voice-agent-test-harness

voice-agent-test-harness is a skill for Claude Code, Codex from sonichi/sutando. It costs 0 tokens per session (977 once invoked), scanned A, original, MIT.

A test harness for evaluating a voice agent with a fixed set of spoken questions and answers. It uses real audio input and output, then measures response delay, clarity, and accuracy against a baseline.

In plain words
What is it for?
Use it to run spoken test cases, capture microphone audio, transcribe and judge responses, record pass or failure outcomes, and report results over Telegram.
Why use it?
It makes voice-agent testing repeatable and shows when a new run differs from an earlier reference. A voice agent is software that communicates through speech.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to run spoken test cases, capture microphone audio, transcribe and judge responses, record pass or failure outcomes, and report results over Telegram.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sonichi/sutando/voice-agent-test-harness
Install

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.

Any agent
npx skills add sonichi/sutando --skill voice-agent-test-harness
Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for voice-agent-test-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonichi/sutando/voice-agent-test-harness.svg)](https://agentmods.dev/skills/sonichi/sutando/voice-agent-test-harness)
Your own site
<a href="https://agentmods.dev/skills/sonichi/sutando/voice-agent-test-harness"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/voice-agent-test-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 977 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00977
Opus 5 $0.00000 $0.00489
Sonnet 5 $0.00000 $0.00195
Haiku 4.5 $0.00000 $0.00098

Measured 5d ago against content hash 5ff084a6aed9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

voice-agent-test-harness 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.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/audio.py, scripts/baseline.py, scripts/report.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/voice-agent-test-harness/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voice-Agent Test Harness

Drive a fixed suite of spoken tests against a voice agent ("subject") from a co-located machine ("prober"), measure response latency / clarity / accuracy, diff against baseline, and report to the owner over Telegram.

Design: docs/voice-agent-test-framework.md

v1 (macOS). Real audio path: TTS via gemini-tts + afplay, mic capture via sox rec (CoreAudio), voice-onset via numpy RMS, STT + judge via Gemini (Sutando-standard, GEMINI_API_KEY). Manual trigger; reports to owner only. Each prober-side component is tested; the full closed loop needs the second laptop speaking.

What runs end-to-end today

So that a half-SKIPPED suite is never mistaken for "mostly fine," here is exactly what executes through the real acoustic path now versus what is stubbed or excluded. A captured live run is committed at examples/run-2026-06-06.json.

Capability Status today
Single-answer suite (test_cases.yaml, core-v1) — speak → capture → onset → Gemini STT → judge → score Wired. Every row runs end-to-end on real audio; pass / fail / partial / no_response are all measured outcomes, not stubs.
Latency / clarity / accuracy scoring + baseline diff + Telegram roll-up Wired — computed on real captured turns.
timer action test — real side-effect verify (waits, listens for the alarm) Wired.
Multi-turn workflow turns (workflow_cases.yaml, e.g. the developer code-change flow) ⚠️ Partial. The spoken handling is captured and judged; remote side effects (branch/test/cleanup) are not observable from the prober, so these score wording only.
Gmail / CRM workflow turns Excluded — unfinished test setup; omitted from results, not reported as failures.
Daily auto-scheduling Not wired — manual trigger only.

How to try it (two laptops, same room)

  1. Subject: on laptop 2, start a normal Sutando voice session, mic open, speaker up.
  2. Prober: on laptop 1 (this one), grant Terminal Microphone permission (System Settings → Privacy → Microphone), then:
    cd ~/GitHub/sutando/skills/voice-agent-test-harness
    python3 scripts/run_suite.py --quick        # --quick shortens the 2-min timer wait to 30s
    
  3. The prober speaks each prompt; the subject replies; the prober measures, transcribes, judges, and prints the roll-up. Add --deliver to send the report to your Telegram.

Read the full file on GitHub · 59 lines

Changes

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.

  1. 5d ago First seen · 59 lines · 0 tokens per session scan A 5ff084a6aed9

Subscribe to this mod's changes

voice-agent-test-harness is a skill published in the GitHub repository sonichi/sutando (394 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 977 tokens. 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 2026-09-03.

Related

Other skills, from other repositories

typescript-eval

Test TypeScript code snippets before persisting as skills.

vellum-ai/vellum-assistant · 14 tokens

ccg-workflow

How to run a non-trivial change end to end with the CCG role tools (ccganalyze / ccgdesign / ccgbuild / ccgdebug / ccgoptimize / ccgreview / ccgtest) and the verify- quality gates. Use when a task is a whole feature, a refactor, a bug whose cause is not yet known, or any change large enough that one straight-through…

fengshao1227/ccg-workflow · 97 tokens

app-builder

Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…

vellum-ai/vellum-assistant · 162 tokens

assistant-migration

Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…

vellum-ai/vellum-assistant · 90 tokens

vellum-memory-v3-migration

One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.

vellum-ai/vellum-assistant · 63 tokens

media-processing

Ingest and process media files (video, audio, image).

vellum-ai/vellum-assistant · 16 tokens