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 aiappsgbb/awesome-gbb --skill foundry-voice-agentsgit clone --depth 1 https://github.com/aiappsgbb/awesome-gbbWrote 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/aiappsgbb/awesome-gbb/foundry-voice-agents)<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/foundry-voice-agents"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/foundry-voice-agents/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/aiappsgbb/awesome-gbb/foundry-voice-agents"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/foundry-voice-agents.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 | $0.00120 | $0.03858 |
| Opus 5.5 | $0.00048 | $0.01543 |
| Sonnet 5.5 | $0.00024 | $0.00772 |
| Haiku 4.5 | $0.00012 | $0.00386 |
Grade A, and why
foundry-voice-agents 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 25d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundry voice agents
UNRELEASED SOURCE CANDIDATE. Manual synthetic greeting, audio input/output, function call, interruption and stored readback/cleanup passed on 2026-09-25. Manual service-trace correlation also passed, but metadata-only tracing failed: server-side message/tool content was emitted without a client toggle. Existing synthetic traces have a one-run, owner-accepted 30-day retention exception; new trace capture is not authorized by that exception. Current-head targeted CI outcomes are recorded in the PR; see the validation record. Do not represent this candidate as production-ready. The service capability is public preview, with no preview SLA; the SDK's stable package version does not make the service GA. Each live run requires an authorized scope, synthetic data controls and owned-resource cleanup.
Scope and prerequisites
This is a new Agent Service agent with kind: voice, managed voice orchestration
and a name/version lifecycle. It is not a new default API version for the
GA Voice Live API, whose existing foundry-voice-live recipe remains unchanged.
Text interaction mode cannot be changed to voice in place; create a new agent.
No Agent Framework, Pipecat, LiveKit, container rebuild, custom WebRTC stack,
phone binding, outbound call, phone number or telephony licensing is included.
For an authorized live test, establish the exact project, tenant, identity, region, model availability, network path, audio source, any user-declared spending limit, owner, expiry and deletion authority. Public preview documentation is not evidence of tenant rollout. The documented author/invoker prerequisite is Foundry User on the project; this skill does not grant roles or authenticate automatically. An already approved credential chain is required for live commands. Never print access tokens, connection URLs, raw SDK payloads, transcripts or protected audio URLs. Use private run artifacts for identifiers and failures.
What ships with it
15 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.
- constraints.txt 684 B
- references/python/definition.py 4.0 KB runs code
- references/python/lifecycle.py 4.0 KB runs code
- references/python/main.py 6.5 KB runs code
- references/python/session.py 13 KB runs code
- references/upstream-pin.md 2.8 KB
- references/voice-service.yaml 342 B
- requirements-dev.txt 34 B
- requirements.txt 136 B
- test-fixture/consumer_prompt.md 4.6 KB
- test-fixture/live_acceptance.py 18 KB runs code
- test-fixture/synthetic_audio.py 2.4 KB runs code
- tests/test_contract.py 23 KB runs code
- tests/test_live_fixture.py 9.4 KB runs code
- tests/test_packaging.py 4.6 KB runs code
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.
- 25d ago First seen · 310 lines · 120 tokens per session scan A bafd505de468
foundry-voice-agents is a skill published in the GitHub repository aiappsgbb/awesome-gbb (8 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 3,858 once invoked, about $0.0005 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 2026-09-27.
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…