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 rules/qubitonhq/qubiton-cursor-plugin/qubiton-lifecyclegit 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/rules/qubitonhq/qubiton-cursor-plugin/qubiton-lifecycle)<a href="https://agentmods.dev/rules/qubitonhq/qubiton-cursor-plugin/qubiton-lifecycle"><img src="https://agentmods.dev/badge/rules/qubitonhq/qubiton-cursor-plugin/qubiton-lifecycle.svg" alt="Measured on agentmods" 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 | $0.01093 | $0.01093 |
| Opus 5 | $0.00547 | $0.00547 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
qubiton-lifecycle 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 3d 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.
QubitOn MCP lifecycle
This workspace uses QubitOn MCP to validate and enrich vendor, supplier, and business data — addresses, tax IDs, bank accounts, phone numbers, and sanctions/PEP screening. These rules govern how you interact with QubitOn tools.
When to use QubitOn
Reach for QubitOn tools when the user asks you to:
- Validate an address, tax ID, bank account, phone number, or email
- Enrich a company or supplier record with firmographic data
- Screen an entity or person against global sanctions or PEP lists
- Look up business registration details (name, status, officers) by country
- Check coverage for a specific country or data type
Do not use QubitOn for general web search, code generation, or tasks unrelated to vendor/supplier data quality.
Authentication
QubitOn MCP requires an API key sent in the apikey header. Before the user
can call any tool, QUBITON_API_KEY must be set in their environment or the
key must be configured in their MCP client settings.
If a tool call fails with 401 Unauthorized or a message mentioning
"apikey" / "api key":
- Tell the user their QubitOn API key is missing or invalid.
- Direct them to www.qubiton.com → Dashboard → API Keys to copy their key.
- Explain they should set
QUBITON_API_KEYin their MCP client config (or theapikeyheader value directly) and reconnect the server.
Never ask the user to paste their API key into chat — it should only live in their MCP client configuration.
Safety model: reads vs writes
All QubitOn MCP tools are read-only validation and screening operations. They do not mutate data in the user's systems. It is always safe to call QubitOn tools without explicit confirmation for individual records.
However, respect quota:
- QubitOn charges per API call against the user's plan quota (visible in the Dashboard). The MCP server does not expose a quota-check tool — always defer quota questions to the dashboard.
- Before running a batch (>10 validations), estimate the call count and confirm with the user: "This will use ~N QubitOn API calls from your quota. Proceed?"
- If a call returns
429, read theRetry-Afterheader and respect it; don't retry-loop a rate-limited call.
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.
- 3d ago First seen · 102 lines · 1,093 tokens per session scan A 2852f69f230d
qubiton-lifecycle is a cursor rule published in the GitHub repository qubitonhq/qubiton-cursor-plugin (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,093 tokens to every session, about $0.0055 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 2026-08-31.
Other cursor rules, from other repositories
cursorrules
You are working on Unity Developer Tools, a Cursor IDE plugin for Unity game development.
performance-rules
Performance optimization rules for Unity.
csharp-unity-conventions
C# coding conventions for Unity development.
shader-conventions
Conventions for Unity shader development.
monobehaviour-lifecycle
Correct usage of MonoBehaviour lifecycle methods.
naming-conventions
Naming conventions for Unity C# code.