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.
git clone --depth 1 https://github.com/cartesia-ai/skillsWrote 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/cartesia-ai/skills/cartesia)<a href="https://agentmods.dev/rules/cartesia-ai/skills/cartesia"><img src="https://agentmods.dev/badge/rules/cartesia-ai/skills/cartesia/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/cartesia-ai/skills/cartesia"><img src="https://agentmods.dev/badge/rules/cartesia-ai/skills/cartesia.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00424 |
| Opus 5 | $0.00000 | $0.00212 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
cartesia 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 10d 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
Cartesia
Fetch current docs before writing Cartesia code. Model IDs, Cartesia-Version dates, and Line CLI flags go stale.
Docs
- Index: https://docs.cartesia.ai/llms.txt
- Append
.mdto anydocs.cartesia.aipage for Markdown (example: https://docs.cartesia.ai/use-the-api/api-conventions.md) - TTS models: https://docs.cartesia.ai/build-with-cartesia/tts-models/latest.md
- STT models: https://docs.cartesia.ai/build-with-cartesia/stt-models/latest.md
- Line: https://docs.cartesia.ai/line/start-building/quickstart.md
- MCP: https://docs.cartesia.ai/tools/ai/mcp.md
MCP
Prefer the hosted server at https://mcp.cartesia.ai/mcp (OAuth via the Playground). Use it to list voices, generate TTS, transcribe, clone, and manage pronunciation dictionaries. Do not treat MCP as a production SDK.
Language vs locale vs accent
Do not collapse these:
- language — coarse code (
en,es) - locale — language-region bucket (
en-US,en-GB) - accent — a specific voice identity inside a locale
One locale can have many accents. en-US includes General American and Southern American. Country cannot pick a unique accent. Prefer catalog IDs from the API over display names when the client will persist or send a value back.
Auth
- Server:
Authorization: Bearer <api_key>from https://play.cartesia.ai/keys - Browser/mobile: never embed API keys. Mint a short-lived access token on the backend.
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.
- 10d ago First seen · 41 lines · 0 tokens per session scan A 13531a1f9d2b
cartesia is a cursor rule published in the GitHub repository cartesia-ai/skills (5 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 424 tokens. 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
python
Python best practices and patterns for modern software development with Flask and SQLite.
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
shared-libraries
Shared libraries - condition framework, inventory containers, file-backed DB, itinerary, references.
env-validation-gate
Env validation gate — every app with ≥1 required env var validates its contract at boot via Zod; raw process.env is banned outside the env module. Full pattern in .claude/skills/t2000-env-gate/.