Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsnpx agentmods add skills/calle-ai/awesome-phone-call-agents/relaymeWrote 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/skills/calle-ai/awesome-phone-call-agents/relayme)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/relayme"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/relayme/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/skills/calle-ai/awesome-phone-call-agents/relayme"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/relayme.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 | $0.00060 | $0.02272 |
| Opus 5.5 | $0.00024 | $0.00909 |
| Sonnet 5.5 | $0.00012 | $0.00454 |
| Haiku 4.5 | $0.00006 | $0.00227 |
Grade A, and why
relayme 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 1mo 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RelayMe
A Deaf father wants to know if his daughter's prescription is ready before he drives across town to a pharmacy with no website and no online refill. He cannot make that call. His options today are to wait for a relay operator to join the line, or to ask a hearing person for a favour. RelayMe is a third option: he types the question, an AI assistant makes the call, and the whole conversation comes back to him as a text thread with the answer at the bottom.
Use this skill when a deaf, hard-of-hearing, or non-speaking person needs one everyday, voice-only task done: is a prescription ready, is an item in stock, what are today's hours, a yes/no question to an office that only takes calls. The user types the task. RelayMe places one disclosed CALL-E call, has the conversation on their behalf, and returns it as a readable thread plus a fail-closed structured result.
RelayMe is a text-first alternative to a telecommunications relay service (711 in the US), built for its known friction:
- No human operator. A relay operator hears every word of a medical or banking call. RelayMe has none; the conversation is between the AI and the business only.
- No hang-ups. Businesses routinely hang up on relay calls they do not recognise. The RelayMe agent speaks naturally in real time, so the callee has an ordinary conversation.
- Not synchronous. The user does not sit and type through the call. They state the task once and read the result when it is done.
- An answer, not a transcript. The result is structured and fail-closed, not raw speech to interpret.
What the user sees
The call is delivered as a conversation thread (apps/python/relayme/thread.py),
rendered in a phone-style chat view (apps/python/relayme/web/relayme.html):
You Is my prescription at Maple Street Pharmacy ready?
RelayMe I'll call and say I'm an AI assistant calling for you. You'll see it all.
Agent Is the prescription for Jordan Rivera ready for pickup?
Them Yes, ready at the pickup counter, any time before 8 PM.
RelayMe Here's your answer: it's ready, collect before 8 PM today.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 211 lines · 60 tokens per session scan A 4e171227644d
relayme is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 2,272 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-18.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…