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 glifxyz/glif-mcp-server --skill app-promo-materialsgit clone --depth 1 https://github.com/glifxyz/glif-mcp-serverWrote 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/glifxyz/glif-mcp-server/app-promo-materials)<a href="https://agentmods.dev/skills/glifxyz/glif-mcp-server/app-promo-materials"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/app-promo-materials/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/glifxyz/glif-mcp-server/app-promo-materials"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/app-promo-materials.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 | $0.00246 | $0.01682 |
| Opus 5.5 | $0.00098 | $0.00673 |
| Sonnet 5.5 | $0.00049 | $0.00336 |
| Haiku 4.5 | $0.00025 | $0.00168 |
Grade A, and why
app-promo-materials 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 8d 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.
For a video or audio item in the set, such as a UGC clip or a jingle, write its brief in the same call the way the audio-and-video skill does: shots with camera and action, the exact script in quotes, or music mood, temp How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn a product into polished promo graphics. For an app, that means real screens. For anything else, it means the user's product photos and references. The user's explicit instructions come first, within host safety rules.
1. Pick the deliverables
Pin down the subject, audience, mood, formats and any references. Ask only about gaps that would change the result. Then pick deliverables from these menus, or the user's own list.
Store and launch sizes:
| Deliverable | Size (px) |
|---|---|
| iPhone App Store screenshots | 1320×2868 or 1290×2796, portrait |
| iPad App Store screenshots | 2064×2752, portrait |
| Google Play feature graphic | 1024×500 |
| Product Hunt gallery | 1270×760 |
| YouTube thumbnail | 1280×720 |
| X post | 1600×900 |
| LinkedIn post | 1200×627 |
| Square post | 1080×1080 |
| Feed post or carousel card (4:5) | 1080×1350, 3 to 6 cards |
| Story or Reel cover (9:16) | 1080×1920 |
| X header | 1500×500 |
Store rules change. Check App Store Connect and Play Console for the sizes they currently require. App Store screenshots must be PNG or JPEG with no transparency.
Campaign sets:
- Ad creative: UGC-style creator video (9:16, script, captions), product ad video, carousel (3 to 6 cards), static banners, unboxing.
- Product photos: studio hero on white, flat-lay, lifestyle scene, multi-angle set, detail close-up, what's in the box. Ask how many (2, 4 or 8) and keep the product identical to the user's photo.
- Social calendar: a week or a month of posts with captions and hashtags.
- Series: a repeatable format, such as a daily 40-second short. Save the recipe so each episode continues the same project.
Make the winner first, then resize it for each placement without cropping.
2. Gather real material
Promo graphics must show the real product. Don't invent screens, features, reviews, awards, press logos or partner logos. Turning real reviews into ads is fine when the user supplies them.
- Use the user's screenshots and product photos if they have them.
- For an app without screenshots, run it and capture screens with Playwright at the device size. For a 1320×2868 iPhone shot, use a 440×956 viewport with
deviceScaleFactor: 3. - Use demo data. Never capture real customer data, emails or keys.
What ships with it
1 file 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.
- 8d ago Changed · +13 lines · +76 tokens per session 12a8e9d3d60c
- 9d ago First seen · 82 lines · 170 tokens per session scan A 2c3b6a399b6b
app-promo-materials is a skill published in the GitHub repository glifxyz/glif-mcp-server (215 stars, last pushed 8d ago), licensed MIT. It adds 246 tokens to every session and 1,682 once invoked, about $0.0010 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 2026-10-08.
Other skills, from other repositories
atelier
Two-agent post-generation quality gate for vibe-coded applications. Deterministic, gradeable ruleset enforcing UI/UX design-system craft and backend architectural soundness.
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
n8n-subworkflows
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-binary-and-data
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…