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 screensdesign-com/screensdesign-agent-skill --skill screensdesign-datagit clone --depth 1 https://github.com/screensdesign-com/screensdesign-agent-skillWrote 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/screensdesign-com/screensdesign-agent-skill/screensdesign-data)<a href="https://agentmods.dev/skills/screensdesign-com/screensdesign-agent-skill/screensdesign-data"><img src="https://agentmods.dev/badge/skills/screensdesign-com/screensdesign-agent-skill/screensdesign-data/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/screensdesign-com/screensdesign-agent-skill/screensdesign-data"><img src="https://agentmods.dev/badge/skills/screensdesign-com/screensdesign-agent-skill/screensdesign-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00091 | $0.02084 |
| Opus 5.5 | $0.00036 | $0.00834 |
| Sonnet 5.5 | $0.00018 | $0.00417 |
| Haiku 4.5 | $0.00009 | $0.00208 |
Grade A, and why
screensdesign-data 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 2mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ScreensDesign Data
Release: 1.0.8 · MCP contract: 2
Use ScreensDesign as an evidence-first mobile-app research source. Its hosted MCP is read-only and returns public app links, recorded-product evidence, App Store creatives, performance estimates, and saved collection context.
Check This Skill Once
When get_screensdesign_skill is available, call it once per conversation before the first ScreensDesign research call and pass installed_version="1.0.8".
- If the status is
current, continue without discussing the check. - If it is
update_available, continue when compatible and briefly tell the user an update exists. - If it is
incompatible, ask to update before relying on workflows whose contracts may have changed. - If the check tool is unavailable, continue with the live tool schemas. Never repeat the check in the same conversation.
The live MCP tool name, description, and input schema override local examples when they disagree with this skill.
Load Only What You Need
| User intent | Read |
|---|---|
| Find apps, compare competitors, inspect an app URL, or research developers | workflows/app-research.md |
| Discover broader-market apps, find semantic competitors, inspect public listings, or analyze App Store reviews | workflows/market-research.md |
| Find recorded screens, verify sequence, inspect flows, compare paywalls, use an attached image, or research App Store creatives | workflows/screen-research.md |
| Filter apps by detected onboarding/paywall patterns and counts | workflows/app-intelligence.md |
| Read the user's saved app collections | workflows/saved-research.md |
| Suggest useful next research after answering | workflows/completion-followups.md |
| Need exact tool parameters and limits | references/tools.md |
| Need returned field meanings | references/response-fields.md |
| Need authentication or setup help | references/connection.md |
Research Workflow
- Identify the entity, scope, platform, time frame, and comparison criteria.
- Start with the narrowest useful discovery call and apply filters early.
- Resolve exact apps, screens, or flows from returned results. Reuse returned identifiers; never invent them.
- Inspect only the records needed to support the answer. For visual or sequence claims, use screen, flow, or replay evidence rather than app metadata alone.
- Stop once the evidence supports a useful answer. Do not repeat successful calls with unchanged arguments.
What ships with it
10 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.
- agents/openai.yaml 581 B
- references/connection.md 2.3 KB
- references/response-fields.md 9.3 KB
- references/tools.md 11 KB
- workflows/app-intelligence.md 1.7 KB
- workflows/app-research.md 2.3 KB
- workflows/completion-followups.md 2.4 KB
- workflows/market-research.md 3.2 KB
- workflows/saved-research.md 1.0 KB
- workflows/screen-research.md 3.6 KB
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.
- 2mo ago First seen · 105 lines · 91 tokens per session scan A 2ceb1726fbaa
screensdesign-data is a skill published in the GitHub repository screensdesign-com/screensdesign-agent-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 2,084 once invoked, about $0.0004 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 2026-08-31.
screensdesign-data compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| screensdesign-datascreensdesign-com/screensdesign-agent-skill | Skill | 3 | 1mo ago | MIT | A | 91 | Codex |
| implementation-guidershankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 40 | Claude Code |
| architecture-specrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 39 | Claude Code |
| foundation-modelsrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 29 | Claude Code |
| liquid-glassrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 45 | Claude Code |
| charts-3drshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 61 | Claude Code |
| app-intentsrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 47 | Claude Code |