cursorrules

A set of operating rules for the Cursor coding agent in this repository. Cursor is a code editor with an AI agent, and these rules explain the project structure, source-of-truth files, synchronization process, and package-specific commands.

In plain words
What is it for?
Use it to guide Cursor when editing the project, syncing skills, installing package dependencies, and running package-owned tests. The rules direct changes to source files rather than generated provider copies.
Why use it?
It helps the agent make changes in the correct files and avoid overwriting generated files or using the wrong installation and test commands. It also keeps related instructions consistent across the repository.

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/team-telnyx/ai/cursorrules
Clone the repo
git clone --depth 1 https://github.com/team-telnyx/ai

Made for: Cursor.

Per session 604 This file is loaded in full into every session.
When invoked 604 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 $0.00604 $0.00604
Opus 5 $0.00302 $0.00302
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00060 $0.00060

Measured 2d ago against content hash 5790a7831a97, 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 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.

.cursorrules · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor rules — team-telnyx/ai

Operating instructions for the Cursor agent working in this repo. This file is the legacy single-file convention. The MDC equivalent lives at .cursor/rules/main.mdc. The canonical source of truth for everything below is AGENTS.md at the repo root — keep these rules in sync with it when changing project-wide guidance.

What this repo is

Telnyx AI — agent toolkits, plugins for Claude Code / Cursor / Gemini / OpenCode, an MCP proxy, 235+ agent skills, and operational guides. The skills under skills/ are the source of truth; they are synced to providers/{claude,cursor}/plugin/skills/ via scripts/sync-skills.sh.

Hard rules (don't break these)

  • Don't hand-edit files under providers/claude/plugin/skills/ or providers/cursor/plugin/skills/ — they are generated. Edit the source under skills/ and run ./scripts/sync-skills.sh.
  • Don't run npm install at the repo root. Each package has its own package.json and node_modules/. Install per-package: cd cli && npm ci, cd tools/typescript && npm ci, etc.
  • Don't introduce a root-level test runner. Each package owns its own tests. Run only the package you touched.
  • Don't commit credentials, API keys, or .env files. Use the patterns in existing .env.example files.

Per-package commands

  • cli/: cd cli && npm test
  • tools/python/: cd tools/python && pytest
  • tools/typescript/: cd tools/typescript && npm test
  • tools/mcp/: cd tools/mcp && npm run build
  • guides/: npm run test:guides from repo root
  • Guides API tests: npm run test:guides-api from repo root

Code style

  • TypeScript: ES2020+, strict mode, ESM where the package supports it.
  • Python: 3.10+, PEP 8, type hints required for public functions.
  • Markdown: GitHub-flavored. ATX headings (#), no underline headings.
  • One concern per PR. Keep skill regenerations in the same PR as the skill source change (run ./scripts/sync-skills.sh and commit both).

Read the full file on GitHub · 49 lines

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. 2d ago First seen · 49 lines · 604 tokens per session scan A 5790a7831a97

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository team-telnyx/ai (212 stars, last pushed 5d ago), licensed MIT. It adds 604 tokens to every session, about $0.0030 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.