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 SerenecoTech/agent-skills --skill mac-design-exploregit clone --depth 1 https://github.com/SerenecoTech/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/serenecotech/agent-skills/mac-design-explore)<a href="https://agentmods.dev/skills/serenecotech/agent-skills/mac-design-explore"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/mac-design-explore/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/serenecotech/agent-skills/mac-design-explore"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/mac-design-explore.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.03471 |
| Opus 5.5 | $0.00021 | $0.01388 |
| Sonnet 5.5 | $0.00010 | $0.00694 |
| Haiku 4.5 | $0.00005 | $0.00347 |
Grade A, and why
mac-design-explore 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 12d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Native macOS design exploration
Help the user choose an interface by comparing real native implementations against the same task. Build, inspect, choose, and remix. Treat tool results and captured output as evidence; treat design judgments as hypotheses until tested.
Entry point
Select from the request without a mode-selection question:
- Explore: compare different approaches to the same task, then await the user's choice unless autonomous selection was authorized.
- Refine: capture a baseline of a specified view or chosen direction, define the visible outcome, and make a scoped correction. Work in a temporary copy unless the user authorized a product fix. Preserve its structure except for changes explicitly requested in a remix or redesign.
- Check setup: inspect the project and available capabilities read-only. Use section 2's discovery guidance and relevant tool references, but skip its build/launch/capture proof and all other execution steps. Report available, unavailable, and unverified capabilities, what each limitation prevents, and the next useful step. Stop without creating files, building, launching, installing, or changing configuration.
Implementing an already agreed feature or fixing an unrelated functional bug belongs to ordinary development. When an ambiguous request fits that work better, leave this workflow out. A request to fix the actual app authorizes that scoped product edit; no special word such as "apply" is required, and existing authorization persists. A request to explore, show a prototype, or choose a favorite does not authorize production integration. If refinement's destination is genuinely unclear, proceed in a temporary copy and show it; clarify only before integrating.
Isolation, retention, and recovery
For explore/refine, inspect project instructions, build configuration, and existing edits first. Create a unique OS temporary workspace and announce its absolute path. Put prototypes, fixtures, build output, logs, images, and a compact run-notes.md there. This file is an evidence index and recovery aid, not a project planning system. Keep project-level workflow/state files out of the repository.
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.
- 12d ago First seen · 109 lines · 52 tokens per session scan A 128a62f00687
mac-design-explore is a skill published in the GitHub repository SerenecoTech/agent-skills (3 stars, last pushed 12d ago), licensed MIT. It adds 52 tokens to every session and 3,471 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
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 $ultragoal 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.