StenoAI is a private desktop notepad and meeting notetaker that records conversations, summarizes them, and lets users query them with local AI models. It is intended for confidential meetings in government, defence, and executive settings on Windows and macOS.
Borrowing it
Nothing to install: this file belongs to stenolabs/stenoai. 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/stenolabs/stenoai/main/CLAUDE.mdgit clone --depth 1 https://github.com/stenolabs/stenoaiWrote 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/stenolabs/stenoai/claude-md)<a href="https://agentmods.dev/instructions/stenolabs/stenoai/claude-md"><img src="https://agentmods.dev/badge/instructions/stenolabs/stenoai/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/stenolabs/stenoai/claude-md"><img src="https://agentmods.dev/badge/instructions/stenolabs/stenoai/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.08856 | $0.08856 |
| Opus 5.5 | $0.03542 | $0.03542 |
| Sonnet 5.5 | $0.01771 | $0.01771 |
| Haiku 4.5 | $0.00886 | $0.00886 |
Grade A, and why
stenoai CLAUDE.md scanned grade A with 1 finding 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 today.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Electron main (`app/main.js`, ~6.2k lines)** owns the UI window, tray, deep-link protocol, and orchestrates everything via `ipcMain.handle(...)`. Handlers shell out to the bundled backend through `getBackendPath()` → How it starts
The opening of the file, as written. The whole thing — 421 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.
Do not use excessive emojis anywhere.
Architecture
The app is a thin Electron shell over a PyInstaller-bundled Python CLI. There is no long-running Python service — every operation is a subprocess invocation.
- Electron main (
app/main.js, ~6.2k lines) owns the UI window, tray, deep-link protocol, and orchestrates everything viaipcMain.handle(...). Handlers shell out to the bundled backend throughgetBackendPath()→process.resourcesPath/stenoai/stenoai(ordist/stenoai/stenoaiin dev) usingchild_process.spawn. - Renderer (
app/renderer/) is a Vite-built React + TypeScript SPA. Runs withcontextIsolation: trueand talks to the main process exclusively through the typed bridge inapp/preload.js→ipc()(app/renderer/src/lib/ipc.ts). Built output lives atapp/renderer/dist/index.htmland is what Electron loads at runtime. - Python CLI (
simple_recorder.py, ~2.9k lines, ~60 click commands) is the single entry point bundled bystenoai.spec. Sub-modules insrc/:audio_recorder(sounddevice),transcriber(pywhispercpp),summarizer(Ollama HTTP client),ollama_manager(lifecycle of the bundledollama serve),config(JSON-backed user settings + model registry),folders,models,whisper_models. - State across CLI invocations is persisted to
recorder_state.jsonand similar small JSON files — there is no daemon. Long-running recordings are arecordsubprocess kept alive by the Electron main process. - User data lives in
~/Library/Application Support/stenoai/(recordings/,transcripts/,output/), resolved viasrc.config.get_data_dirs(). Repo-rootrecordings//transcripts//output/dirs are dev-only scratch. - Bundled binaries (
bin/): Ollama + ffmpeg, downloaded byscripts/download-ollama.sh. PyInstaller copies them intodist/stenoai/ollama/anddist/stenoai/ffmpeg. Electron then re-bundlesdist/stenoai/as anextraResource.bin/steno-diarize(macOS only) is a separate Swift/CoreML sidecar built byscripts/build-diarize-sidecar.sh— see "Speaker diarization" below. - Deep links: app registers the
stenoai://URL scheme. Handler logic is inapp/main.jsnearSHORTCUT_PROTOCOL. Used by macOS Shortcuts:stenoai://record/start?name=...andstenoai://record/stop.
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.
- today Changed · +2 lines · +44 tokens per session 5fd7c51f042a
- 19d ago Changed · +26 tokens per session 90128b5de3c9
- 20d ago Changed · +20 lines · +375 tokens per session 6d2e26737d9f
- 25d ago Changed · +13 lines · +232 tokens per session 434ebf310b9a
- 1mo ago Changed · +5 lines · +111 tokens per session 97cce418358f
- 2mo ago First seen · 381 lines · 8,068 tokens per session scan A 72c8c2134102
stenoai CLAUDE.md is an instructions file published in the GitHub repository stenolabs/stenoai (1,350 stars, last pushed yesterday), licensed MIT. It adds 8,856 tokens to every session, about $0.0354 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.