What is dictate CLAUDE.md?

A project instruction file for Dictate, a Linux voice-to-text tool for Claude Code. It explains local speech transcription and sending audio to a remote computer with a GPU.

Use it when developing Dictate, running its daemon or push-to-talk mode, or configuring transcription through a remote GPU server.

It gives a coding agent the project context and commands needed to work on, install, update, and run the tool.

How vimalk78/dictate configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vimalk78/dictate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/vimalk78/dictate/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vimalk78/dictate

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vimalk78/dictate/claude-md/github.svg)](https://agentmods.dev/instructions/vimalk78/dictate/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vimalk78/dictate/claude-md"><img src="https://agentmods.dev/badge/instructions/vimalk78/dictate/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/vimalk78/dictate/claude-md"><img src="https://agentmods.dev/badge/instructions/vimalk78/dictate/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,317 This file is loaded in full into every session.

When invoked 2,317 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02317	$0.02317
Opus 5.5	$0.00927	$0.00927
Sonnet 5.5	$0.00463	$0.00463
Haiku 4.5	$0.00232	$0.00232

Measured 26d ago against content hash 52152820fb36, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dictate 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 26d 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.

CLAUDE.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 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.

What is this

Dictate is a voice-to-text tool for Claude Code on Linux. It records speech using faster-whisper and outputs text via clipboard or stdout. Supports local transcription or forwarding audio to a remote GPU server over TCP. Single Python script (dictate), no build system.

Development

Running locally

bash install.sh                    # checks requirements (prints fix commands, never sudo), then venv + launcher; also the upgrade path (detects an existing install, asks, restarts running services)
bash uninstall.sh                  # remove everything (asks before config/models; --purge to skip)
bash install-service.sh            # install and start systemd services
bash update.sh                     # update after code changes (no venv rebuild; refuses if requirements.lock changed)
dictate --serve &                  # start daemon (keeps Whisper model in memory)
dictate --once                     # send one request to daemon, print text
dictate                            # standalone push-to-talk mode (no daemon)

# Network transcription (remote GPU)
dictate --serve --listen 0.0.0.0:5555   # on GPU machine: headless transcription server
dictate --serve --server GPU_IP:5555    # on laptop: daemon forwarding to remote
dictate --once                          # client unchanged

After install, reboot or re-login once for input group membership (required for evdev access).

After code changes, run bash update.sh to deploy — it copies the script, service files, and restarts running services. No venv rebuild needed. If requirements.lock changed since the last install (compared with the copy in ~/.local/share/dictate/), it refuses and asks for install.sh instead.

Testing

Install test (fresh distro in a podman container — run before each release):

bash tests/install-test.sh fedora:44     # also: ubuntu:24.04, ubuntu:22.04 (Python 3.10, like Jetson)

Read the full file on GitHub · 156 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.

26d ago Changed · +3 lines · +130 tokens per session 52152820fb36
1mo ago Changed · +12 lines · +360 tokens per session 3b0e98ff5064
2mo ago First seen · 141 lines · 1,827 tokens per session scan A 7139323b7bf5

Subscribe to this mod's changes

dictate CLAUDE.md is an instructions file published in the GitHub repository vimalk78/dictate (24 stars, last pushed 26d ago), licensed MIT. It adds 2,317 tokens to every session, about $0.0093 per session on Opus 5.5. 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.

Languages

dictate CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dictate CLAUDE.mdvimalk78/dictate	Instructions file	24	26d ago	MIT	A	2,317	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

dictate: Instructions file for Claude Code