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 qubitonhq/qubiton-cursor-plugin --skill qubiton-setupgit clone --depth 1 https://github.com/qubitonhq/qubiton-cursor-pluginWrote 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/qubitonhq/qubiton-cursor-plugin/qubiton-setup)<a href="https://agentmods.dev/skills/qubitonhq/qubiton-cursor-plugin/qubiton-setup"><img src="https://agentmods.dev/badge/skills/qubitonhq/qubiton-cursor-plugin/qubiton-setup/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/qubitonhq/qubiton-cursor-plugin/qubiton-setup"><img src="https://agentmods.dev/badge/skills/qubitonhq/qubiton-cursor-plugin/qubiton-setup.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 | $0.00102 | $0.01214 |
| Opus 5.5 | $0.00041 | $0.00486 |
| Sonnet 5.5 | $0.00020 | $0.00243 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade B, and why
qubiton-setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- The plugin's `mcp.json` header substitutes `${QUBITON_API_KEY}` at How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QubitOn setup
Introduce QubitOn MCP, get the user authenticated, verify the connection, and suggest a first validation to run.
Step 1: Introduction
Start with a short pitch so the user understands what QubitOn unlocks:
"QubitOn MCP connects your AI to global vendor and supplier data validation — addresses (USPS, Royal Mail, BAN, and 200+ country authorities), tax IDs (VAT, GSTIN, EIN, and many more), bank accounts (IBAN, SWIFT, ACH, and country-specific routing), phone and email validation, firmographic enrichment, and sanctions/PEP screening against OFAC, EU, UN, and UK HMT lists. Ask in plain language — 'validate this address', 'check this VAT number', 'screen this company against sanctions' — and I'll run it."
Then check connection.
Check connection
Attempt to list available QubitOn tools. Based on what you find:
- Tools are available: The user is already connected. Give a shorter intro — "You've got QubitOn MCP connected. Let me verify your setup and suggest a first test." — then skip to Step 3.
- No QubitOn tools available: The server is installed but needs authentication. Proceed to Step 2.
Step 2: Authentication
QubitOn MCP uses an API key sent in the apikey header.
-
Get an API key. Direct the user to www.qubiton.com:
- If they don't have an account: Get Started → sign up → verify email. A free plan with limited quota is available.
- Once signed in: Dashboard → API Keys → copy the key
(prefix
svm_...).
-
Configure the MCP client. The plugin's
mcp.jsonreferences aQUBITON_API_KEYenvironment variable. Two paths work:Path A — environment variable (preferred):
- Set
QUBITON_API_KEY=<key>in the shell where you launch Cursor (e.g., your shell profile,.zshenv/.bashrc). Relaunch Cursor. - The plugin's
mcp.jsonheader substitutes${QUBITON_API_KEY}at load time.
Path B — direct header (fallback, always works):
- Open Settings → Cursor Settings → Tools & MCP → find the qubiton server.
- If the
apikeyheader shows the literal string${QUBITON_API_KEY}instead of being expanded (you'll see a 401 on the first call), paste the key value directly into theapikeyheader field in Cursor's UI.
- Set
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.
- 1mo ago First seen · 109 lines · 102 tokens per session scan B 93087921ddc9
qubiton-setup is a skill published in the GitHub repository qubitonhq/qubiton-cursor-plugin (5 stars, last pushed 6mo ago), licensed MIT. It adds 102 tokens to every session and 1,214 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ecs-dots
Use when the user works with DOTS, ECS, Entities, ISystem or SystemBase, IComponentData, Bakers, SubScenes, the Job System, or Burst, or needs to simulate thousands of objects. Covers entity queries, baking, entity command buffers, jobs, and Burst constraints.
editor-scripting
Use when the user wants to extend the Unity Editor with a custom inspector, editor window, property drawer, menu item, gizmo, Scene View overlay, or tooling under an Editor folder. Covers UI Toolkit inspectors, SerializedProperty, Undo, and editor-only assemblies.
input-systems
Use when the user handles keyboard, mouse, gamepad, or touch input, sees errors from UnityEngine.Input, sets up PlayerInput or .inputactions assets, adds key rebinding, or adds local multiplayer. Covers the Input System package, action maps, callbacks, rebinding, and migrating from the legacy Input Manager.
monobehaviour-patterns
Use when the user writes or debugs MonoBehaviour scripts, asks about Awake vs Start vs OnEnable, execution order, coroutines vs async, Awaitable, singletons, events, or object pooling. Covers lifecycle order, Awaitable async patterns, and common gameplay architecture patterns.
networking
Use when the user builds multiplayer, sets up a host or server, syncs state, writes RPCs or NetworkVariables, or chooses between Netcode for GameObjects, Netcode for Entities, Mirror, and Photon Fusion. Covers authority, ownership, RPCs, prediction, and solution tradeoffs.
performance-optimization
Use when the game lags, stutters, drops FPS, has GC spikes, too many draw calls, long load times, or high memory use, or the user asks how to profile. Covers CPU and GC allocations, pooling, batching and the SRP Batcher, LOD and culling, memory, and the Profiler, Memory Profiler, and Frame Debugger.