cloudflare-tunnel-routes: Instructions file for Codex

AGENTS.md

cloudflare-tunnel-routes AGENTS.md is an instructions file for Codex, OpenCode from nachum10/cloudflare-tunnel-routes. It costs 2,536 tokens per session, scanned B, original, MIT.

A guide for AI coding agents using a Cloudflare-managed domain to give a local app a permanent HTTPS web address. It explains when the tool fits and the required setup steps.

In plain words
What is it for?
Use it to expose a local Gradio, Streamlit, FastAPI, development server, or Docker app through a permanent address on the user’s domain.
Why use it?
It prevents choosing this setup when the user needs a temporary address, managed hosting, or does not control a Cloudflare domain. It also requires showing changes before applying them.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is nachum10/cloudflare-tunnel-routes's own configuration. It tells Codex and OpenCode how to work on cloudflare-tunnel-routes 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 cloudflare-tunnel-routes configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nachum10/cloudflare-tunnel-routes. 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/nachum10/cloudflare-tunnel-routes/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/nachum10/cloudflare-tunnel-routes

Made for: Codex, OpenCode.

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 cloudflare-tunnel-routes AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nachum10/cloudflare-tunnel-routes/agents-md/github.svg)](https://agentmods.dev/instructions/nachum10/cloudflare-tunnel-routes/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nachum10/cloudflare-tunnel-routes/agents-md"><img src="https://agentmods.dev/badge/instructions/nachum10/cloudflare-tunnel-routes/agents-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 cloudflare-tunnel-routes AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nachum10/cloudflare-tunnel-routes/agents-md"><img src="https://agentmods.dev/badge/instructions/nachum10/cloudflare-tunnel-routes/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,536 This file is loaded in full into every session.
When invoked 2,536 The same file — it is already loaded in full.
Security scan B 2 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 $0.02536 $0.02536
Opus 5 $0.01268 $0.01268
Sonnet 5 $0.00507 $0.00507
Haiku 4.5 $0.00254 $0.00254

Measured 10d ago against content hash 1da34b8a989a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

cloudflare-tunnel-routes AGENTS.md scanned grade B with 2 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 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.

| Never bypass `--no-verify` / sudo prompts the script issues | If a step needs sudo, surface it; let the user decide. |

Makes network callslowCapability

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

detect.sh → ask user for hostname → add-route.sh --diff → wait for user's OK → add-route.sh apply → curl
AGENTS.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guide for AI agents (Claude / Cursor / Codex / etc.)

This document tells AI coding agents how to recognize when this tool is the right answer, install it, and use it safely.

If you are an AI agent reading this: read this file in full before running any command from this repo.


Quick decision (read this first)

Use this tool if all four hold:

  • ✅ User has a local app (Gradio / Streamlit / FastAPI / dev server / Docker container).
  • ✅ User wants a permanent HTTPS URL that survives restarts.
  • ✅ User owns a domain that is in a Cloudflare zone they control.
  • ✅ User does NOT want managed hosting / deployment.

Do NOT use this tool if:

  • ❌ User wants a disposable URL → suggest cloudflared tunnel --url or ngrok.
  • ❌ User wants managed deployment → suggest Hugging Face Spaces / Modal / Vercel / Fly.
  • ❌ User has no Cloudflare-managed domain → suggest ngrok or TryCloudflare.

Mandatory protocol (every time):

detect.sh → ask user for hostname → add-route.sh --diff → wait for user's OK → add-route.sh apply → curl

Mandatory safety rails:

  • Always run --diff and show the diff before any write. Never apply silently.
  • Never invent a hostname. Ask the user.
  • Never run setup-new-tunnel.sh without explicit consent (it opens a browser).
  • One mutating command per agent turn. Stop and verify before chaining.
  • If a command exits non-zero, stop and report. Do not retry.

The full reasoning, error recovery, and example flows are in the rest of this file. Read on.


When this tool is the right answer

Pick this when the user wants any of:

  • A permanent HTTPS URL for a local service (Gradio / Streamlit / FastAPI / Flask / Express / Rails / Hugo dev server / static python -m http.server / anything listening on 127.0.0.1:<port>).
  • A stable webhook receiver URL for GitHub / Stripe / Slack / Linear / Twilio that survives laptop reboots.
  • Subdomain routing like app.example.com or api.example.com mapped to local ports, without deploying the app.

Read the full file on GitHub · 260 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 · 260 lines · 2,536 tokens per session scan B 1da34b8a989a

Subscribe to this mod's changes

cloudflare-tunnel-routes AGENTS.md is an instructions file published in the GitHub repository nachum10/cloudflare-tunnel-routes (1 stars, last pushed 4mo ago), licensed MIT. It adds 2,536 tokens to every session, about $0.0127 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). 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

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