design

A structured command for planning complex features before implementation. It records the problem, possible approaches, chosen solution, user stories, and final decisions.

In plain words
What is it for?
Use it to start, continue, or review a feature design and break the result into implementable stories.
Why use it?
It helps clarify scope and trade-offs before coding begins, especially when a feature has several parts.

Command

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/b33eep/claude-code-setup/design
Clone the repo
git clone --depth 1 https://github.com/b33eep/claude-code-setup
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,500 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 $0.00000 $0.03500
Opus 5 $0.00000 $0.01750
Sonnet 5 $0.00000 $0.00700
Haiku 4.5 $0.00000 $0.00350

Measured 2d ago against content hash fe6c283a024e, 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 2d 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.

commands/design.md · 538 lines

How it starts

The opening of the file, as written. The whole thing — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design: Structured Feature Design

A structured way to plan complex features before implementing. Works through: Problem → Options → Solution → Stories → Finalize.

The result is a Record (markdown file) that documents design decisions and breaks work into implementable stories.

Usage

/design "Feature name"     # Start new design
/design --continue         # Resume incomplete design
/design --review           # Get feedback on current design (requires comprehensive-review)

When to Use /design vs /todo

Use /design when... Use /todo when...
Feature has multiple parts Just need a reminder
Unsure how to implement Quick idea for later
Need to evaluate options Simple task
Architecture decision -

Tasks

Prerequisites

  • If no project CLAUDE.md found: Tell user to run /init-project first
  • If no docs/records/ directory: Create it

Handle Arguments

No arguments:

  1. Check for incomplete designs (Records with Status: "Designing")
  2. If found: Show state summary, offer to resume (see "Resume Design Workflow")
  3. If none: Ask "What feature do you want to design?"

With feature name:

  1. Check if a Record for this feature already exists (search by title)
  2. If found with Status "Designing": Ask "Resume existing design?" or "Start fresh?"
  3. If found with Status "Designed/In Progress/Done": Ask "Feature already has Record [NNN]. Create new design anyway?"
  4. Start new design workflow for the given feature

--continue flag:

  1. Find incomplete designs (Records with Status: "Designing")
  2. If multiple found: Show list, ask "Which design to continue?"
  3. If single found: Show state summary, resume from current step
  4. If none: "No incomplete design found. Start new with /design 'feature name'"

See "Resume Design Workflow" section below for details.

--review flag:

  1. Find current design (active session or incomplete Record)
  2. If multiple incomplete designs: Ask "Which design to review?" with list
  3. If no design found: "No design to review. Start with /design 'feature name'"
  4. If comprehensive-review plugin not installed: "Install comprehensive-review plugin for design reviews: /claude-code-setup → External Plugins"
  5. If plugin installed: Invoke review agent (see Review Agent section below)
  6. Show feedback to user (do not store in Record)
  7. After review: Prompt with explicit next step (see After Review section)

Read the full file on GitHub · 538 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. 2d ago First seen · 538 lines · 0 tokens per session scan A fe6c283a024e

Subscribe to this mod's changes

design is a command published in the GitHub repository b33eep/claude-code-setup (56 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,500 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 2026-08-30.