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.
npx agentmods add skills/clownware/product-dev/ux-optimizationnpx skills add clownware/product-dev --skill ux-optimizationgit clone --depth 1 https://github.com/clownware/product-devWhat 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 | $0.00049 | $0.01682 |
| Opus 5 | $0.00024 | $0.00841 |
| Sonnet 5 | $0.00010 | $0.00336 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
ux-optimization 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a UX strategist auditing an existing product (ADR 0013). The forward-pass skills elicit truth from the user; this skill extracts it from a repository and then earns owner confirmation. Extracted artifacts are claims with evidence grades, not facts — provenance and confidence are first-class throughout.
Entry
- Identify the target: a repository path (or deployed product plus repo) from
$ARGUMENTSor conversation. If none is given, ask for it — there is no reverse pass without a target. - Read
.product-dev/context.json. If absent, runcreateProjectwith"mode": "reverse". If a forward-pass project exists, confirm before mixing modes. - Ask whether the user is the product owner — this determines how the validation checkpoint runs (owner validates live vs. flags propagate for later owner review).
- If the user has pre-existing tactical feedback (their own notes, a reviewer's list), save it verbatim as
existing_feedbackin the registry — the final spec integrates it.
Prompt Sequence
Prompts live in ${CLAUDE_PLUGIN_ROOT}/prompts/07_ux_optimization/:
| Step | Prompt | Run | Produces |
|---|---|---|---|
| 1 | 01_product_archaeology.md |
entry_point | initial_concept |
| 2 | 02_evidence_mining.md |
context_gated | problem_statement |
| 3 | 03_journey_tracing.md |
always | user_flow |
| 4 | 04_persona_extraction.md |
always | proto_persona |
| 5 | 05_value_prop_synthesis.md |
always | value_prop_inventory |
| 6 | 06_validation_checkpoint.md |
always | validation_log |
| 7 | 07_objective_metrics.md |
always | core_objective |
| 8 | 08_gap_analysis.md |
always | hypothesis_backlog |
| 9 | 09_optimization_spec.md |
always | optimization_spec |
| 10 | 10_live_site_audit.md |
context_gated (Tier 2) | live_site_audit |
| 11 | 11_runtime_audit.md |
context_gated (Tier 2) | runtime_audit |
Step 2 gate: "Target repo contains research, interview, marketing, or outreach material." When skipping: "No research or marketing material found — skipping evidence mining. The problem statement will be inferred from code and README only, at reduced confidence. If research exists elsewhere (notes, call transcripts), share it and we'll run this step."
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.
- 2d ago First seen · 73 lines · 49 tokens per session scan A 8e7278e2e3e6
ux-optimization is a skill published in the GitHub repository clownware/product-dev (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,682 once invoked, about $0.0002 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.
Other skills, from other repositories
feature-flags
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
frontend-unit-testing
Write comprehensive, behaviour-driven unit tests for Gradio frontend Svelte components using Vitest browser mode, Playwright, and the @self/tootils test utilities.
gradio-themes
Build and customise Gradio themes. Use when creating, editing, or publishing Python-based Gradio themes that control colours, typography, spacing, shadows, and dark mode.
hf-gradio
Use Gradio applications via API. Use when the user asks for to generate a prediction from a Gradio app on Hugging Face spaces or public URL. For example, "Generate an image using black-forest-labs/FLUX.2-dev".
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.
flags
Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.