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 skills add CALLE-AI/awesome-phone-call-agents --skill dialtone-handshakegit clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote 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/dialtone-handshake)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/dialtone-handshake"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/dialtone-handshake/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/dialtone-handshake"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/dialtone-handshake.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 | $0.00063 | $0.00942 |
| Opus 5.5 | $0.00025 | $0.00377 |
| Sonnet 5.5 | $0.00013 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
dialtone-handshake 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DIALTONE Handshake
DIALTONE v1 is a spoken handshake plus an attestation rule for phone calls where both ends may be AI agents. It has two halves:
- Caller side: a CALL-E task that opens with a spoken token and switches mode depending on who answers.
- Inbound side: three system-prompt sentences that let a voicebot acknowledge the token.
The runnable reference implementation is apps/python/dialtone. It includes detection, the attestation gate, an honest evaluation and a demo.
When To Use
- You place calls with CALL-E to businesses that may answer with a voicebot.
- You operate an inbound voicebot and want automated callers to finish faster and more honestly.
- Your workflow treats
task_completed: trueas a commitment: bookings, cancellations, refunds, payments or reschedules.
When Not To Use
- As authentication. The nonce proves an acknowledgement answers this call, not who operates the agent.
- To skip disclosure. The token is spoken after the AI disclosure, never instead of it.
- For emergency, medical, legal or financial decisions. An
agent_assertedresult is not sufficient evidence for these.
Protocol
1. Caller opening, after the disclosure, with a fresh 3-digit nonce per call:
Hi, I'm an AI assistant calling on behalf of Jordan Lee. Dialtone one, code four seven two.
2. Acknowledgement from a DIALTONE-aware voicebot:
Dialtone one acknowledged, code four seven two. Automated agent. Human review: no.
3. Mode. Pick one based on who answered:
| Who answered | Mode | Style |
|---|---|---|
| Acknowledged, or clearly an automated agent | MACHINE | field: value sentences; ask only for outcome, confirmation code, and human review |
| Phone menu | MENU | Navigate with keypad tones or short options |
| Otherwise, or unsure | HUMAN | Full disclosure, natural pace |
4. Attestation. Label every result by who confirmed it:
| Label | Who confirmed | Counts as task completed? |
|---|---|---|
human_attested |
A person, with high detector confidence | Yes |
system_asserted |
A phone system read back a record | Yes |
agent_asserted |
An AI agent: information, or a commitment with a verifiable artifact | Yes |
refused |
An AI agent confirmed a binding commitment with no artifact | No |
unverified |
Nothing confirmed, or the counterpart is uncertain | No |
What ships with it
2 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 · 87 lines · 63 tokens per session scan A 4b02a3376db4
dialtone-handshake is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 942 once invoked, about $0.0003 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 2026-09-15.
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…