design-with-questions

design-with-questions is a command for Claude Code, Cursor from codeready-toolchain/tarsy. It costs 0 tokens per session (1,178 once invoked), scanned A, original, Apache-2.0.

A guided design workflow that studies a codebase, its documentation, and tests before creating a design draft and a list of open questions.

In plain words
What is it for?
Use it to plan a feature, document its proposed structure, and discuss decisions that still need answers.
Why use it?
It helps avoid designs based on guesses and makes unresolved decisions visible before implementation begins.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

Good fit Use it to plan a feature, document its proposed structure, and discuss decisions that still need answers.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/codeready-toolchain/tarsy/design-with-questions
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.

Clone the repo
git clone --depth 1 https://github.com/codeready-toolchain/tarsy

Made for: Claude Code, Cursor.

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-with-questions

README.md
[![agentmods](https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/design-with-questions/github.svg)](https://agentmods.dev/commands/codeready-toolchain/tarsy/design-with-questions)
Your own site
<a href="https://agentmods.dev/commands/codeready-toolchain/tarsy/design-with-questions"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/design-with-questions/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-with-questions

Your own site · 80×15
<a href="https://agentmods.dev/commands/codeready-toolchain/tarsy/design-with-questions"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/design-with-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 1,178 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 $0.00000 $0.01178
Opus 5 $0.00000 $0.00589
Sonnet 5 $0.00000 $0.00236
Haiku 4.5 $0.00000 $0.00118

Measured 9d ago against content hash 741330121835, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-with-questions 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 9d 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.

.cursor/commands/design-with-questions.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-with-questions

You are in design mode. Generate two documents and then walk through the questions together.


Before you start

Do a thorough analysis before generating anything. A good design requires deep understanding of the existing system.

  • Explore the codebase: understand the structure, relevant packages, existing interfaces, patterns, and conventions
  • Read existing documentation in docs/ — sketches, prior designs, proposals, anything related to this feature
  • Look at existing tests to understand expected behavior and boundaries
  • If the feature involves external technologies, libraries, or patterns you're not confident about, research them first

Only start generating documents once you have enough context to produce an accurate, well-grounded design.


Phase 1: Generate two documents

1. docs/proposals/{name}-design.md — Design Document

A best-guess draft of the full design. Complete enough to reason about, but with open question markers wherever a decision is still needed.

Required sections:

  • Status header: Draft — pending decisions from [{name}-questions.md]({name}-questions.md)
  • Overview — what this is and why it exists
  • Design Principles — key constraints and guiding goals
  • Architecture / How It Works — components, relationships, data flows (use diagrams where helpful)
  • Core Concepts — key abstractions and their roles
  • Implementation Plan — PR-sized steps (see below)
  • Open Questions — summary list cross-referencing the questions doc
Implementation Plan

Write it for an AI implementer, not a human project plan. Split code into PRs; non-code steps (research, configuration-only, docs-only) are fine when they are not a PR.

Each PR:

  • Leaves the product fully working. New behavior may land incrementally and only be “complete” in a later PR. Do not break existing functionality unless the payoff is clearly worth it — call that out for discussion.
  • Is one logical chunk: not a dump, not a drive-by. Split or merge only when it makes implementation easier.
  • Ships tests with the change. Deferring tests (e.g. e2e until the feature is whole) is OK if the plan says what is deferred, to which PR, and why.

Read the full file on GitHub · 128 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. 9d ago First seen · 128 lines · 0 tokens per session scan A 741330121835

Subscribe to this mod's changes

design-with-questions is a command published in the GitHub repository codeready-toolchain/tarsy (10 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,178 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 2026-08-31.