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 paulotaylor/voyp-mcp --skill voypgit clone --depth 1 https://github.com/paulotaylor/voyp-mcpWrote 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/paulotaylor/voyp-mcp/voyp)<a href="https://agentmods.dev/skills/paulotaylor/voyp-mcp/voyp"><img src="https://agentmods.dev/badge/skills/paulotaylor/voyp-mcp/voyp/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/paulotaylor/voyp-mcp/voyp"><img src="https://agentmods.dev/badge/skills/paulotaylor/voyp-mcp/voyp.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 | $0.00109 | $0.01946 |
| Opus 5.5 | $0.00044 | $0.00778 |
| Sonnet 5.5 | $0.00022 | $0.00389 |
| Haiku 4.5 | $0.00011 | $0.00195 |
Grade A, and why
voyp 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 yesterday.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voyp phone calls
Voyp places a real phone call to a real person. A Voyp voice agent talks to whoever answers.
That agent knows only the context you give it, so you brief it like an assistant you
are sending to make the call. Every call uses the user's paid credits and reaches someone
who did not ask to be called, so check before dialling and keep the call short.
Tools
The tool names come from the Voyp MCP server. Your client may add a prefix, such as mcp__voyp__start_call.
| Tool | Use it to | Server |
|---|---|---|
start_call(number, context, language) |
Place the call. Returns the call id and a live URL |
both |
get_live_call(id) |
Status and transcript while the call is running | hosted |
get_call(id) |
Details and transcript (hosted: the final result after the call ends) | both |
hangup_call(id) |
End a call that is running | both |
search_places(search) |
Find businesses, e.g. "sushi restaurants in Lisbon" | local |
search_place(place, location) |
Get the phone number and details of one business | local |
search_place_by_number(number) |
Find which business a number belongs to | local |
get_user() |
Check the connection and the user's profile | both |
If a tool is missing, use the ones you have. For example, with no place search tool, get the number from the user or a web search. See references/tools.md for arguments and responses.
Workflow
1. Understand the task
Find out who to call, what outcome the user wants, and the details the callee will ask for: name for the booking, date and time, party size, order or account number, callback number. Also ask what is acceptable if the first choice is not available ("8pm, or anything between 7 and 9", "any weekday morning"). Ask the user for anything essential that is missing. Do not invent personal details.
2. Find and check the number
- If the user did not give a number, use
search_place(orsearch_places) to find it. If several businesses match, show the options and let the user choose. - Convert the number to E.164:
+then country code then number, with no spaces (for example+14155550123or+351212345678). If the country is unclear, ask. - Use
search_place_by_numberwhen the user gives a bare number and you need to check what it is.
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.
- yesterday First seen · 131 lines · 109 tokens per session scan A 25dc56542d53
voyp is a skill published in the GitHub repository paulotaylor/voyp-mcp (10 stars, last pushed 2d ago), licensed MIT. It adds 109 tokens to every session and 1,946 once invoked, about $0.0004 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 2026-11-08.
voyp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| voyppaulotaylor/voyp-mcp | Skill | 10 | 2d ago | MIT | A | 109 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 113k | today | MIT | A | 30 | Claude Code, Codex |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | today | Apache-2.0 | A | 60 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 4d ago | MIT | A | 184 | Claude Code |
| feishuHmbown/CodeWhale | Skill | 41k | 2d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 13d ago | MIT | A | 52 | Claude Code, Codex |