GreenTunnel: Instructions file for Claude Code

CLAUDE.md

GreenTunnel CLAUDE.md is an instructions file for Claude Code from SadeghHayeri/GreenTunnel. It costs 11,732 tokens per session, scanned A, original, MIT.

Repository instructions for GreenTunnel, a local proxy that bypasses certain deep-packet inspection censorship by splitting TLS connection data and using encrypted DNS. They also describe the TypeScript v3 layout and development commands.

In plain words
What is it for?
They are for installing dependencies, building, type-checking, linting, testing, running checks, starting development mode, and understanding the CLI and desktop app.
Why use it?
They warn developers about the current codebase structure and about commands that can change the computer's real system proxy.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is SadeghHayeri/GreenTunnel's own configuration. It tells Claude Code how to work on GreenTunnel 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 GreenTunnel configures →

About the project

GreenTunnel is an anti-censorship utility that runs a local proxy to help bypass ISP website blocking based on deep packet inspection. It is for people who need to reach websites blocked through hostname-based filtering; it does not hide the user's IP address or act as a VPN. The catalogue instruction relates to using GreenTunnel.

SadeghHayeri/GreenTunnel · 4,907 stars · on GitHub

Reuse

Borrowing it

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

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 GreenTunnel CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sadeghhayeri/greentunnel/claude-md"><img src="https://agentmods.dev/badge/instructions/sadeghhayeri/greentunnel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11,732 This file is loaded in full into every session.
When invoked 11,732 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.11732 $0.11732
Opus 5 $0.05866 $0.05866
Sonnet 5 $0.02346 $0.02346
Haiku 4.5 $0.01173 $0.01173

Measured 10d ago against content hash 57edd963ed15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

GreenTunnel CLAUDE.md scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Add `--remote-debugging-port=9333` and `curl -s localhost:9333/json/list` to
CLAUDE.md · 806 lines

How it starts

The opening of the file, as written. The whole thing — 806 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GreenTunnel v3

Ground-up TypeScript rewrite of GreenTunnel: a local proxy that bypasses DPI censorship by splitting the TLS ClientHello so the SNI never appears whole in a single packet, and by resolving hostnames over encrypted DNS.

v3 reuses v2's techniques, not its code. v3 is the repository now — it was developed in a v3/ subdirectory and promoted to the root, replacing v2's src/, bin/ and gui/. Those are gone from the working tree; read them at the v2.0.3 tag (git show v2.0.3:src/proxy.js) and treat them as reference material, not as something to keep in sync.

Status: working base. The engine, CLI and desktop app all build, pass lint and tests, and have been exercised end-to-end. Features and packaging are the next phase — see Roadmap.

Commands

Run everything from the repository root.

npm install            # workspaces: packages/*, apps/*

npm run build          # tsc --build (cli) + electron-vite build (desktop)
npm run typecheck      # all three TS projects
npm run lint           # eslint, type-aware
npm test               # vitest
npm run check          # typecheck + lint + test

npm run dev            # electron-vite dev — the desktop app, with HMR
npm run dev:cli        # build the CLI and run it

npm run clean          # drop dist/, out/, release/, build info

Per package:

npm run build --workspace packages/cli           # the engine and the CLI
npm run package --workspace apps/desktop         # electron-builder, current OS
npm run package:mac --workspace apps/desktop     # or :win / :linux

Running the CLI

node packages/cli/dist/main.js --help
node packages/cli/dist/main.js --port 8080 --no-system-proxy

⚠️ npm run dev changes your real system proxy

Default settings are startOnLaunch: true + manageSystemProxy: true, so launching the app points macOS/Windows/GNOME at it. For iterating on UI or main-process code, use a throwaway profile instead:

mkdir -p /tmp/gt-profile
cat > /tmp/gt-profile/settings.json <<'JSON'
{ "startOnLaunch": false, "manageSystemProxy": false, "launchAtLogin": false,
  "port": 18500, "dnsMode": "doh", "fragmentSize": 40, "tlsRecords": false }
JSON
npm run build --workspace apps/desktop
./node_modules/.bin/electron apps/desktop --user-data-dir=/tmp/gt-profile

Read the full file on GitHub · 806 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. 10d ago First seen · 806 lines · 11,732 tokens per session scan A 57edd963ed15

Subscribe to this mod's changes

GreenTunnel CLAUDE.md is an instructions file published in the GitHub repository SadeghHayeri/GreenTunnel (4,907 stars, last pushed 6d ago), licensed MIT. It adds 11,732 tokens to every session, about $0.0587 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

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

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 · 7,104 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

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