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/peripan/openwhisperer/claude-mdgit clone --depth 1 https://github.com/PerIPan/OpenWhispererWrote 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/peripan/openwhisperer/claude-md)<a href="https://agentmods.dev/instructions/peripan/openwhisperer/claude-md"><img src="https://agentmods.dev/badge/instructions/peripan/openwhisperer/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 | $0.00276 | $0.00276 |
| Opus 5 | $0.00138 | $0.00138 |
| Sonnet 5 | $0.00055 | $0.00055 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
OpenWhisperer 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 6d 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
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
Open Whisperer is a macOS menubar app (Swift/SwiftUI, Apple Silicon, macOS 14+) that adds full voice mode to Claude Code, Codex CLI, and Pi: dictation in (speech→text, typed into the focused app) and spoken replies out (text→speech). Everything runs locally — no cloud APIs.
The README describes an obsolete architecture.
README.mddocuments an out-of-process Python server (unified_server.py, FastAPI, uvicorn, spaCy, MLX Whisper, a~/mlx-openai-whispervenv,setup.sh,servers/start-servers.sh). All of that is gone. The app was ported to pure Swift with both models running in-process on the ANE.setup.shandservers/start-servers.shno longer exist; ignore the README's Python/setup sections for anything architectural. The README's[VOICE:]tag mechanism is also vestigial (see "Voice-turn handshake" below).
For commands, testing, changes workflow, commit message rules, architecture details, and developer conventions: See @AGENTS.md
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.
- 6d ago First seen · 13 lines · 276 tokens per session scan A 9983bb9e7cf4
OpenWhisperer CLAUDE.md is an instructions file published in the GitHub repository PerIPan/OpenWhisperer (5 stars, last pushed 3d ago), licensed MIT. It adds 276 tokens to every session, about $0.0014 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
speech-swift AGENTS.md
AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
Vocello AGENTS.md
AGENTS.md instructions for PowerBeef/Vocello, covering agents.md — vocello (qwenvoice), product and authority, start and resume work, release-first execution and hard invariants.
Logue CLAUDE.md
Claude Code instructions for bitwize-ai/Logue, covering logue — development guidelines, project overview, running the build you just made, where documentation goes and dependencies.
localvoxtral AGENTS.md
AGENTS.md instructions for T0mSIlver/localvoxtral, covering localvoxtral — agent guide, build & test — read this first on a non-mac dev box, proof culture — non-negotiable, test tiers — the short version and ci / shipping.
OpenSuperMLX AGENTS.md
AGENTS.md instructions for axot/OpenSuperMLX, covering agents.md — opensupermlx, agent behavioral guidelines, 1. think before coding, 2. simplicity first and 3. surgical changes.
memo CLAUDE.md
Claude Code instructions for jagoff/memo, covering claude.md, dev commands, type checking, lint + format and run the cli.