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 sujitnoronha/voicecheck --skill setup-voicecheckgit clone --depth 1 https://github.com/sujitnoronha/voicecheckWrote 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/sujitnoronha/voicecheck/setup-voicecheck)<a href="https://agentmods.dev/skills/sujitnoronha/voicecheck/setup-voicecheck"><img src="https://agentmods.dev/badge/skills/sujitnoronha/voicecheck/setup-voicecheck.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 | $0.00096 | $0.01666 |
| Opus 5 | $0.00048 | $0.00833 |
| Sonnet 5 | $0.00019 | $0.00333 |
| Haiku 4.5 | $0.00010 | $0.00167 |
Grade A, and why
setup-voicecheck 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 7d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up VoiceCheck
Drive the user from nothing to a passing voice-agent test. Go one step at a time, confirm each step worked before moving on, and never write secrets into files.
This skill bundles supporting files next to this SKILL.md:
references/transports.md— exact env vars +transport:block for each transportreferences/evaluators-and-providers.md— audio providers and the evaluator catalogtemplates/first_scenario.yaml— a starter scenarioscripts/preflight.sh— environment checkscripts/check_env.py— report which env vars a transport needs and which are set
Read a reference file only when the step needs it. Prefer the bundled files over
guessing. Paths below use ${CLAUDE_SKILL_DIR} — Claude Code expands it to this
skill's directory whether the skill is bundled in the repo or installed under
~/.claude/skills/. In Codex or other tools the bundled files sit next to this
SKILL.md; read them by relative path or use the inline fallback shown.
Step 0 — Preflight
Confirm the basics before installing anything. Run the bundled check (or the inline equivalent if the path doesn't resolve):
bash "${CLAUDE_SKILL_DIR}/scripts/preflight.sh" \
|| { python3 --version; python3 -c "import voicecheck,sys;print('voicecheck',voicecheck.__version__)" 2>/dev/null || echo "voicecheck: not installed"; }
VoiceCheck needs Python 3.10+. If python3 is older, stop and tell the user to
upgrade (e.g. pyenv install 3.12 or their OS package manager) before continuing.
If a virtualenv isn't active, recommend one so the install stays isolated:
python3 -m venv .venv && source .venv/bin/activate
Step 1 — Install
Ask the user which path they want. Recommend the first one to start:
- Everything (recommended for first run):
pip install "voicecheck[all]" - Targeted (smaller install): pick a transport + audio extras, e.g.
pip install "voicecheck[livekit,tts,stt]"— see the extras table in the project README for every combination (livekit,daily,vapi,retell,tts,stt,dashboard).
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.
- 7d ago First seen · 153 lines · 96 tokens per session scan A bc788a060044
setup-voicecheck is a skill published in the GitHub repository sujitnoronha/voicecheck (5 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 1,666 once invoked, about $0.0005 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
BrowserStack Cloud Testing
Cloud-based cross-browser and cross-device testing with BrowserStack including Automate, App Automate, Percy visual testing, Observability, and integration with Playwright, Selenium, and CI/CD pipelines.
e2e-alertmanager-test
Render end-to-end previews of what an alert notification will actually look like (plain-text email, HTML email, Slack attachment JSON, raw webhook JSON) by replaying a Prometheus unit-test file's expected alerts through a live Alertmanager. Effectively a "print preview" for alerts. Use to review notification…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.