cursorrules

A Cursor rules file that routes pronunciation questions about technical terms to the say-it command-line tool. It covers project names, programming jargon, and technology acronyms.

In plain words
What is it for?
Use it in a project when Cursor should play and explain the pronunciation of a single technical term.
Why use it?
It gives Cursor a consistent way to handle technical pronunciation questions, including alternate readings and dictionary confidence information.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/anzy-renlab-ai/pronounce/cursorrules
Clone the repo
git clone --depth 1 https://github.com/anzy-renlab-ai/pronounce

Made for: Cursor.

Per session 314 This file is loaded in full into every session.
When invoked 314 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00314 $0.00314
Opus 5 $0.00157 $0.00157
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00031 $0.00031

Measured yesterday against content hash 3d0aeb5e3201, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

integrations/cursor/.cursorrules · 30 lines

What it actually says

Pronounce integration for Cursor

Drop into your project root as .cursorrules, or merge with your existing one.

Cursor will pick this up and route pronunciation questions to the say-it CLI.

When the user asks how to pronounce a project name, product name, programmer jargon, or tech acronym (English "how do you pronounce X" / "pronounce X" / Chinese "X 怎么读" / "X 怎么发音"), do this:

  1. Run say-it "$WORD" — plays the audio through macOS speakers using a community-maintained dictionary of how engineers actually pronounce things.
  2. Run say-it --json "$WORD" to get the IPA, alternates, source URL, and confidence level for the citation.
  3. Reply with the IPA, the respelling, and the source citation. For contested words (GIF, SQL, JSON, kubectl, ...), mention the alternate reading and how to play it (say-it --alt <word>).

Constraints:

  • Tech terms only. Not for general English vocabulary.
  • General American English only.
  • If the word isn't in the dictionary, say-it --why <word> prints "did you mean" suggestions — surface those to the user before guessing.

Install if not already on $PATH: git clone https://github.com/anzy-renlab-ai/pronounce.git cd pronounce && ./install.sh

Browse the dictionary: https://pronounce.renlab.ai

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.

  1. yesterday First seen · 30 lines · 314 tokens per session scan A 3d0aeb5e3201

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository anzy-renlab-ai/pronounce (37 stars, last pushed 5d ago), licensed MIT. It adds 314 tokens to every session, about $0.0016 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 2026-08-30.