discovery-question-form

discovery-question-form is a skill for Claude Code, Codex from nexu-io/open-design. It costs 13 tokens per session (887 once invoked), scanned A, original, Apache-2.0.

A structured form for asking focused clarification questions when important project requirements are still unresolved. It returns the user's answers in a format the workflow can use.

In plain words
What is it for?
Collecting the minimum missing information needed before starting a design or content workflow.
Why use it?
It prevents the agent from guessing about decisions that could materially change the design, content, or delivery format.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Collecting the minimum missing information needed before starting a design or content workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nexu-io/open-design/discovery-question-form
About the project

OpenDesign is an open-source, local-first desktop app that lets coding agents create prototypes, dashboards, slide decks, images, video, and design systems as exportable files. It is used by people working with agent runtimes such as Claude Code, Codex, Cursor, and DeepSeek Harness. The catalogue add-ons extend the OpenDesign workflow with skills, instructions, commands, and plugins.

nexu-io/open-design · 95,021 stars · on GitHub · open-design.ai

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 nexu-io/open-design --skill discovery-question-form
Clone the repo
git clone --depth 1 https://github.com/nexu-io/open-design

Made for: Claude Code, Codex.

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 discovery-question-form

README.md
[![agentmods](https://agentmods.dev/badge/skills/nexu-io/open-design/discovery-question-form/github.svg)](https://agentmods.dev/skills/nexu-io/open-design/discovery-question-form)
Your own site
<a href="https://agentmods.dev/skills/nexu-io/open-design/discovery-question-form"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/discovery-question-form/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 discovery-question-form

Your own site · 80×15
<a href="https://agentmods.dev/skills/nexu-io/open-design/discovery-question-form"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/discovery-question-form.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 887 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. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00013 $0.00887
Opus 5 $0.00006 $0.00443
Sonnet 5 $0.00003 $0.00177
Haiku 4.5 $0.00001 $0.00089

Measured yesterday against content hash bf66980e3bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

discovery-question-form 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 yesterday.

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/_official/atoms/discovery-question-form/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discovery question form

This atom defines the <question-form> protocol. It does not decide whether clarification is required. Follow the active skill and core prompt's requirements-clarification policy. When they identify unresolved information that would materially change the design direction, content structure, or delivery format, surface the smallest possible set of questions that unblocks the workflow.

The questions are rendered as a <question-form> artifact inline in the originating assistant message. This is assistant text parsed by the host, not a plugin GenUI surface or a native tool call. Submitted answers return as the next user message, beginning with [form answers — <form-id>].

Activation boundary

  • A first turn or new project does not by itself require a form.
  • A discovery pipeline stage only makes this protocol available; declaring or entering the stage does not trigger a form.
  • Missing metadata is not automatically a question. First use the request, conversation, plugin inputs, memory, active skill, and design system.
  • If enough information is available to proceed safely, do not emit a form.
  • If a material blocker remains, ask only for that unresolved information.

Emission shape

Emit the form as a question-form block whose body is a JSON object with a top-level questions array. Do not emit a bare question object by itself; the renderer only recognizes the wrapped form contract.

<question-form id="discovery" title="Quick brief — 30 seconds">
{
  "description": "I'll lock these in before building. Skip what doesn't apply — I'll fill defaults.",
  "questions": [
    {
      "id": "audience",
      "label": "Who's the primary audience?",
      "type": "checkbox",
      "options": ["VC", "Customer", "Internal team"],
      "maxSelections": 2,
      "required": true
    }
  ]
}
</question-form>

Question object shape

Each entry in the top-level questions array uses:

  • id: stable answer key, for example audience.
  • label: user-facing question copy.
  • type: one of radio, checkbox, select, text, textarea, number, range, date, time, datetime-local, color, url, email, tel, file, or switch.
  • options: required for choice controls; strings are allowed, or objects with localized label and stable value.
  • At most 6-7 options per question; merge near-duplicates instead of listing more.
  • Choose radio vs select by option count, not importance: radio for a short list, select once it runs long (languages, timezones, voices). checkbox is always a plain list.
  • select options may carry group (first group expands, the rest collapse) and trailingLabel (a short end-of-row code such as ZH-CN). Both optional.
  • Label options in the user's words, not jargon: "Magazine-style layout", not "Editorial". Reword only label; never change a stable value.
  • Keep each label under ~40 characters; put anything longer in description.
  • allowCustom: leave unset or set to true for finite-choice controls so users can type their own answer instead of accepting only generated options. Set allowCustom: false only when the downstream system needs an exact machine id.
  • customLabel / customPlaceholder: optional localized copy for that custom answer input.
  • maxSelections: include this for checkbox controls with a limited selection count.
  • required: set to true only when the answer is needed before work can continue.

Read the full file on GitHub · 90 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday Changed · +5 lines bf66980e3bcd
  2. 6d ago First seen · 85 lines · 13 tokens per session scan A 8daefdaadfcd

Subscribe to this mod's changes

discovery-question-form is a skill published in the GitHub repository nexu-io/open-design (95,021 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 887 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 2026-09-03.