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 instructions/sujitnoronha/voicecheck/agents-mdgit 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/instructions/sujitnoronha/voicecheck/agents-md)<a href="https://agentmods.dev/instructions/sujitnoronha/voicecheck/agents-md"><img src="https://agentmods.dev/badge/instructions/sujitnoronha/voicecheck/agents-md.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 | $0.00452 | $0.00452 |
| Opus 5 | $0.00226 | $0.00226 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
voicecheck AGENTS.md 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.
What it actually says
AGENTS.md — VoiceCheck
Instructions for Codex (and other agents reading AGENTS.md). The full guidance lives in CLAUDE.md — read it; the two files are kept in sync.
VoiceCheck is an end-to-end testing framework for voice agents. A test is a YAML
scenario: a transport (how to reach the agent — livekit/daily/vapi/retell,
or keyless echo), an audio block (edge TTS + whisper STT need no keys), and
turns, where each turn sends user: text and lists expect: evaluators that must
pass (e.g. latency, keyword, llm_judge, info_leakage, tool_called).
Skills
Agent Skills are in .agents/skills/ (mirrors .claude/skills/). Invoke via /skills
or $skillname:
setup-voicecheck— install, smoke-test, configure a transport, run a first scenario.write-voicecheck-test— author a scenario YAML + evaluators, validate/dry-run, wire pytest.
Authoring loop
voicecheck validate <f> (schema only) → voicecheck run <f> --skip-llm-judge
(dry-run, no cost) → voicecheck run <f>. The authoritative field list is
voicecheck schema — don't invent evaluator names or config keys. pytest:
@pytest.mark.voicecheck("scenario.yaml").
Repo rules
- Python 3.10+. CI gates on
ruff check src/ tests/ANDruff format --check src/ tests/(runruff format src/ tests/before committing) andpytest tests/unit/. - Never write real API keys into files; scenarios use
${ENV_VAR}, set in a local.env. - Do not modify files under
.claude/or.agents/unless the task is specifically about the skills.
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 · 33 lines · 452 tokens per session scan A 09bf7166a39b
voicecheck AGENTS.md is an instructions file published in the GitHub repository sujitnoronha/voicecheck (5 stars, last pushed 2mo ago), licensed MIT. It adds 452 tokens to every session, about $0.0023 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 instructions, from other repositories
Math-To-Manim tests.instructions.md
Guidelines for writing and maintaining tests in Math-To-Manim.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.
android-qa-kit AGENTS.md
Instructions for willbytee-sudo/android-qa-kit, covering agents.md — setting up and driving an android device, 1. how to work with the user, 2. start by finding out what's already there, 3. what you can do in each mode and 4. if there's no device: ask first.
pipecat CLAUDE.md
Claude Code instructions for pipecat-ai/pipecat, a project described as: Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
flightrules CLAUDE.md
Instructions for winsznx/flightrules, covering flightrules — operating contract, what this product is, non-negotiable rules, determinism boundary and verified environment (phase 00, 2026-07-25).
gemini-cli-hud GEMINI.md
Instructions for yideng-xl/gemini-cli-hud, covering gemini cli hud, what it shows, how it works and notes.