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 aa-on-ai/agentic-design-system --skill visual-reference-calibrationgit clone --depth 1 https://github.com/aa-on-ai/agentic-design-systemWrote 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/aa-on-ai/agentic-design-system/visual-reference-calibration)<a href="https://agentmods.dev/skills/aa-on-ai/agentic-design-system/visual-reference-calibration"><img src="https://agentmods.dev/badge/skills/aa-on-ai/agentic-design-system/visual-reference-calibration.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 | $0.00098 | $0.01080 |
| Opus 5 | $0.00049 | $0.00540 |
| Sonnet 5 | $0.00020 | $0.00216 |
| Haiku 4.5 | $0.00010 | $0.00108 |
Grade A, and why
visual-reference-calibration 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 7d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Reference Calibration
Use this when the user points to a visual reference and wants a UI to borrow its feel, quality, interaction, surface treatment, motion, or style.
Do not use this merely because a screenshot is attached. If the screenshot only marks a bug, awkward edge, or region to review, treat it as evidence for the existing UI and continue with design-review.
This skill exists because we badly missed the Jhey CodePen portfolio-card task by translating a visual reference into implementation mechanics instead of design judgment.
Core rule
Do not code first.
First identify what the reference is actually contributing, confirm that with the user when ambiguous, then create or inspect a visual target before implementation.
Failure pattern to avoid
- Treating a reference as vague “inspiration” when the user expects close spirit/fidelity.
- Copying incidental structure from the reference, e.g. fake icons, overflow menus, app chrome.
- Implementing the mechanism while missing the visual quality.
- Making isolated component hover polish when the reference is a system-level effect.
- Shipping preview attempts before comparing side-by-side with the reference.
- Saying “I’m aligned” before being able to describe the reference in the user’s terms.
Required workflow
1. Build a reference contract
Before implementation, write a short contract. Use templates/reference-intake-contract.md when available:
Reference contract:
- Source/reference:
- What we are borrowing:
- What we are not borrowing:
- Fidelity target: close mimic / same spirit / loose cue
- Existing product constraints:
- Hard no’s:
- Review gate before code:
If any line is uncertain, ask the user before coding.
Hard rule: if you cannot state what to borrow, what not to borrow, and the fidelity target, you cannot build.
2. Ask the right calibration questions
Ask the smallest set that resolves ambiguity. Usually 1-3 questions, not a survey.
Use these in priority order:
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.
- 7d ago First seen · 120 lines · 98 tokens per session scan A e615548f3b2e
visual-reference-calibration is a skill published in the GitHub repository aa-on-ai/agentic-design-system (5 stars, last pushed 18d ago), licensed MIT. It adds 98 tokens to every session and 1,080 once invoked, about $0.0005 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).
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.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.