Borrowing it
Nothing to install: this file belongs to kookoo1sabzy/BaleVPN. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kookoo1sabzy/BaleVPN/main/CLAUDE.mdgit clone --depth 1 https://github.com/kookoo1sabzy/BaleVPNWrote 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/kookoo1sabzy/balevpn/claude-md)<a href="https://agentmods.dev/instructions/kookoo1sabzy/balevpn/claude-md"><img src="https://agentmods.dev/badge/instructions/kookoo1sabzy/balevpn/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.
<a href="https://agentmods.dev/instructions/kookoo1sabzy/balevpn/claude-md"><img src="https://agentmods.dev/badge/instructions/kookoo1sabzy/balevpn/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02648 | $0.02648 |
| Opus 5 | $0.01324 | $0.01324 |
| Sonnet 5 | $0.00530 | $0.00530 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade B, and why
BaleVPN CLAUDE.md scanned grade B 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 10d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo setcap cap_net_admin+eip $(which bale-vpn) How it starts
The opening of the file, as written. The whole thing — 149 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 This Is
A reverse-engineering research project for the Bale messenger web app (web.bale.ai). It extracts protobuf service / message definitions from Bale's minified webpack bundles and ships:
bale-vpn-rust/— a single Rust binary that runs as either VPN client (local SOCKS5 listener over a QUIC channel) or VPN server (TUN-based or userspace NAT bridging traffic from admitted Bale peers to the internet). HTTP management UI on127.0.0.1:3001. CLI:bale-vpn [--port 3001] [--mode client|server] [--nat-mode kernel|userspace] [--headless].bale-vpn-android/— Android app that runs as either VPN client (device-wide TUN viaVpnService, optional LAN-facing SOCKS5) or VPN server (userspace NAT, no root). Mode-toggle in the app's main screen.
Both apps consume the same Rust stack:
lktunnel-rust/— WebRTC transport onwebrtc-rs(pure Rust, no libwebrtc) + QUIC channel + userspace NAT. Reuses crates.iolivekit-api(signal client) +livekit-protocol(wire types); no vendored crates, no patches.lk-signaling-rust/— generic signaling traitbale-signaling-rust/— Bale impl (WS client + RPCs + auth + contacts), single source of truth for the protocol
The Rust and Android server modes are interchangeable: an Android client can connect to either, same wire protocol.
Supported features
| Role | Platform | Notes |
|---|---|---|
| Server | Rust (Linux) | Kernel TUN + iptables MASQUERADE — best throughput. One-time root setup. (Userspace NAT path also works.) |
| Server | Rust (macOS) | Kernel TUN (utunN) + pf anchor — best throughput. Runs as root. |
| Server | Rust (Windows) | Userspace NAT — no root, no driver install. |
| Server | Android | Userspace NAT — no root. APK install, no command line. |
| Client | Rust (any OS) | SOCKS5 listener on 127.0.0.1:1080 (configurable) over a QUIC channel. |
| Client | Android | Kernel TUN via VpnService. Optional LAN-facing SOCKS5 lets other devices on the same WiFi use this Android as their proxy. |
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.
- 10d ago First seen · 149 lines · 2,648 tokens per session scan B 80c632806282
BaleVPN CLAUDE.md is an instructions file published in the GitHub repository kookoo1sabzy/BaleVPN (402 stars, last pushed 2mo ago), licensed MIT. It adds 2,648 tokens to every session, about $0.0132 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.