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 voicelogica/voice-logica-plugin --skill manage-phonesgit clone --depth 1 https://github.com/voicelogica/voice-logica-pluginWrote 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/voicelogica/voice-logica-plugin/manage-phones)<a href="https://agentmods.dev/skills/voicelogica/voice-logica-plugin/manage-phones"><img src="https://agentmods.dev/badge/skills/voicelogica/voice-logica-plugin/manage-phones/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/voicelogica/voice-logica-plugin/manage-phones"><img src="https://agentmods.dev/badge/skills/voicelogica/voice-logica-plugin/manage-phones.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 | $0.00068 | $0.01674 |
| Opus 5 | $0.00034 | $0.00837 |
| Sonnet 5 | $0.00014 | $0.00335 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
manage-phones 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 12d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Voice Logica phones
Use Voice Logica MCP phone tools. Do not invent numbers, SIP credentials, or agent IDs. Never print SIP passwords in chat.
MCP tools
get_voip_phones/create_voip_phone/update_voip_phone/delete_voip_phoneactivate_voip_phone/deactivate_voip_phoneget_edge_devices/set_edge_device_forward/remove_edge_device_forward
Before changing anything
- List phones and list agents. Match by name, then use real IDs.
- If the user names a number, find that exact registration first.
- Confirm the target agent before assigning or moving a number.
- If inbound calls never appear in Voice Logica at all (zero Call IDs in the window), traffic never reached the platform — treat it as carrier / portability / PBX routing first, not a prompt bug.
Three phone paths — do not swap them
| Path | When | Transport |
|---|---|---|
| Direct SIP | Hosted / cloud PBX (public SIP) | Internet SIP. Register the extension in Phones. |
| Via edge device | On-prem PBX on a private LAN (Grandstream, FreePBX, Alcatel, Panasonic, …) | WireGuard UDP 51820 + control TCP 443. UI: Phones → Edge Devices. |
| On-prem SSH tunnel | Private HTTP ERP / API, not phones | AI → Tunnels. See manage-erp. Wrong product for SIP/RTP. |
Yuboto / cloud numbers usually use Direct. A Yuboto PBX integration (API key under Integrations) is not the same as a SIP phone and not an Edge Device.
A third-party hosted PBX (Vodafone One Net, Cosmote, …) is configured on their portal. Voice Logica cannot set their forwarding rules. They must send the public number to the AI DID / extension themselves.
Common jobs
Why does this agent have no phone?
An agent with no DID usually needs a number from Phones, or a plan that includes DIDs (did / free-did). Check phones first, then the agent, then get_subscription. Demo / No Plan / Inactive plans often lock number CTAs.
Assign a number to an agent. List free or existing phones, pick one, attach it to the agent ID, then confirm the agent shows that number. Suggest a test inbound call.
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.
- 12d ago First seen · 102 lines · 68 tokens per session scan A c4d589b29f46
manage-phones is a skill published in the GitHub repository voicelogica/voice-logica-plugin (0 stars, last pushed 20d ago), licensed MIT. It adds 68 tokens to every session and 1,674 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
hardware-performance-expert
Expert system for hardware analysis, real-time performance troubleshooting, and LLM optimization.
design-for-additive-manufacturing
Use when translating an OpenRocket logical design into a physical component tree for FDM/SLA 3D printing. Decides per-component fate (print, fuse, purchase, skip), applies AM-specific geometry patterns, and emits componenttree.json.
local-inference-optimizer
Expert system for analyzing local hardware/software topology and providing actionable recommendations for LLM inference.
print-preparation
Use when slicing rocket parts for FDM printing, or when choosing print orientation and settings for a specific part.
meteocontrol-assistant
Specialized assistant for monitoring and analyzing solar installations via the MeteoControl VCOM API. Use it to troubleshoot production drops, triage alerts, and generate system reports.
expert-llmfit
(BETA) Use this skill to verify, maintain, and adapt the hardware recommendation logic (VRAM, TPS, Model specs) based on the upstream AlexsJones/llmfit Rust project.