Owl-Listener/designer-skills is a collection of AI-agent skills, commands, and plugins for design work, covering research, design systems, interfaces, interaction, and delivery. Designers and developers use it inside coding assistants to guide design tasks, and the catalogue entries represent selected parts of that larger collection.
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.
git clone --depth 1 https://github.com/Owl-Listener/designer-skillsWrote 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.
[](https://agentmods.dev/commands/owl-listener/designer-skills/start-here)<a href="https://agentmods.dev/commands/owl-listener/designer-skills/start-here"><img src="https://agentmods.dev/badge/commands/owl-listener/designer-skills/start-here.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00033 | $0.01331 |
| Opus 5 | $0.00016 | $0.00665 |
| Sonnet 5 | $0.00007 | $0.00266 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
start-here 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 3d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start-here
Route a designer to one entry point in the collection, then get out of the way.
Steps
- Read the situation — Place what the user gave you on two axes: how much is already decided (nothing, a problem, a direction, a built screen), and what they owe someone (a decision, a spec, a critique, a plan). If they gave you nothing, or gave you a mood rather than a situation — "it feels off", "something's wrong" — ask the one question that would place it, then route. One question, not three.
- Name the stage — Say which stage they are in and why, in one line. The stages run understand → frame → explore → make → validate → ship. Naming it wrong costs more than any later step, so state it plainly and let them correct you.
- Route to one command — Give exactly one entry point from the map below, never a menu. If two fit, pick the earlier stage: starting upstream is cheap, discovering you skipped a stage after the work is built is not. If the request holds two jobs — build it and prove it worked — route the first and name the second as what follows.
- Say when it isn't here — If nothing in the map fits, say so and name the collection that does, rather than routing to the nearest row. Hiring, growth, and org work are
design-leadership-skills. Running a programme — roadmaps, stakeholders, delivery — isux-pgm-skills. Designing an AI product's behaviour isai-design-skills. Accessibility has an audit and a test plan here, as skills rather than commands, so name those before sending anyone away; the depth — cognitive, adaptive, multi-modal — isinclusive-design-skills. A confident wrong route costs more than an honest "not in this collection". - Show the sequence — Name the two commands that follow, so the path is visible rather than implied, and say which stages this particular job can skip and why.
- Hand off — Run the routed command, or state the exact line to type. If its plugin is not installed, give the install command first:
/plugin install <plugin>@designer-skills. Do not summarise the collection.
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.
- 3d ago First seen · 38 lines · 33 tokens per session scan A 4da5f543a8f7
start-here is a command published in the GitHub repository Owl-Listener/designer-skills (2,572 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 1,331 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 2026-09-05.
Other commands, from other repositories
hatch3r-design-system-create
Create a project design system from brand assets or an elicitation dialog — DTCG 2025.10 token emission, 3-tier taxonomy (primitive → semantic → component), OKLCH ramps, dual output design.md + design-tokens.json, gated on WCAG 2.2 AA contrast, 100% theme parity, and 0 dangling aliases.
build_dashboard
Design & build a dense SaaS dashboard or app shell — navigation, tables, empty/loading states, a generated product-UI system — not a marketing page in disguise.
port_to_platform
Take an existing design or implementation to another platform (iOS ↔ Android ↔ macOS ↔ web) — porting the intent and IA, not the components.
redesign
Improve an existing UI (bolder, quieter, cleaner, higher-converting) using SaglitzDesign craft standards, with measured before→after.
critique_screenshot
Grounded, reproducible visual critique of an attached UI screenshot against the fixed 0–40 rubric — cites specific elements, no padding.
design_review
Audit an existing website / app / landing page against SaglitzDesign checklists, the deterministic auditors, and the 0–40 critique rubric.