What is architecture.write_design?

A software design documentation workflow that turns a product requirements document (PRD) into architecture documents before coding begins. It divides the system into components and records how they fit together.

Use it to read requirements and existing code, propose components, and write overview and component design documents.

It gives a project a planned structure before implementation and prevents unclear or conflicting requirements from being silently guessed.

architecture.write_design — Skill for Claude Code by gpsaggese/helpers

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 gpsaggese/helpers --skill architecture.write_design

Clone the repo

git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

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/gpsaggese/helpers/architecture.write_design/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/architecture.write_design)

Your own site

<a href="https://agentmods.dev/skills/gpsaggese/helpers/architecture.write_design"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/architecture.write_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.

Your own site · 80×15

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

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 863 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	$0.00015	$0.00863
Opus 5.5	$0.00006	$0.00345
Sonnet 5.5	$0.00003	$0.00173
Haiku 4.5	$0.00002	$0.00086

Measured yesterday against content hash df90dd4c710a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architecture.write_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 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.

.claude/skills/architecture.write_design/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Given a PRD (Product Requirement Document), write docs/02-design.architecture.md and docs/02.<N>-design.<component>.md per component
Design before the code exists: do not write code

Input

<PRD>: the PRD file, e.g., docs/01-prd.md
<DOCS_DIR>: the docs/ dir of the project, optional
- If missing, use the dir of <PRD>

Workflow

Read the Inputs

Read <PRD> and the existing docs in <DOCS_DIR>
Read the existing code and docs that the design must fit
Read .claude/skills/architecture.rules.md and .claude/skills/C4.rules.md

Ask If the PRD Is Unclear

If a requirement is ambiguous or two requirements conflict:
- Do not guess
- Ask the user and wait for the answers

Split Into Components

Propose components, each with one responsibility
Respect the layering rules in .claude/skills/architecture.rules.md
Show the proposal and wait for user confirmation before writing the docs

Write the Overview

Create <DOCS_DIR>/02-design.architecture.md
Follow the template .claude/templates/project_design.template.md
Show the context and containers with a PlantUML C4 diagram, per .claude/skills/C4.rules.md
Map each requirement R<N> of the PRD to its component
- Link each R<N> to its H3 in the PRD, per .claude/skills/project.rules.md section "Link Requirements and Decisions"

Write One Doc per Component

Create <DOCS_DIR>/02.<N>-design.<component>.md for each component
Follow .claude/skills/project.rules.md section "Write a Design Doc" and the template .claude/templates/project_design.template.md
Record each non-obvious choice in <DOCS_DIR>/03-decisions.md, following the template .claude/templates/project_decisions.template.md
- Create the file if it does not exist
Link each decision from the design docs that follow it, per .claude/skills/project.rules.md section "Link Requirements and Decisions"

Update the Index

Add a row for each new doc to <DOCS_DIR>/README.md, if the file exists

Read the full file on GitHub · 93 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.

yesterday First seen · 93 lines · 15 tokens per session scan A df90dd4c710a

Subscribe to this mod's changes

architecture.write_design is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 863 once invoked, about $0.0001 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 2026-11-06.

Planning Writing and docs

architecture.write_design next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
architecture.write_designgpsaggese/helpers	Skill	158	today	Apache-2.0	A	15	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex