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/speech-mcp/cursorrulesgit clone --depth 1 https://github.com/sandraschi/speech-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 | $0.00255 | $0.00255 |
| Opus 5 | $0.00128 | $0.00128 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00026 | $0.00026 |
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
Cursor Rules — speech-mcp
- Python:
uv run ruff check src/ --fixbefore commit; line length 120. - Type hints:
Annotated[T, Field(description="...")]— noArgs:blocks. - Tools return
{"success": bool, ...}dicts; list/status tools use Prefab UI (@mcp.tool(app=True)). - Never call
os.getenv()outsideserver.py; never block the event loop. - Frontend: React + Vite + Tailwind (dark theme only), Biome for lint/format.
- Tests:
uv run pytest tests/ -m "not live".
Session Context (Speech MCP)
You have access to the fleet voice gateway: TTS (windows/gemini/hume/elevenlabs/gemma), local STT (FunASR), offline wake word, RAG over speech docs, and a Voice Command Bus into fleet-agent.
Before starting work:
- Check provider availability: fleet_health_overview()
- Find speech docs: search_docs(query="FunASR or wake word")
At end of work, save insights:
- Ingest useful speech findings into the RAG knowledge base
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 · 22 lines · 255 tokens per session scan A 2c43b3be0cf9
cursorrules is a cursor rule published in the GitHub repository sandraschi/speech-mcp (2 stars, last pushed 13d ago), licensed MIT. It adds 255 tokens to every session, about $0.0013 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
openapi
This document provides comprehensive guidelines for writing OpenAPI annotations in the Sayna Rust/Axum codebase using the utoipa crate.
rust
Comprehensive best practices for Rust development (Edition 2024).
axum
Comprehensive best practices for Axum 0.8+ development with WebSocket support.
core
Core STT/TTS abstraction layer documentation.
livekit
We are using LiveKit Rust SDK livekit-rust for our real-time communication needs. The idea is that we should have a separate folder named livekit in the src folder. That folder should contain the main logic for connecting to the livekit server and receiving the audio chunks from subscribed tracks.
cursorrules
Composite MCP server for AI-powered music production workflows. Mounts and orchestrates multiple MCP servers (VirtualDJ, Plex, Suno, Reaper, OBS).