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 sleekdotdesign/agent-skills --skill design-mobile-appsgit clone --depth 1 https://github.com/sleekdotdesign/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/sleekdotdesign/agent-skills/design-mobile-apps)<a href="https://agentmods.dev/skills/sleekdotdesign/agent-skills/design-mobile-apps"><img src="https://agentmods.dev/badge/skills/sleekdotdesign/agent-skills/design-mobile-apps/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/sleekdotdesign/agent-skills/design-mobile-apps"><img src="https://agentmods.dev/badge/skills/sleekdotdesign/agent-skills/design-mobile-apps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 19 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 47 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- high Data Exfiltration · line 215 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- high Tool Misuse · line 266 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Prompt Injection · line 486 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Data Exfiltration · line 187 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 190 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Tool Misuse · line 323 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Prompt Injection · line 368 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 482 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 484 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 485 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 487 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 490 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 491 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 492 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 493 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 494 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 555 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 495 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00030 | $0.01930 |
| Opus 5.5 | $0.00012 | $0.00772 |
| Sonnet 5.5 | $0.00006 | $0.00386 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
sleek-design-mobile-apps scanned grade A with 1 finding 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 20d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Parsing responses**: write the body to a file (`curl -o run.json`) and parse the file. Piping JSON through `echo` corrupts it: zsh expands the escaped `\n` inside string values into real newlines, which makes the body How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designing with Sleek
Overview
sleek.design provides a REST API at /api/v1/* to create projects, design screens from a brief, and fetch their HTML and renders.
Base URL: https://sleek.design
Auth: Authorization: Bearer $SLEEK_API_KEY, except the public device start/poll endpoints
Content-Type: send application/json for JSON request bodies.
CORS: Enabled on all /api/v1/* endpoints
Envelope: check HTTP status first. Successful JSON wraps its payload in data; lists also include sibling pagination. Errors use top-level code, status and message, with optional data.url. Successful screenshots and share cards return image bytes; 204 has no body.
Ids: opaque 11-character tokens like V1StGXR8Z5j, with no type prefix. Nothing about an id says whether it names a project, screen, component, version or theme, so track each one by the response field it arrived in.
Parsing responses: write the body to a file (curl -o run.json) and parse the file. Piping JSON through echo corrupts it: zsh expands the escaped \n inside string values into real newlines, which makes the body invalid JSON.
API docs: OpenAPI spec at https://sleek.design/api/v1/spec.json; browsable docs at https://sleek.design/api/v1/docs. Fetch the spec for any contract detail not covered here.
Designing or implementing
A single run can take both directions — "design me a fitness app and build it in Expo" is a design pass followed by an implementation pass. Gate each pointer on the artefact in front of you rather than on a one-time reading of the request:
Designing — you are about to send a chat message to Sleek. Read designing.md first; it carries the create → chat → screenshot loop, how to author a style direction, and when to seed one from a reference instead.
What ships with it
6 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.
- 20d ago Changed · -446 lines · -21 tokens per session 25586a3c431b
- 24d ago Changed 19ef7520c986
- 1mo ago Changed · +1 lines f648637fb793
- 1mo ago First seen · 564 lines · 51 tokens per session scan A eb1afcae224d
sleek-design-mobile-apps is a skill published in the GitHub repository sleekdotdesign/agent-skills (591 stars, last pushed 21d ago), licensed MIT. It adds 30 tokens to every session and 1,930 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
refero-design
Primary/default skill for UI design, product design, web design, landing pages, dashboards, product screens, redesigns, visual polish, frontend/CSS styling, design systems, components, responsive design, typography, color, spacing, motion, icons, accessibility, copywriting, conversion, and anti-AI-slop work. Use this…
compose-ui
Writes and reviews composables for Compose and CMP: the Route/Screen/leaf split, state-read placement and stability, loading/empty/error UX states, LazyColumn lists and grids, animation choice, accessibility and semantics, design-system tokens, CMP Res resources, Coil images, and keyboard/focus. Use when touching…
cometchat-flutter-v6-customization
Theme and brand the Flutter v6 UI Kit — light/dark mode, the CometChatColorPalette / CometChatTypography / CometChatSpacing theme extensions, per-widget style objects, and view slots. Triggers: 'change chat colors flutter', 'dark mode chat flutter', 'match my brand flutter', 'customize cometchat theme flutter'…
build-swiftui-interface
Use when a coding agent must design, scaffold, implement, or verify an iOS or macOS SwiftUI interface with Apple-platform state, accessibility, availability, testing, and Xcode evidence.
Audit Apple-platform UI work against Human Interface Guidelines with HIG Doctor
Run a repeatable HIG compliance audit over app code before shipping UI changes, then use the findings to guide remediation.
generate-figma-screen
Kod veya açıklamadan Figma'da tam ekran/sayfa oluşturur. Yayınlanmış design system bileşenlerini arayıp instance olarak yerleştirir; hardcode değer yerine DS token'larını kullanır. "Figma'da ekran oluştur", "kodu Figma'ya çevir", "landing page çiz", "ekran tasarla", "generate screen", "UI'ı Figma'ya aktar"…