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 skills add ohong/agent-skills --skill capture-designgit clone --depth 1 https://github.com/ohong/agent-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/skills/ohong/agent-skills/capture-design)<a href="https://agentmods.dev/skills/ohong/agent-skills/capture-design"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/capture-design.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 | $0.00029 | $0.01355 |
| Opus 5 | $0.00015 | $0.00678 |
| Sonnet 5 | $0.00006 | $0.00271 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
capture-design 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 8d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture Design
Turn reference assets containing a "target design" into a permanent, importable swipefile entry: a named design system, a full description document, and the saved references. The output must be complete enough that a design engineer or coding agent who has never seen the references can convincingly recreate or apply the aesthetic to a new website, app, or piece of hardware.
Inputs
The user provides one or more of:
- Images / screenshots — analyze qualitatively. Only state precise values (hex codes, px) you can actually sample or confidently infer; otherwise describe qualitatively ("warm gray plastic, roughly #9B968C–#A8A298").
- Live URLs — you have browser and computer-use tools; use them fully. Open the link, traverse the landing page plus 3–5 primary pages/flows, click around the site or app, hover elements, open modals and forms, and take screenshots as you go (these become references). Where DevTools/computed styles are accessible, extract exact colors, font stacks, sizes, spacing, shadows, and transition timings. Interactive states define much of a system's character — do whatever it takes to deeply study the reference, not just read the first page.
- Other media (video stills, PDFs, physical product photos, architecture) — extract what's visible; note the medium.
Use available image-analysis tools to sample colors when practical. Do not add a dependency solely for this workflow without the user's approval.
Workflow
- Save the references. Copy every provided asset into
references/at the project root, naming files descriptively (landing-hero.png,detail-typography.png). Do this first, and verify the files actually exist on disk before moving on — this step fails silently in some environments:- Images pasted into chat are often visible to you but never materialized as files (the uploads folder is empty). Check the uploads folder; if the assets aren't there, tell the user immediately and ask them to re-attach as files or connect a folder, then continue with the available material rather than blocking.
- Browser screenshots may not be persistable to disk in your session. Try the save option once; if unavailable, fall back to downloading the page's own image assets, or note the gap.
- If some assets truly cannot be saved, write a
references/{name}-sources.mdmanifest listing each missing asset with a description and source URL, so the user (or a future agent) can complete the folder manually. Never skip the references step without leaving this manifest and telling the user.
What ships with it
2 files 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.
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.
- 8d ago First seen · 54 lines · 29 tokens per session scan A c17c651d2372
capture-design is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 8d ago), licensed MIT. It adds 29 tokens to every session and 1,355 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.