently without central coordination". "Cost efficiency" → "Use managed services to reduce operational overhead".

  3. Make Principles Memorable: Use simple language. "Move fast with confidence" better than "Implement robust CI/CD pipelines". Acronyms help: KISS (Keep It Simple, Stupid).

  4. Create Decision Rules: For each principle, what are concrete decisions? "Cloud-first" → "Use EC2 not on-prem", "Use Lambda for new services", "Data in S3 not shared NFS".

  5. Communicate and Enforce: Share with teams. Use in architecture reviews. Celebrate adherence; discuss exceptions constructively. Update as organization evolves.

Anti-Patterns

  • Too Many Principles: 20 principles, teams ignore most. Result: becomes noise. Guard: 5-7 principles max. Memorable, not exhaustive.
  • Principles Without Teeth: Define but don't enforce. Result: ignored, no effect. Guard: Use in reviews; track compliance; discuss exceptions.
  • Conflicting Principles: "Always use consistency" vs "Optimize for latency" without hierarchy. Result: confusion. Guard: Explicit trade-off hierarchy; example: consistency > cost > speed.
  • No Updates: Principles defined 5 years ago; organization evolved. Result: misalignment. Guard: Review annually; update with changes in strategy.

Read the full file on GitHub · 48 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. 10d ago First seen · 48 lines · 29 tokens per session scan A a3cf4585e015

Subscribe to this mod's changes

architecture-principles is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 614 once invoked, about $0.0001 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.

Related

Other skills, from other repositories