design

design is a skill for Claude Code from sembraniteam/claude-plugins. It costs 155 tokens per session (14,101 once invoked), scanned A, original, MIT.

A guided process for designing a new application's architecture, meaning the system's major parts, connections, and technical decisions. It covers planning, diagrams, review, testing, and optional implementation materials.

In plain words
What is it for?
Use it to plan a new system, create architecture diagrams, review the design, define a test strategy, and optionally produce a code skeleton.
Why use it?
It turns an early project idea into a documented design that can be reviewed before code is written. The process also records testing and unresolved decisions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the architecture-designer plugin — 3 skills, 13 agents shipped together

Good fit Use it to plan a new system, create architecture diagrams, review the design, define a test strategy, and optionally produce a code skeleton.

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

Made for: Claude Code.

Or install architecture-designer, the plugin that ships this one along with the rest of its 3 skills, 13 agents.

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 design

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sembraniteam/claude-plugins/design"><img src="https://agentmods.dev/badge/skills/sembraniteam/claude-plugins/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 14,101 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 $0.00155 $0.14101
Opus 5.5 $0.00062 $0.05640
Sonnet 5.5 $0.00031 $0.02820
Haiku 4.5 $0.00015 $0.01410

Measured 1mo ago against content hash 3aed74db032f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

architecture-designer/skills/design/SKILL.md · 843 lines

How it starts

The opening of the file, as written. The whole thing — 843 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Designer — Main Design Workflow

This skill guides the user through a six-stage design process plus a sequence of post-design steps (architecture review, optional persona reviews, browser preview, optional visual verification, user confirmation, low-level design, test strategy, document save, document review, implementation offer), ending with browser-rendered Mermaid diagrams, low-level design artifacts, a test strategy, a reviewed and approved document, and an optional code skeleton.

Always use this skill for new architecture design, even if the user has already started describing their system in the conversation — do not skip straight to diagram generation or freeform advice.

Scripts directory: ../../scripts/ relative to this SKILL.md — referred to as <scripts_dir> throughout this file. Resolve it at runtime from this SKILL.md's absolute path.


How to run this workflow

Before starting — check for an existing session: look for docs/architecture-designer/session.json. If it exists, read it and ask the user:

"I found an existing design session for

[project name from the file, or 'a previous project' if unnamed] — [description from the file, or omit this clause if unset].

Would you like to continue where we left off, or start a new design from scratch?"

If continuing: first check progress.owner, if the key is present. If it reads "review" and progress.lastCompletedStep is before step11 (per references/session-schema.md section "Resuming Steps 6a–13 via progress" step 2 — step11 means that /architecture-designer:review pass already reached a document save and left a clean handoff), a /architecture-designer:review revision died mid-pipeline, not this skill's own design pipeline — this skill's resume logic below only covers the original design pass. Tell the user: "It looks like a previous /architecture-designer:review revision didn't finish. Run /architecture-designer:review to resume it instead." and stop here rather than proceeding into Stage resume. Otherwise (progress.owner is "design", the key is absent — legacy sessions predating this key, or one that never reached Stage 6a — or it reads "review" with lastCompletedStep at step11 or later, meaning that pass already completed cleanly): brief the user on where the previous session left off and resume from the first incomplete stage. Once stage1–5 are confirmed (the "Session completeness gate" precondition — stage6b/6c are not required, since Stage 6a can already have progressed before either is confirmed), also apply references/session-schema.md section "Resuming Steps 6a–13 via progress" — a session that died anywhere from Stage 6a through Step 13 should resume there, not restart the whole pipeline, and any pending key found means the previous session died mid-stage within 1–6c (same section covers this). If starting fresh: delete docs/architecture-designer/session.json (and docs/architecture-designer/diagrams.json and docs/architecture-designer/last-review.md if present) first.

Read the full file on GitHub · 843 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. 1mo ago First seen · 843 lines · 155 tokens per session scan A 3aed74db032f

Subscribe to this mod's changes

design is a skill published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 155 tokens to every session and 14,101 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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

Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…

vercel/next.js · 123 tokens