architecture-design

architecture-design is a skill for Claude Code, Codex from pueraeternis/agentic-project-template. It costs 0 tokens per session (761 once invoked), scanned A, original, MIT.

A planning guide for deciding how a software system should be organized after the project definition and roadmap are approved. It sets the main parts of the system and the boundaries between them before implementation details are chosen.

In plain words
What is it for?
Creating an initial system architecture and updating it when a roadmap phase adds or changes major capabilities.
Why use it?
It prevents major structural decisions from being made ad hoc during coding and gives later engineering work a stable direction.

Skill for Claude CodeCodex

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

Good fit Creating an initial system architecture and updating it when a roadmap phase adds or changes major capabilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pueraeternis/agentic-project-template/architecture-design
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 pueraeternis/agentic-project-template --skill architecture-design
Clone the repo
git clone --depth 1 https://github.com/pueraeternis/agentic-project-template

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-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/pueraeternis/agentic-project-template/architecture-design/github.svg)](https://agentmods.dev/skills/pueraeternis/agentic-project-template/architecture-design)
Your own site
<a href="https://agentmods.dev/skills/pueraeternis/agentic-project-template/architecture-design"><img src="https://agentmods.dev/badge/skills/pueraeternis/agentic-project-template/architecture-design/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-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/pueraeternis/agentic-project-template/architecture-design"><img src="https://agentmods.dev/badge/skills/pueraeternis/agentic-project-template/architecture-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 761 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 $0.00000 $0.00761
Opus 5 $0.00000 $0.00380
Sonnet 5 $0.00000 $0.00152
Haiku 4.5 $0.00000 $0.00076

Measured 9d ago against content hash 5d33bae06a14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

architecture-design 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.

skills/architecture-design/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Design

Purpose

This skill transforms an approved project definition and roadmap into a stable system architecture.

It defines the long-term organization of the system before engineering design and implementation begin.

The resulting architecture becomes the foundation for engineering decisions and implementation planning.


Lifecycle Stage

Project Discovery
        ↓
Roadmap Creation
        ↓
Architecture Design
        ↓
Engineering Design

Architecture Design defines how the system is organized.

Engineering Design later defines how that architecture will be implemented.


Role

Primary role:

Architecture Agent

This skill may also be executed by another reasoning-capable agent when acting in the Architecture Agent role.


When to Use

Use this skill when:

  • PROJECT.md has been approved;
  • ROADMAP.md has been approved;
  • the initial architecture must be created;
  • a roadmap phase introduces new architectural capabilities;
  • architectural boundaries need to evolve.

Do not use this skill for:

  • project discovery;
  • engineering decisions;
  • repository initialization;
  • implementation planning;
  • production code.

Inputs

Required:

  • PROJECT.md
  • ROADMAP.md

Optional:

  • existing ARCHITECTURE.md
  • existing ADRs

The project vision and roadmap should already be stable.


Outputs

Produce:

  • ARCHITECTURE.md
  • ADRs (when required)

The architecture should provide sufficient structure for Engineering Design without introducing implementation details.


Procedure

Step 1 — Understand the Project

Review:

  • project goals;
  • roadmap phases;
  • constraints;
  • target users;
  • expected capabilities.

Architecture must support the approved project direction.


Step 2 — Design the System

Define:

  • major components;
  • responsibilities;
  • ownership boundaries;
  • dependency rules;
  • integration points.

Focus on stable system organization rather than implementation.


Read the full file on GitHub · 227 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 · 227 lines · 0 tokens per session scan A 5d33bae06a14

Subscribe to this mod's changes

architecture-design is a skill published in the GitHub repository pueraeternis/agentic-project-template (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 761 tokens. 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.