What is edgeViewLauncher CLAUDE.md?

Project-specific instructions for developing EdgeView Launcher, a Tauri desktop app with a React frontend, Rust core, and Go backend.

Use them when changing the EdgeView Launcher frontend, understanding its communication with the backend, or building and testing the application.

They give the coding agent the project's architecture, safety rules, development commands, and required checks. This helps prevent unsafe changes and keeps frontend work aligned with the repository.

How sergey-zededa/edgeViewLauncher configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sergey-zededa/edgeViewLauncher. 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/sergey-zededa/edgeViewLauncher/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sergey-zededa/edgeViewLauncher

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/sergey-zededa/edgeviewlauncher/claude-md/github.svg)](https://agentmods.dev/instructions/sergey-zededa/edgeviewlauncher/claude-md)

Your own site

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

Per session 2,986 This file is loaded in full into every session.

When invoked 2,986 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	$0.02986	$0.02986
Opus 5.5	$0.01194	$0.01194
Sonnet 5.5	$0.00597	$0.00597
Haiku 4.5	$0.00299	$0.00299

Measured 5d ago against content hash 12fab57d449a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

edgeViewLauncher 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 5d 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 · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 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.

Critical Rules

NEVER DELETE KEYCHAIN ITEMS unless explicitly and unambiguously instructed for a specific item.
NEVER create git tags or trigger release builds unless explicitly instructed.
NEVER commit directly to main. Always work on a feature branch and use PRs.
Do not modify eve/ — it contains reference implementations.
Do NOT include Co-Authored-By attribution in commit messages.
Always run tests and build after modifying code to verify changes.

Architecture

EdgeView Launcher is a Tauri v2 desktop app with three layers:

Tauri Core (Rust) — src-tauri/
  Spawns Go backend as sidecar, creates windows, tray, and IPC commands.
  All frontend API calls go through the generic api_call IPC command,
  which proxies HTTP requests to the Go backend on a dynamic port.

Frontend (React + Vite) — frontend/
  src/App.jsx: main UI — clusters, devices, tunnels, settings
  src/tauriAPI.js: wraps all Tauri invoke() calls
  src/components/TerminalView.jsx: xterm.js terminal over WebSocket
  src/components/VncViewer.jsx: noVNC embedded viewer (overlay in main window)
  vnc.html: standalone VNC window (separate Vite entry point, NOT in src/)
  ⚠️  vnc.html imports noVNC independently from VncViewer.jsx — both
     must be kept in sync for any dependency or import changes.

Go Backend (sidecar) — cmd/edgeview-backend/
  http-server.go: HTTP routes and WebSocket SSH terminal handler
  app.go: business logic, ZEDEDA API integration, session management
  internal/config/: cluster config persistence (~/.edgeview-config.json)
  internal/session/: EdgeView session cache, TCP tunnel management
  internal/ssh/: SSH key generation (~/.ssh/edgeview_rsa)
  internal/zededa/: ZEDEDA Cloud API client

Data flow: React → tauriAPI.js (invoke) → Rust api_call command → HTTP to Go backend on localhost:<dynamic-port>. The port is discovered at startup by parsing the Go backend's stdout log line "HTTP Server starting on :<PORT>".

Read the full file on GitHub · 130 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.

5d ago Changed · +150 tokens per session 12fab57d449a
11d ago Changed · +2 lines · +279 tokens per session 2125b0ddba3d
15d ago Changed · +2 lines · +172 tokens per session d5681d5fab26
1mo ago Changed · +133 tokens per session 2797c04fce6b
1mo ago Changed · +290 tokens per session a2ee3a205d26
1mo ago Changed · -1 lines · +38 tokens per session 9dcc6c7fd554
2mo ago First seen · 127 lines · 1,924 tokens per session scan A 1fb13d35a56f

Subscribe to this mod's changes

edgeViewLauncher CLAUDE.md is an instructions file published in the GitHub repository sergey-zededa/edgeViewLauncher (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 2,986 tokens to every session, about $0.0119 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 2026-08-31.

edgeViewLauncher CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
edgeViewLauncher CLAUDE.mdsergey-zededa/edgeViewLauncher	Instructions file	5	6d ago	Apache-2.0	A	2,986	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

edgeViewLauncher: Instructions file for Claude Code