features:design

features:design is a command for coding agents from ruslan-korneev/claude-plugins. It costs 14 tokens per session (1,450 once invoked), scanned A, original, MIT.

An interactive command for deciding what a new application should include. It asks about the application type, user roles, core data objects, and workflows before shaping the feature list.

In plain words
What is it for?
Use it when starting a new application or planning its main features, such as an online store, subscription service, API, or internal tool.
Why use it?
It turns a broad product idea into a clearer set of features and requirements. This helps uncover missing users, business areas, and important work flows early.

Command

Part of the tech-lead plugin — 14 commands, 9 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 commands/ruslan-korneev/claude-plugins/features-design
Clone the repo
git clone --depth 1 https://github.com/ruslan-korneev/claude-plugins

Or install tech-lead, the plugin that ships this one along with the rest of its 14 commands, 9 agents.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,450 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 $0.00014 $0.01450
Opus 5 $0.00007 $0.00725
Sonnet 5 $0.00003 $0.00290
Haiku 4.5 $0.00001 $0.00145

Measured 3d ago against content hash c72e1cdb87b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

features: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 3d 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.

plugins/tech-lead/commands/features-design.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command /feature-list:design

Interactive feature design session for new or greenfield projects.

Instructions

Step 1: Understand Project Context

Use AskUserQuestion to gather initial context:

questions:
  - question: "What type of application are you building?"
    header: "App Type"
    options:
      - label: "E-commerce"
        description: "Online store with products, cart, checkout"
      - label: "SaaS Platform"
        description: "Multi-tenant application with subscriptions"
      - label: "API Service"
        description: "Backend API for mobile/web clients"
      - label: "Internal Tool"
        description: "Admin panel or back-office system"

Step 2: Identify User Roles

questions:
  - question: "What user roles will your application have?"
    header: "User Roles"
    multiSelect: true
    options:
      - label: "Anonymous User"
        description: "Unauthenticated visitors"
      - label: "Registered User"
        description: "Authenticated regular users"
      - label: "Admin"
        description: "System administrators"
      - label: "Moderator"
        description: "Content or user moderators"

Step 3: Define Core Entities

Based on project type, suggest core entities:

E-commerce:

  • User, Product, Category, Cart, Order, Payment

SaaS:

  • User, Organization, Team, Subscription, Feature

API Service:

  • User, APIKey, RateLimit, Webhook

Ask user to confirm or modify:

questions:
  - question: "Which core entities does your system need?"
    header: "Entities"
    multiSelect: true
    options:
      - label: "Users"
        description: "User accounts and profiles"
      - label: "Products"
        description: "Items for sale or display"
      - label: "Orders"
        description: "Purchase transactions"
      - label: "Organizations"
        description: "Multi-tenant companies/teams"

Step 4: Define Key Workflows

questions:
  - question: "What are the main workflows in your application?"
    header: "Workflows"
    multiSelect: true
    options:
      - label: "User Registration"
        description: "Sign up, email verification, onboarding"
      - label: "Purchase Flow"
        description: "Cart → Checkout → Payment → Confirmation"
      - label: "Content Publishing"
        description: "Draft → Review → Publish"
      - label: "Approval Process"
        description: "Submit → Review → Approve/Reject"

Read the full file on GitHub · 252 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. 3d ago First seen · 252 lines · 14 tokens per session scan A c72e1cdb87b0

Subscribe to this mod's changes

features:design is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 1,450 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 2026-08-31.