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 fledgeling-co/fledgeling-plugins --skill mac-craftgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/mac-craft)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/mac-craft"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/mac-craft/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/fledgeling-co/fledgeling-plugins/mac-craft"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/mac-craft.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 | $0.00222 | $0.06591 |
| Opus 5.5 | $0.00089 | $0.02636 |
| Sonnet 5.5 | $0.00044 | $0.01318 |
| Haiku 4.5 | $0.00022 | $0.00659 |
Grade A, and why
mac-craft 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 1mo 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mac-craft
Design macOS app interfaces that are native to the platform (correct), committed to a direction (beautiful), and distinct from each other (varied) — and prove the first of those three with a script rather than a sentence.
First, two quick exits. If the request is empty, ask in one line what surface to design
and for what app, then stop. If it is a bare word that names something designable — settings,
onboarding, empty state, toolbar — that is a brief: design it. Do not design
something called "settings".
Icons are not designed here. An icon request routes to create-mac-icon:create-mac-icon, in full,
including the "make an icon for my app" phrasing this skill's description used to claim. See
§ Icons at the end: it is a five-line handoff, not a fallback pipeline, because two drifting
copies of an icon catalogue are worse than one honest gap.
Using Gemini? Read gemini.md for this skill's task-specific calibration and artifact checks. Its older runs do not establish Gemini 3.8 capability limits: preserve the user's selected implementation lane, and apply a model-specific route only when the current model or an observed failure supports it.
What a finished commission looks like on disk
Learn the anatomy before building it.
<app-slug>-<surface>.html the mock. Named from the app, never mock/index/design.html
<app-slug>-<surface>-dark.html only if light and dark are separate files rather than one
captures/ one PNG per surface × state × appearance, all of them opened
<app-slug>-spec.md direction + runner-up + signature + risk · state matrix ·
token table · audit scores · what you did NOT check
The token table is the source; the mock is the output. That is the re-entrancy contract and it decides what a second run does — see § Running this twice.
Knowledge sources — load before designing
The corpus, first — it ships with this marketplace. mac-design-digest:mac-design-digest maintains it and
this skill reads it; the two are one pipeline. Resolve it in this order and take the first that
exists:
What ships with it
32 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.
- assets/fixtures/ledgerline-accounts.html 7.0 KB
- assets/fixtures/mock.html 2.7 KB
- evals/evals.json 8.8 KB
- evals/panel-iteration-1/judge_panel.sh 5.5 KB runs code
- evals/panel-iteration-1/mapping.json 52 B
- evals/panel-iteration-1/prompt.md 1.4 KB
- evals/panel-iteration-1/verdict-anthropic.txt 1.4 KB
- evals/panel-iteration-1/verdict-google.txt 825 B
- evals/panel-iteration-1/verdict-openai.txt 86 B
- evals/panel-iteration-1/verdict-xai.txt 684 B
- evals/results-iteration-1.md 6.4 KB
- gemini.md 21 KB
- references/content-area-ideation.md 3.4 KB
- references/corpus-evidence.md 18 KB
- references/design-directions.md 25 KB
- references/evidence.md 19 KB
- references/kit-macos-27.md 10 KB
- references/mac-essence.md 9.1 KB
- references/model-calibration.md 7.0 KB
- references/motion-and-feel.md 7.6 KB
- references/native-foundation.md 18 KB
- references/patterns/card-grid.md 6.7 KB
- references/patterns/empty-state.md 5.4 KB
- references/patterns/floating-panel.md 7.6 KB
- references/patterns/list-table.md 7.8 KB
- references/patterns/menu-bar-extra.md 7.2 KB
- references/patterns/onboarding.md 5.0 KB
- references/patterns/settings.md 7.3 KB
- references/patterns/sidebar.md 7.6 KB
- references/patterns/toolbar.md 7.3 KB
- scripts/gate_tests.sh 8.4 KB runs code
- scripts/mock_check.py 61 KB runs code
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.
- 1mo ago Changed · -1 lines · +13 tokens per session b9e20de57ccf
- 1mo ago First seen · 375 lines · 209 tokens per session scan A 7b7b269b74eb
mac-craft is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 222 tokens to every session and 6,591 once invoked, about $0.0009 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 2026-09-04.
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.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.