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/signalengine/pipevoice/claude-mdgit clone --depth 1 https://github.com/SignalEngine/PipeVoiceWhat 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 | $0.01447 | $0.01447 |
| Opus 5 | $0.00724 | $0.00724 |
| Sonnet 5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
PipeVoice 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 3d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Orientation: directory nesting
The invoked working directory (.../Desktop/wisperlite) is just a container. The actual
project lives one level down and the name drops an "e":
wisperlite/ <- working dir (NOT a git repo)
wisprlite/ <- project root + git repo (.git is here). Run all commands from here.
wisprlite/ <- the Python package (app.py, engines/, ...)
assets/ installer/ *.bat launch.py requirements.txt
Almost everything below assumes you have cd wisprlite first. This repo is the desktop app only.
The pipevoice.app website + marketing live in a separate private repo (Powleads/pipevoice-site).
Commands (run from wisprlite/, Windows)
- Run from source:
run.bat— first run creates.venv, installsrequirements.txt, then runspython -m wisprlite. Subsequent runs just activate and launch. Equivalent manual launch after venv exists:python -m wisprlite. - Open the settings GUI:
python -m wisprlite --settings(the app spawns this as a separate process; see Architecture). - Transcribe an existing file:
python -m wisprlite --transcribe(also tray → "Transcribe a file…"). Local whisper by default; Deepgram with speaker labels whenDEEPGRAM_API_KEYis set. - Build the single .exe:
build_exe.bat→dist\WisprLite.exe(PyInstaller onefile, no console, bundles all three engines incl. the local Whisper runtime). - Build the full installer:
build_installer.bat→installer\Output\WisprLite-Setup.exe(runsbuild_exe.batfirst; needs Inno Setup 6 installed). - List microphones (to set
devicein config):python -m sounddevice. - CI:
.github/workflows/build.ymlbuilds the installer on push tomain; av*tag additionally publishes a GitHub Release with the installer attached.
There is no test suite, linter, or formatter configured — don't look for pytest/tox/ruff targets.
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.
- 3d ago First seen · 56 lines · 1,447 tokens per session scan A e7454acfbd48
PipeVoice CLAUDE.md is an instructions file published in the GitHub repository SignalEngine/PipeVoice (24 stars, last pushed 19d ago), licensed MIT. It adds 1,447 tokens to every session, about $0.0072 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 2026-08-30.
Other instructions, from other repositories
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.