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 Appllama/appllama-skills --skill appllama-usagegit clone --depth 1 https://github.com/Appllama/appllama-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/appllama/appllama-skills/appllama-usage)<a href="https://agentmods.dev/skills/appllama/appllama-skills/appllama-usage"><img src="https://agentmods.dev/badge/skills/appllama/appllama-skills/appllama-usage/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/appllama/appllama-skills/appllama-usage"><img src="https://agentmods.dev/badge/skills/appllama/appllama-skills/appllama-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector 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 | $0.00124 | $0.01563 |
| Opus 5 | $0.00062 | $0.00781 |
| Sonnet 5 | $0.00025 | $0.00313 |
| Haiku 4.5 | $0.00012 | $0.00156 |
Grade A, and why
appllama-usage 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 10d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Appllama Usage Skill
Appllama is the design library of top-grossing mobile apps — their real screens, flows, and UI patterns, with revenue and download context. The MCP puts that library in an agent's hands: not just a research tool, a builder's tool. You study what already wins, then you build something better.
Pair this skill with appllama-app-design-skill for every design/implementation step — this skill tells you what to study; that one tells you how to build.
Ground rules (read first)
- Start with
get_credits— it's free. It tells you the balance, limits, and reset date. Pro includes 1,500 credits a month (they reset in full on the 1st, UTC); every other call spends 1 credit. - Go deep. Design language lives in the whole journey, not a sample — walk every screen of the apps that matter for the task, images included. That is exactly what the library is for. The one thing that's against the terms is harvesting: sweeping the catalog to extract the dataset itself rather than to answer a real task. That isn't research, and it's detected server-side.
- Media URLs expire in ~1 hour. Download/view what you study promptly. If links died mid-task, re-request that page for fresh ones — screen ids are durable, links are not.
- Ignore the watermark. Every Appllama image and video carries a small Appllama watermark in the top-left corner. It is provenance, not part of the screen — don't let it skew your read of that corner (status bar, back button, title), and never reproduce it in anything you build.
- Pagination is sequential. Every list response carries
next_cursor; pass it back to continue. You cannot jump to page N — and a cursor only works for the same query that minted it. If a cursor errors, drop it and restart from page one. - If you hit a rate limit, wait it out. The per-minute and per-day limits sit far above real research; on the rare hit, wait the stated time — don't retry-hammer.
- Errors are instructions. Tool errors are written to be acted on (expired cursor → restart; out of credits → tell the user their credits reset on the 1st and they can request more in Settings → Usage).
What ships with it
4 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.
- 10d ago First seen · 102 lines · 124 tokens per session scan A 2d0c706a5c43
appllama-usage is a skill published in the GitHub repository Appllama/appllama-skills (1,240 stars, last pushed 3d ago), licensed MIT. It adds 124 tokens to every session and 1,563 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
Other skills, from other repositories
excalidraw
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .excalidraw files and exports to PNG/SVG via Kroki API or locally using…
subagent-driven-prototyping
Builds a prototype component by component, self-reviewing each component against the Discovery Plan before moving to the next. Invoked by prototype-builder after the layout direction is confirmed. Trigger phrases: "build the prototype", "let's build it", "start building". Also invoked by prototype-builder-agent after…
visual-companion
Presents layout options to the SME in plain language before any prototype construction begins. Invoked after the Discovery Plan is approved to confirm visual structure and direction. Trigger phrases: "what should it look like", "show me some layout options", "let me see the design options before we build". Also…
prototype-builder
Orchestrates the full prototype build cycle for a Subject Matter Expert. Coordinates layout confirmation and component building — it does not build components directly. Acts as the single entry point for all prototype-related requests. Trigger phrases: "build a prototype", "create a working prototype", "show me a…
vibe-browser-audit
A visual & functional crawler operation utilizing Chrome DevTools Protocol (CDP) or Playwright/Puppeteer to audit prototype UI/UX and behavior.
convert-mermaid
Translate .mmd diagram files into PNG images with configurable resolution (retina/HQ/scale), supporting rasterization (raster, rasterize, rasterization). V2 includes L5 Delegated Constraint Verification via verifypng for strict binary linting and Puppeteer-based rendering.