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 agentmods add skills/verygoodplugins/streamdeck-mcp/streamdeck-designernpx skills add verygoodplugins/streamdeck-mcp --skill streamdeck-designergit clone --depth 1 https://github.com/verygoodplugins/streamdeck-mcpWhat 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 | $0.00167 | $0.04761 |
| Opus 5 | $0.00084 | $0.02380 |
| Sonnet 5 | $0.00033 | $0.00952 |
| Haiku 4.5 | $0.00017 | $0.00476 |
Grade A, and why
streamdeck-designer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://$HUE_BRIDGE_IP/api/$HUE_API_KEY/groups/1/action" \ How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stream Deck Designer
You are designing a Stream Deck layout for the user. The streamdeck-mcp tools let you author it directly to disk; the Elgato desktop app picks it up on next launch and the deck lights up exactly how you composed it. Your job is to produce something cohesive, useful, and visually considered — not a randomly-placed grid of icons.
A good authored deck:
- Has a deliberate palette and typography (not whatever colors land by accident).
- Reflects how the user actually works (their real apps, their real scenes, their real shortcuts).
- Runs standalone — every button does something even when Claude is offline.
- Tells the user what each control does without them having to guess.
Follow this authoring order
Resist the urge to start generating icons before the structure is decided. Every reordering of these steps increases the chance of wasted work.
1. Inventory the hardware before anything else
Call streamdeck_read_profiles first. The response has each profile's device.Model (raw Elgato product ID like 20GBX9901) and device.ModelName (human-readable, like "Stream Deck + XL"). Always use ModelName in your reasoning — the raw product ID is easy to mis-translate, especially between the four devices Elgato sells with "+" or "XL" in the name. If you see "Unknown Stream Deck model (<id>)", flag it to the user and ask what hardware they have.
Never assume a layout — Original (5×3), MK.2 (5×3), XL (8×4), Stream Deck + (4×2 keys + 4 dials, original 2022 Plus), Stream Deck + XL (9×4 keys + 6 dials + 1200×100 touchstrip, newer 2025 big Plus), Mini (3×2), and Neo (4×2) are all in active use, and the tradeoffs differ. See references/hardware.md for per-model guidance and the "+ vs + XL" disambiguation.
If you're replacing existing content, call streamdeck_read_page for the target page and inspect what's already there. Confirm with the user that overwriting is OK — a deck full of the user's prior work is precious, even if it looks generic.
What ships with it
13 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/env-template.txt 1.7 KB
- assets/recipes/dev-nordic.json 6.1 KB
- assets/recipes/music-retrowave.json 4.0 KB
- assets/recipes/streamer-hello-kitty.json 7.5 KB
- references/dials-and-touchstrip.md 7.8 KB
- references/hardware.md 7.5 KB
- references/icons.md 6.2 KB
- references/integrations.md 11 KB
- references/patterns.md 7.4 KB
- references/sdk-primer.md 10 KB
- references/sdk-urls.md 5.2 KB
- references/themes.md 5.6 KB
- references/troubleshooting.md 8.1 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.
- 2d ago First seen · 231 lines · 167 tokens per session scan A e360d46a10e9
streamdeck-designer is a skill published in the GitHub repository verygoodplugins/streamdeck-mcp (40 stars, last pushed 21d ago), licensed MIT. It adds 167 tokens to every session and 4,761 once invoked, about $0.0008 per session on Opus 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
HA Dashboard Design
Beautiful, copy-paste-ready Home Assistant dashboard designs with complete CSS themes, card-mod styles, and button-card templates. Nine distinct visual styles: Glassmorphism, Dark Minimal, Material You, Nordic, Neon/Cyberpunk, Warm Home, Soft Pastel, Luxury Gold, and Retro Terminal. Use this skill whenever the user…
ha-integration-knowledge
Everything you need to know to build, test and review Home Assistant Integrations. If you're looking at an integration, you must use this as your primary reference.
widget-design
Best practices for designing UI widgets in xmcp. Use when creating interactive widgets for GPT Apps or MCP Apps, choosing between React components and template literals, designing widget layouts, handling state and data fetching, or troubleshooting widget rendering issues.
myco:live-smoke-testing
Activate this skill when running, interpreting, extending, or debugging the live hardware smoke test harness in scripts/livesmoke.py. Covers all aspects of manifest-driven live testing against real UniFi hardware: .env credential setup, tool classification tiers, --phase flag selection to bound blast radius, the…
myco:unifi-client-data-correctness
Apply this skill whenever modifying, debugging, or extending UniFi client data retrieval in the unifi-mcp monorepo — even if the user doesn't explicitly ask about correctness or fallback behavior. Covers five permanent architectural fixtures of clients.py: (1) choosing the right endpoint (/stat/sta for live clients…
firewall-manager
Manage UniFi firewall policies using natural language — create, modify, and review firewall rules, content filters, and traffic policies. Use when asked to block traffic, create firewall rules, manage content filtering, set up time-based access controls, or review firewall configuration.