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 instructions/team-telnyx/ai/agents-mdgit clone --depth 1 https://github.com/team-telnyx/aiWrote 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/instructions/team-telnyx/ai/agents-md)<a href="https://agentmods.dev/instructions/team-telnyx/ai/agents-md"><img src="https://agentmods.dev/badge/instructions/team-telnyx/ai/agents-md.svg" alt="Measured on agentmods" 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 | $0.02206 | $0.02206 |
| Opus 5 | $0.01103 | $0.01103 |
| Sonnet 5 | $0.00441 | $0.00441 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
ai AGENTS.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Operating instructions for AI coding agents working on this repo, and for runtime agents consuming it.
This file is a complement to README.md (human-facing) and .github/CONTRIBUTING.md (contribution flow). When in doubt, prefer the commands here.
What this repo is
The one-stop shop for AI agents and AI-first developers building with Telnyx. It contains agent toolkits (Python/TypeScript), an agent CLI, per-product plugins for Claude Code / Cursor / Gemini CLI / OpenCode, an MCP proxy, 236 Agent Skills, and operational guides.
Working on this repo
Setup
This is an npm-based monorepo, but the workspaces are independent — install per-package, not at the root.
# Root tooling (only for `npm run test:guides*`)
npm ci
# Per-package
cd cli && npm ci
cd tools/typescript && npm ci
cd tools/mcp && npm ci
cd tools/mcp-apps && npm ci
cd tools/python && pip install -e ".[dev]"
Test / build / lint
| Package | Command |
|---|---|
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 |
tools/mcp-apps/ |
cd tools/mcp-apps && npm run typecheck && npm run build && npm test |
guides/ |
npm run test:guides (from root) |
| Guides API tests | npm run test:guides-api (root) |
Run the relevant package's test suite before declaring a task done. Don't run all of them — pick the one you touched.
Where things live
| Path | What it contains |
|---|---|
skills/ |
Canonical agent skills (SKILL.md files). 236 skills covering messaging, voice, numbers, AI, IoT, WebRTC, Twilio migration. |
providers/claude/ |
Claude Code plugin packaging — synced from skills/ via scripts/sync-skills.sh. Don't edit by hand. |
providers/cursor/ |
Cursor plugin packaging — synced from skills/ via scripts/sync-skills.sh. Don't edit by hand. |
plugins/opencode/ |
OpenCode plugin (auth + TUI for Telnyx-hosted models). |
tools/python/ |
Python agent toolkit (PyPI: telnyx-agent-toolkit). |
tools/typescript/ |
TypeScript agent toolkit (npm). |
tools/mcp/ |
MCP proxy server for the generic Telnyx API MCP endpoint. |
tools/mcp-apps/ |
Focused app-layer MCP servers with MCP Apps UI resources. |
tools/ffl-cli/ |
Filling-from-life CLI tooling. |
cli/ |
Agent CLI for provisioning Telnyx infrastructure. |
inference/ |
Documentation for Telnyx-hosted inference. |
guides/ |
Step-by-step operational guides. |
scripts/sync-skills.sh |
Syncs skills/ → providers/{claude,cursor}/plugin/skills/. |
agent.json |
Top-level agent manifest (capabilities, auth, endpoints). |
plugin.json, mcp.json |
Agent Plugins (agent-plugins.org) manifest bundling skills/ + the hosted MCP server. |
.claude-plugin/ |
Claude Code marketplace metadata. |
.cursor-plugin/ |
Cursor marketplace metadata. |
gemini-extension.json |
Gemini CLI extension manifest. |
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.
- 4d ago First seen · 158 lines · 2,206 tokens per session scan A 2895c55f300d
ai AGENTS.md is an instructions file published in the GitHub repository team-telnyx/ai (212 stars, last pushed 7d ago), licensed MIT. It adds 2,206 tokens to every session, about $0.0110 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.
Other instructions, from other repositories
toki AGENTS.md
Instructions for choi138/toki, covering workspace rules, source of truth, toki workflow, required checks and global safety rules.
Ocul-PM CLAUDE.md
Instructions for bunhine0452/Ocul-PM, covering claude.md, what this is, commands, single frontend test and rust (run from src-tauri/).
Ocul-PM AGENTS.md
Instructions for bunhine0452/Ocul-PM, covering ocul-pm 작업 기록 규칙, 0. 시작하기 전 — 과거를 먼저 찾는다, 1. 언제 기록하는가 (5 trigger), 2. 일지 파일 규격 (도구가 없을 때만) and 3. 금지.
rrweb-stack AGENTS.md
Instructions for Cubenest/rrweb-stack, covering project context for ai coding assistants, what the repo is, build, test & dev commands, planning context — the context/ convention and maintainer-only setup (do this once per fresh checkout).
shopify-app-builder GEMINI.md
Gemini CLI instructions for khadinakbarlabs/shopify-app-builder: Use this extension for Shopify app architecture, implementation, debugging, launch readiness, and growth work.
rrweb-stack CLAUDE.md
Instructions for Cubenest/rrweb-stack, covering claude code and deploying the docs sites.