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 call-voice-deepfake-liveness-detectorgit 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/call-voice-deepfake-liveness-detector)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-voice-deepfake-liveness-detector"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-voice-deepfake-liveness-detector/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/call-voice-deepfake-liveness-detector"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-voice-deepfake-liveness-detector.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 | $0.00039 | $0.01807 |
| Opus 5.5 | $0.00016 | $0.00723 |
| Sonnet 5.5 | $0.00008 | $0.00361 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade A, and why
call-voice-deepfake-liveness-detector 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Deepfake Liveness Detector
This skill directly addresses one of the most urgent and growing threats in telephony: AI-powered voice cloning fraud. With tools like ElevenLabs and VALL-E, a bad actor can clone a person's voice from just a few seconds of audio and use it to impersonate family members, executives, or even government officials in phone calls.
Unlike transcript-oriented call-fraud-shield, this prototype accepts three already-extracted numeric acoustic features. It includes no raw-waveform extraction, telephony middleware, call blocking, identity verification, or audit logger. Its synthetic-fixture labels are advisory examples, not proof that a caller is human or synthetic.
Note: This skill and
call-fraud-shieldare complementary, not competing. Together, they form a two-layer defense: acoustic (this skill) + semantic (call-fraud-shield).
Scientific Foundation
This skill is grounded in the peer-reviewed anti-spoofing literature:
- ASVspoof 2021 (IEEE/ACM TASLP, 2023): The gold-standard benchmark for countermeasures against TTS and voice-conversion (VC) attacks. Defines the Equal Error Rate (EER) metric and the feature taxonomy adopted by this skill.
- ADD 2022 Challenge (ICASSP 2022): The first challenge to address Partially Fake Audio Detection (PF) — where only a fragment of the call is synthetic — a critical real-world threat model.
- FTC Voice Cloning Challenge (April 2024): Official U.S. regulatory acknowledgement of the consumer threat, validating the practical urgency of this skill's design.
How It Works
The helper combines supplied features using illustrative thresholds. A separate host would have to extract and validate these inputs; the following rationale is a design hypothesis:
- Spectral Flatness Analysis: Real human speech contains a rich, irregular harmonic structure. TTS engines produce overly smooth spectrograms with unnaturally low spectral flatness variance.
- Phase Noise Floor Inspection: Microphone recordings always contain ambient environmental noise (Gaussian noise floor, ≈−40 to −60 dB). AI-generated audio is typically unnaturally clean (≈−85 to −95 dB).
- Temporal Periodicity Deviation (Jitter): Human vocal production involves micro-variations in pitch period. Synthetic voices exhibit machine-regular periodicity detectable by statistical analysis.
- Liveness Score Aggregation: The three sub-scores are averaged into a single
liveness_score(0.0 = fully synthetic → 1.0 = genuine human). Requires ≥ 2 valid features; otherwise returnsINDETERMINATE. - Suggested Review Action: Returns an action string only. It does not route, block, escalate, log, or authorize a transaction.
What ships with it
5 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 · 109 lines · 39 tokens per session scan A d4aa60a5139f
call-voice-deepfake-liveness-detector is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,807 once invoked, about $0.0002 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 2026-09-19.
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…