A command for reviewing an existing product and creating a prioritized plan to improve its user experience. It examines the product and repository, then checks the findings with the owner or records them for later review.

Use it to audit a repository or deployed product, reconstruct users and journeys, validate findings, identify gaps, and produce a prioritized UX improvement specification.

It gives products built without formal user-experience documents a structured way to uncover problems and improvement opportunities. It also preserves existing feedback instead of making the audit start from scratch.

optimize — 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/optimize

Clone the repo

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

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 278 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	$0.00014	$0.00278
Opus 5	$0.00007	$0.00139
Sonnet 5	$0.00003	$0.00056
Haiku 4.5	$0.00001	$0.00028

Measured yesterday against content hash 60bfe98fcd53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimize 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/optimize.md · 23 lines

What it actually says

Start a reverse-pass UX audit using the ux-optimization skill.

If $ARGUMENTS names a repository path or product, use it as the audit target. Otherwise ask the user what product to audit — a repo path is the minimum input.
Read .product-dev/context.json:
- If it doesn't exist, the skill creates a new project with "mode": "reverse".
- If a forward-pass project exists in this directory, confirm before proceeding — the reverse pass writes the same artifact names (initial_concept, problem_statement, proto_persona, user_flow) and would version over them.
Ask two setup questions before extraction begins:
- Is the user the product owner (live validation) or a reviewer (deferred validation, flags propagate)?
- Do they have existing tactical feedback to integrate? If yes, save it as the existing_feedback artifact first.
Hand off to the ux-optimization skill for the full sequence: extraction (subagents) → synthesis → validation checkpoint → gap analysis → optimization spec.

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 · 23 lines · 14 tokens per session scan A 60bfe98fcd53

Subscribe to this mod's changes

optimize is a command published in the GitHub repository clownware/product-dev (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 14 tokens to every session and 278 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.

Code review Data and AI Frontend 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