vzt-flow: Instructions file for Claude Code

CLAUDE.md

vzt-flow CLAUDE.md is an instructions file for Claude Code from vonzelle-vzt/vzt-flow. It costs 4,707 tokens per session, scanned A, original, MIT.

A set of instructions for VZT Flow, a private voice-dictation app that runs on a Mac and turns speech into text wherever the cursor is. It also includes an MCP server, which lets coding assistants call the app's functions.

In plain words
What is it for?
It helps maintain audio capture, speech transcription, text cleanup, shortcuts, snippets, history, meeting transcripts, and the desktop app.
Why use it?
It gives contributors the project layout, build commands, test guidance, and important rules for working across Rust, desktop, and assistant-integration code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is vonzelle-vzt/vzt-flow's own configuration. It tells Claude Code how to work on vzt-flow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vzt-flow configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is open ../../target/release/bundle/dmg/*.dmg # bundle lands at workspace-root target/, not src-tauri/target/.

Reuse

Borrowing it

Nothing to install: this file belongs to vonzelle-vzt/vzt-flow. 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/vonzelle-vzt/vzt-flow/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vonzelle-vzt/vzt-flow

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.

agentmods badge for vzt-flow CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vonzelle-vzt/vzt-flow/claude-md/github.svg)](https://agentmods.dev/instructions/vonzelle-vzt/vzt-flow/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vonzelle-vzt/vzt-flow/claude-md"><img src="https://agentmods.dev/badge/instructions/vonzelle-vzt/vzt-flow/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.

agentmods 80×15 button for vzt-flow CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vonzelle-vzt/vzt-flow/claude-md"><img src="https://agentmods.dev/badge/instructions/vonzelle-vzt/vzt-flow/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,707 This file is loaded in full into every session.
When invoked 4,707 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04707 $0.04707
Opus 5 $0.02354 $0.02354
Sonnet 5 $0.00941 $0.00941
Haiku 4.5 $0.00471 $0.00471

Measured 12d ago against content hash 9255fb847b3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vzt-flow 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 12d 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 · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — VZT Flow

Local, private, on-device voice dictation for macOS (+ experimental Windows). Hold a key, talk, transcript lands wherever the cursor is — no cloud, no subscription. Full product context: docs/PRD.md. Full user docs: README.md, docs/USAGE-macOS.md, docs/USAGE-Windows.md, docs/MEETINGS.md.

Workspace layout

crates/flow-core/   engine: audio capture, ASR (Parakeet), LLM cleanup, dictionary,
                     code mode, snippets, profiles, history, hotkey, paste,
                     model download/management, daemon IPC. Platform-agnostic;
                     macOS-only pieces are #[cfg(target_os = "macos")]-gated.
crates/flow-cli/     the `flow` binary — daemon-first, standalone fallback.
apps/desktop/        Tauri 2 menu-bar app: tray, overlay, Settings, hotkey,
                     daemon control socket (apps/desktop/src-tauri/src/).
mcp/                 Node/TypeScript MCP server (listen, transcribe_file,
                     dictation_history, meeting_transcript) for Claude Code.

Build / test / run

source ~/.cargo/env                                   # Rust not on PATH by default here

cargo build --release -p flow-cli
cargo test --release --workspace
./target/release/flow doctor                          # env/model/daemon sanity check

cd apps/desktop && npm install && cargo tauri build    # unsigned local build
open ../../target/release/bundle/dmg/*.dmg             # bundle lands at workspace-root target/, not src-tauri/target/

cd mcp && npm install && npm run build

Critical gotchas

(a) Unsigned rebuilds drop macOS TCC grants. Every unsigned/ad-hoc-signed cargo tauri build mints a new code signature; macOS silently revokes Input Monitoring/Accessibility grants tied to the old one — no error dialog, the hotkey just stops working. After any rebuild: relaunch the daily-driver app via nohup <dev-path-binary> & (e.g. nohup ./target/release/bundle/macos/VZT\ Flow.app/Contents/MacOS/vzt-flow &), not openopen re-resolves to whatever's in /Applications and can mask which binary you're actually testing. Never kill the user's running daily-driver app without relaunching it — they lose their dictation tool mid-session. See docs/USAGE-macOS.md#the-rebuild-drops-permissions-gotcha for the full remove/re-add grant fix.

Read the full file on GitHub · 305 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. 12d ago First seen · 305 lines · 4,707 tokens per session scan A 9255fb847b3a

Subscribe to this mod's changes

vzt-flow CLAUDE.md is an instructions file published in the GitHub repository vonzelle-vzt/vzt-flow (5 stars, last pushed yesterday), licensed MIT. It adds 4,707 tokens to every session, about $0.0235 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.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens