project

project is a cursor rule for Cursor from bobbylkchao/ai-phone-agent. It costs 451 tokens per session, scanned A, original, MIT.

Project instructions for an AI phone agent built with TypeScript, Node.js, Express, Twilio, Amazon Connect, and OpenAI Realtime. They describe code conventions, shared folders, tool registration, voice-agent locations, and security rules.

In plain words
What is it for?
Use them when working on Twilio or Amazon Connect phone channels, shared OpenAI and MCP code, TypeScript tools, builds, linting, or voice prompts.
Why use it?
They give a coding agent the project's technical context and rules before it changes the phone backend.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

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/bobbylkchao/ai-phone-agent/project
Clone the repo
git clone --depth 1 https://github.com/bobbylkchao/ai-phone-agent

Made for: Cursor.

Wrote 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.

agentmods badge for project

README.md
[![agentmods](https://agentmods.dev/badge/rules/bobbylkchao/ai-phone-agent/project.svg)](https://agentmods.dev/rules/bobbylkchao/ai-phone-agent/project)
Your own site
<a href="https://agentmods.dev/rules/bobbylkchao/ai-phone-agent/project"><img src="https://agentmods.dev/badge/rules/bobbylkchao/ai-phone-agent/project.svg" alt="Measured on agentmods" height="20"></a>
Per session 451 This file is loaded in full into every session.
When invoked 451 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 5.1 $0.00451 $0.00451
Opus 5 $0.00226 $0.00226
Sonnet 5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 6d ago against content hash dc37681797a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

project 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 6d 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.

.cursor/rules/project.mdc · 31 lines

What it actually says

Project context

  • Stack: Node.js, TypeScript, Express; OpenAI Realtime for phone audio.
  • Channels: src/service/twilio-phone/ (Twilio Media Streams) and src/service/amazon-connect-phone/openai-sip-webhook/ (Connect + OpenAI SIP webhook).
  • Shared code: src/foundation/ (OpenAI helpers, MCP, Twilio WS, Amazon Connect SDK).

Conventions

  • Linting: eslint.config.mjs extends Airbnb base + @kesills/eslint-config-airbnb-typescript (TypeScript layer) + eslint-config-prettier. Run npm run lint; new code should pass.
  • TypeScript style (arrow functions, callbacks): .cursor/rules/typescript-style.mdc applies when you edit src/**/*.ts(x).
  • Prefer small, task-focused changes; match existing patterns and naming.
  • Imports: @/* maps to src/*. After npm run build, tsc-alias rewrites paths in dist/.
  • New tools (Connect Realtime): add Zod + parametersJsonSchema, export tool, register in openai-sip-webhook/tools/index.ts.
  • SIP voice prompts: openai-sip-webhook/agents/ (Connect; not the Twilio stack).
  • Twilio Realtime agent + tools: service/twilio-phone/agents/ (front-desk + general-agents).

Security

  • Do not commit or hardcode secrets; .env is gitignored. Use GSM or env vars in deployment.
  • Do not log tokens, API keys, or unnecessary PII.

When unsure

  • Read doc/amazon-connect-openai-webhook.md or doc/twilio-integration.md before changing call flow.
  • Developer-facing agent instructions: root AGENTS.md / CLAUDE.md (keep in sync).
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. 6d ago First seen · 31 lines · 451 tokens per session scan A dc37681797a3

Subscribe to this mod's changes

project is a cursor rule published in the GitHub repository bobbylkchao/ai-phone-agent (110 stars, last pushed 4mo ago), licensed MIT. It adds 451 tokens to every session, about $0.0023 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.