stenoai CLAUDE.md

stenoai CLAUDE.md is an instructions file for coding agents from stenolabs/stenoai. It costs 8,179 tokens per session, scanned A, original, MIT.

Repository instructions for Claude Code working on stenolabs/stenoai, an Electron desktop app with a React interface and a Python command-line backend.

In plain words
What is it for?
Use them when modifying the Electron app, React and TypeScript interface, Python commands, build process, or project architecture.
Why use it?
They explain the project structure, development commands, and boundaries between the desktop shell, user interface, and backend so changes fit the existing design.

Instructions file

About the project

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.

stenolabs/stenoai · 1,304 stars · on GitHub · stenoai.co

Install

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.

agentmods
npx agentmods add instructions/stenolabs/stenoai/claude-md
Clone the repo
git clone --depth 1 https://github.com/stenolabs/stenoai

Wrote 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.

agentmods badge for stenoai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stenolabs/stenoai/claude-md.svg)](https://agentmods.dev/instructions/stenolabs/stenoai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stenolabs/stenoai/claude-md"><img src="https://agentmods.dev/badge/instructions/stenolabs/stenoai/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,179 This file is loaded in full into every session.
When invoked 8,179 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08179 $0.08179
Opus 5 $0.04090 $0.04090
Sonnet 5 $0.01636 $0.01636
Haiku 4.5 $0.00818 $0.00818

Measured yesterday against content hash 97cce418358f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 yesterday.

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()` →
CLAUDE.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 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 via ipcMain.handle(...). Handlers shell out to the bundled backend through getBackendPath()process.resourcesPath/stenoai/stenoai (or dist/stenoai/stenoai in dev) using child_process.spawn.
  • Renderer (app/renderer/) is a Vite-built React + TypeScript SPA. Runs with contextIsolation: true and talks to the main process exclusively through the typed bridge in app/preload.jsipc() (app/renderer/src/lib/ipc.ts). Built output lives at app/renderer/dist/index.html and is what Electron loads at runtime.
  • Python CLI (simple_recorder.py, ~2.9k lines, ~60 click commands) is the single entry point bundled by stenoai.spec. Sub-modules in src/: audio_recorder (sounddevice), transcriber (pywhispercpp), summarizer (Ollama HTTP client), ollama_manager (lifecycle of the bundled ollama serve), config (JSON-backed user settings + model registry), folders, models, whisper_models.
  • State across CLI invocations is persisted to recorder_state.json and similar small JSON files — there is no daemon. Long-running recordings are a record subprocess kept alive by the Electron main process.
  • User data lives in ~/Library/Application Support/stenoai/ (recordings/, transcripts/, output/), resolved via src.config.get_data_dirs(). Repo-root recordings//transcripts//output/ dirs are dev-only scratch.
  • Bundled binaries (bin/): Ollama + ffmpeg, downloaded by scripts/download-ollama.sh. PyInstaller copies them into dist/stenoai/ollama/ and dist/stenoai/ffmpeg. Electron then re-bundles dist/stenoai/ as an extraResource. bin/steno-diarize (macOS only) is a separate Swift/CoreML sidecar built by scripts/build-diarize-sidecar.sh — see "Speaker diarization" below.
  • Deep links: app registers the stenoai:// URL scheme. Handler logic is in app/main.js near SHORTCUT_PROTOCOL. Used by macOS Shortcuts: stenoai://record/start?name=... and stenoai://record/stop.

Read the full file on GitHub · 386 lines

Changes

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.

  1. yesterday Changed · +5 lines · +111 tokens per session 97cce418358f
  2. 6d ago First seen · 381 lines · 8,068 tokens per session scan A 72c8c2134102

Subscribe to this mod's changes

stenoai CLAUDE.md is an instructions file published in the GitHub repository stenolabs/stenoai (1,304 stars, last pushed today), licensed MIT. It adds 8,179 tokens to every session, about $0.0409 per session on Opus 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.

Related

Other instructions, from other repositories