Borrowing it
Nothing to install: this file belongs to sujitnoronha/voicecheck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sujitnoronha/voicecheck/main/CLAUDE.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/claude-md)<a href="https://agentmods.dev/instructions/sujitnoronha/voicecheck/claude-md"><img src="https://agentmods.dev/badge/instructions/sujitnoronha/voicecheck/claude-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 5.1 | $0.00931 | $0.00931 |
| Opus 5 | $0.00465 | $0.00465 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
voicecheck CLAUDE.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 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — VoiceCheck
Guidance for AI coding agents (Claude Code, Codex) working in this repo. VoiceCheck is an end-to-end testing framework for voice agents: a YAML scenario synthesizes real audio, streams it through a real transport, captures the agent's reply, and grades every turn.
Skills in this repo
Two Agent Skills ship with the repo and inside the pip package (canonical source:
src/voicecheck/skills/). They auto-load in Claude Code when the repo is open
(.claude/skills/ symlinks to the package copy) and in Codex (.agents/skills/).
Pip users (who didn't clone the repo) get them via voicecheck install-skill, which
copies them into ~/.claude/skills/ (add --codex for ~/.agents/skills/).
/setup-voicecheck— install VoiceCheck, smoke-test with the zero-keyechotransport, configure a transport + audio providers, scaffold and run a first scenario. Use for onboarding / "how do I get started"./write-voicecheck-test— turn a description of an agent's expected behavior into a scenario YAML with the right evaluators, validate + dry-run it, and wire it into pytest. Use for "write a voice test / add a scenario / test this agent".
The skills' references/ files (transport env vars, the evaluator catalog) are the
quickest accurate source when authoring scenarios.
How testing works (the model to keep in mind)
A test is a YAML scenario, not Python:
transport:— how to reach the agent (livekit,daily,vapi,retell, or built-inechofor keyless plumbing tests).audio:—tts_provider/stt_provider. Defaultsedge+whisperneed no key.turns:— a list; each turn sendsuser:text and listsexpect:evaluators that must all pass. 13 evaluators:latency,keyword,turn_count,llm_judge,rubric_judge,emotional_tone,fact_accuracy,info_leakage,memory_recall,character_break,personality_consistency,tool_called,tool_sequence.
Authoring loop: write YAML → voicecheck validate <f> (schema only, no keys) →
voicecheck run <f> --skip-llm-judge (dry-run, no LLM cost) → voicecheck run <f>.
The authoritative field list is voicecheck schema. Don't invent evaluator names or
config keys — check the schema or the skill references.
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 · 69 lines · 931 tokens per session scan A 3a8fe80bb54b
voicecheck CLAUDE.md is an instructions file published in the GitHub repository sujitnoronha/voicecheck (5 stars, last pushed 2mo ago), licensed MIT. It adds 931 tokens to every session, about $0.0047 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.