A command for starting a structured exploration of a product idea or problem area. It creates a project record and guides a conversation through early user-experience research.

Use it to start a new product project, capture an initial concept, explore a problem domain, and continue toward a defined problem, user, objective, solution, and testable hypothesis.

It gives an unformed idea a clear starting point and keeps the resulting decisions and documents in the project. It can begin with either a specific idea or a broader area of interest.

idea — Command by clownware

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/clownware/product-dev/idea

Clone the repo

git clone --depth 1 https://github.com/clownware/product-dev

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 321 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.

Model	Per session	Once invoked
Fable 5	$0.00010	$0.00321
Opus 5	$0.00005	$0.00161
Sonnet 5	$0.00002	$0.00064
Haiku 4.5	$0.00001	$0.00032

Measured yesterday against content hash 6a961231a890, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

idea 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.

plugin/commands/idea.md · 28 lines

What it actually says

Start a product ideation session using the product-ideation skill.

Setup

Check if .product-dev/context.json exists in the working directory.
- If not, create the project: initialize .product-dev/context.json with timestamps, tier: 1, empty artifacts and prompts_executed. Ask the user for a project name.
- If it exists, read it and briefly note existing progress.
Determine entry point from user input:
- If $ARGUMENTS contains a specific product idea (e.g., "tea tracking app") → use capture_idea prompt
- If $ARGUMENTS describes a domain interest (e.g., "problems in specialty tea") → use explore_problem prompt
- If no arguments provided → ask: "What's on your mind? Tell me about the idea, problem, or space you're interested in."
Read the selected prompt from ${CLAUDE_PLUGIN_ROOT}/prompts/01_ux_research/00_fuzzy_front_end/ and execute it.
After producing output, write the artifact to .product-dev/artifacts/initial_concept.md and update the registry.
Continue the product-ideation skill flow: advance through the prompt chain conversationally, checking tier escalation signals after each user response.

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.

yesterday First seen · 28 lines · 10 tokens per session scan A 6a961231a890

Subscribe to this mod's changes

idea is a command published in the GitHub repository clownware/product-dev (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 10 tokens to every session and 321 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.

Data and AI Frontend Research claude-code claude-code-plugin claude-skills mcp prompt-toolkit ui

start

Front door. Reads the current project (framework, tokens, brief, spec, harness) and reports what ui-craft can do right now, then routes you to the right next step. Run this first if you're new or unsure where to begin. No code changes.

educlopez/ui-craft · 54 tokens

tokens

Audit or establish the project's 3-layer token spine.

educlopez/ui-craft · 11 tokens

remember

Record a learned design constraint from a correction into the project brief.

educlopez/ui-craft · 13 tokens

craft

One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface ("build me a dashboard", "I need a landing page") and expects a shippable result, not component-level help.

educlopez/ui-craft · 64 tokens

audit

Technical UI audit — a11y, performance, responsive. Produces a prioritized findings table.

educlopez/ui-craft · 19 tokens

brief

Write or update the project's durable design brief at .ui-craft/brief.md.

educlopez/ui-craft · 17 tokens