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.
npx agentmods add instructions/sergey-zededa/edgeviewlauncher/agents-mdgit clone --depth 1 https://github.com/sergey-zededa/edgeViewLauncherWrote 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/sergey-zededa/edgeviewlauncher/agents-md)<a href="https://agentmods.dev/instructions/sergey-zededa/edgeviewlauncher/agents-md"><img src="https://agentmods.dev/badge/instructions/sergey-zededa/edgeviewlauncher/agents-md.svg" alt="Measured on agentmods" 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 | $0.02319 | $0.02319 |
| Opus 5 | $0.01159 | $0.01159 |
| Sonnet 5 | $0.00464 | $0.00464 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
edgeViewLauncher AGENTS.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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI Agents (including WARP) when working with code in this repository.
Critical Rules
IMPORTANT:
- NEVER DELETE KEYCHAIN ITEMS: You are strictly forbidden from deleting items from the user's keychain (e.g., via
security delete-generic-password) unless explicitly and unambiguously instructed to do so by the user for a specific item. - NEVER create git tags or trigger release builds (CI/CD) unless explicitly instructed by the user.
- ALWAYS work using PR process:
- Create a new branch for every task or set of changes.
- NEVER commit directly to the
mainormasterbranch. - Push your branch to the remote to facilitate PR creation.
- Write meaningful commit messages:
- Include decent human-readable comments describing the changes.
- This ensures GitHub produces meaningful "What's changed" messages for every new release.
- Do not modify
eve/directory contents as they are reference implementations. - ALWAYS run tests and build after modifying code to verify changes:
- Check your current directory (
pwd) before running commands. - If in project root (
edgeViewLauncher/):- Frontend:
npm run build:frontend(orcd frontend && npm run build) - Backend:
go build -o edgeview-backend ./cmd/edgeview-backend
- Frontend:
- If in frontend directory (
edgeViewLauncher/frontend/): - Frontend:
npm run build(DO NOT runcd frontendagain)- Backend:
cd .. && go build -o edgeview-backend ./cmd/edgeview-backend
- Backend:
- Check your current directory (
- Commit Message Attribution:
- DO NOT include the
Co-Authored-Byattribution line in commit messages.
- DO NOT include the
Project Overview
EdgeView Launcher is a Tauri desktop application with a Go backend sidecar for managing remote ZEDEDA edge devices. It provides SSH terminal access, VNC remote desktop, and TCP tunneling through EdgeView proxy connections.
Architecture
┌──────────────────────────────────────────────────────────────────────────┐
│ Tauri Core (Rust) │
│ src-tauri/src/main.rs │
│ - Spawns Go backend as sidecar (edgeview-backend) │
│ - Creates WebviewWindow, tray menu, native dialogs │
│ - Handles IPC commands (api_call, open_terminal_window) │
└─────────────────────────────┬────────────────────────────────────────────┘
│ IPC via invoke() / listen()
┌─────────────────────────────▼────────────────────────────────────────────┐
│ Frontend (React + Vite) │
│ frontend/src/ │
│ ├── App.jsx – Main UI (search, settings, device details) │
│ ├── tauriAPI.js – Wraps Tauri commands for API calls │
│ └── components/ │
│ ├── TerminalView.jsx – xterm.js WebSocket terminal │
│ └── VncViewer.jsx – NoVNC remote desktop viewer │
└─────────────────────────────┬────────────────────────────────────────────┘
│ HTTP/WebSocket to localhost:<dynamic-port>
┌─────────────────────────────▼────────────────────────────────────────────┐
│ Go Backend │
│ http-server.go – HTTP API routes, WebSocket SSH terminal handler │
│ app.go – Business logic, session management, ZEDEDA integration│
│ │
│ internal/ │
│ ├── config/ – Cluster configuration persistence (~/.edgeview-config)│
│ ├── session/ – EdgeView session cache, TCP tunnel management │
│ ├── ssh/ – SSH key generation and management │
│ └── zededa/ – ZEDEDA Cloud API client (devices, apps, EdgeView) │
└──────────────────────────────────────────────────────────────────────────┘
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.
- 3d ago First seen · 173 lines · 2,319 tokens per session scan A dd10ee2b205c
edgeViewLauncher AGENTS.md is an instructions file published in the GitHub repository sergey-zededa/edgeViewLauncher (5 stars, last pushed 9d ago), licensed Apache-2.0. It adds 2,319 tokens to every session, about $0.0116 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.
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).
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.
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.