design

design is a skill for Claude Code, Codex 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 CodeCodex

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

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.

agentmods
npx agentmods add skills/sembraniteam/claude-plugins/design
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, Codex.

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.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
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 $0.00155 $0.14101
Opus 5 $0.00077 $0.07050
Sonnet 5 $0.00031 $0.02820
Haiku 4.5 $0.00015 $0.01410

Measured 4d ago against content hash 3aed74db032f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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. 4d 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 1mo ago), licensed MIT. It adds 155 tokens to every session and 14,101 once invoked, about $0.0008 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 2026-08-31.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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