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 skills/handset-hq/handset-ui/skillnpx skills add handset-hq/handset-ui --skill skillgit clone --depth 1 https://github.com/handset-hq/handset-uiWrote 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/handset-hq/handset-ui/skill)<a href="https://agentmods.dev/skills/handset-hq/handset-ui/skill"><img src="https://agentmods.dev/badge/skills/handset-hq/handset-ui/skill.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 5.1 | $0.00061 | $0.00776 |
| Opus 5 | $0.00030 | $0.00388 |
| Sonnet 5 | $0.00012 | $0.00155 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
handset 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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handset
Handset (https://handset.dev) gives a platform a complete business phone
system through one REST API: https://api.handset.dev/v1, bearer-auth with
mode-scoped keys. Docs: https://docs.handset.dev (LLM index: /llms.txt,
full text: /llms-full.txt).
The rules that keep integrations correct
- Test mode first, always.
hs_test_…keys hit a simulated carrier: numbers are free and instant, compliance approves immediately, calls answer in ~1s and auto-complete, delivery receipts and webhooks fire for real. Build and verify everything on a test key; the same code runs live by swapping the key. Never send to real people while developing. - The tenant model is the architecture. Each of the platform's customer
businesses = one tenant (
POST /v1/tenants) owning its own numbers, conversations, opt-out lists, and routing. Provision per-customer, never share one number across customers. - Sends are one call.
POST /v1/messages {from, to, body}— threading (conversation_id), opt-out enforcement, and 10DLC checks happen inside it. Pass anIdempotency-Keyheader tied to your trigger id so retries never double-text. - Events come to you. Register webhook endpoints for the catalog
(
message.received,call.transcript,call.summary,voicemail.created, …) — signed, retried. For UI latency, mint realtime tokens (POST /v1/realtime/tokens) and connect the browser towss://media.handset.dev/v1/events. - Voice is layered. Click-to-call:
POST /v1/calls {from, to, connect_to, transcribe}. Mid-call:/transcription(on-demand transcription),/gather(keypad questions),/dtmf,/streams(raw bidirectional audio for voice agents). AI summary lands ~15s after a transcribed call ends. - Magic numbers rehearse failure (test mode): +15005550001 delivery fails, +15005550002 replies STOP, +15005550003 never answers, +15005550007 gather times out, +15005550008 media stream fails.
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.
- 5d ago First seen · 57 lines · 61 tokens per session scan A ab5beec43b38
handset is a skill published in the GitHub repository handset-hq/handset-ui (1 stars, last pushed 10d ago), licensed MIT. It adds 61 tokens to every session and 776 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…