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/notepadpp-mcp/cursorrulesgit clone --depth 1 https://github.com/sandraschi/notepadpp-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 | $0.00241 | $0.00241 |
| Opus 5 | $0.00120 | $0.00120 |
| Sonnet 5 | $0.00048 | $0.00048 |
| Haiku 4.5 | $0.00024 | $0.00024 |
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 yesterday.
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
notepadpp-mcp — Cursor Rules
Tool awareness
Session Context (Notepad++ MCP)
You have access to an MCP server that automates Notepad++ on Windows:
file_ops, text_ops, tab_ops, session_ops, linting_ops, display_ops,
plugin_ops, status_ops (portmanteau tools with an operation enum).
Before starting work:
- Check the editor is reachable:
status_ops(operation="health_check") - Inspect the active document:
file_ops(operation="info")
At end of work, persist state:
- Save the workspace when asked:
session_ops(operation="save", session_name="...") - Lint before declaring code done:
linting_ops(operation="python", file_path="...")
General
- FastMCP portmanteau pattern: tools use an
operationenum discriminator - Responses are structured dicts with
success,message, and domain fields - Dual transport: stdio (Claude Desktop) + HTTP bridge (10815)
- Fleet standards live in
mcp-central-docs/(read before major changes)
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.
- yesterday First seen · 25 lines · 241 tokens per session scan A 4227422b6d89
cursorrules is a cursor rule published in the GitHub repository sandraschi/notepadpp-mcp (5 stars, last pushed 12d ago), licensed MIT. It adds 241 tokens to every session, about $0.0012 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
Composite MCP server for AI-powered music production workflows. Mounts and orchestrates multiple MCP servers (VirtualDJ, Plex, Suno, Reaper, OBS).
cursorrules
FastMCP server + webapp that bridges Claude Desktop / Cursor to OpenClaw (agent Gateway, channels, routing, sessions, skills, security) and Moltbook (AI-agent social network). It uses those platforms; it does not implement or replace them.
cursorrules
You are working on stripe-mcp, an MCP server and SOTA React webapp providing Stripe payment tools and Austrian/EU tax compliance.
cursorrules
BEFORE making any changes or starting work, ALWAYS.
cursorrules
BEFORE making any changes or starting work, ALWAYS.
cursorrules
BEFORE making any changes or starting work, ALWAYS.