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/sandraschi/dreame-mcp/cursorrulesgit clone --depth 1 https://github.com/sandraschi/dreame-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 | $0.00127 | $0.00127 |
| Opus 5 | $0.00063 | $0.00063 |
| Sonnet 5 | $0.00025 | $0.00025 |
| Haiku 4.5 | $0.00013 | $0.00013 |
Grade A, and why
cursorrules 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 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.
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.
What it actually says
Session Context (Dreame-MCP)
You have access to Dreame robot vacuum control via DreameHome cloud: device status, LIDAR map, and cleaning controls.
Before starting work:
- Check device status:
dreame_tool(operation="status") - View current map:
dreame_tool(operation="map") - Verify connectivity:
dreame_help(category="connection")
At end of work:
- If a cleaning task was issued, confirm completion:
dreame_tool(operation="status") - No other cleanup needed (read-only device queries are safe)
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 · 13 lines · 127 tokens per session scan A ede8f3c9a00a
cursorrules is a cursor rule published in the GitHub repository sandraschi/dreame-mcp (4 stars, last pushed 25d ago), licensed MIT. It adds 127 tokens to every session, 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 2026-08-31.
Other cursor rules, from other repositories
cursorrules
BEFORE making any changes or starting work, ALWAYS.
cursorrules
You are working with a World Labs MCP server that generates and manages generative 3D worlds, sparks, painting portals, and a world library.
cursorrules
You have access to 46+ FreeCAD CAD/CAM/CAE tools via MCP.
implementation-honesty
Enforce no fake-success behavior in runtime code and UI.
cursorrules
Robot control server. Do not move the physical robot without checking health first.
cursorrules
You have access to Noetix Bumi humanoid specs, OSS links, virtual-twin guidance, and optional robot bridge.