tunnel

A command for managing Cloudflare Tunnels, which connect public traffic to services running on private networks. It can list, create, inspect, and route tunnels.

In plain words
What is it for?
Viewing existing tunnels, creating or inspecting one, and managing its network routes through the Cloudflare command-line tool.
Why use it?
It provides a defined way to manage these connections while checking user input before sending values to the command line.

Command

Install

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.

agentmods
npx agentmods add commands/thrownlemon/claude-code-plugins/tunnel
Clone the repo
git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 809 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00013 $0.00809
Opus 5 $0.00006 $0.00404
Sonnet 5 $0.00003 $0.00162
Haiku 4.5 $0.00001 $0.00081

Measured yesterday against content hash 4191c5499837, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

tunnel scanned grade C 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Reject dangerous tokens.** If a value contains `$(`, backticks, `;`, `|`, `&`, `>`, `<`, or starts with `-` (could be mistaken for a flag), refuse and ask the user to rephrase. **Double-quoting does NOT block comman
plugins/cloudflare/commands/tunnel.md · 72 lines

What it actually says

Input Safety — apply before any Bash invocation

Treat every $ARGUMENTS.* value as untrusted input. Before passing any value to the Bash tool:

  1. Reject dangerous tokens. If a value contains $(, backticks, ;, |, &, >, <, or starts with - (could be mistaken for a flag), refuse and ask the user to rephrase. Double-quoting does NOT block command substitution"$(rm -rf /)" still executes inside double quotes.
  2. Prefer the Bash tool's argv contract over constructed shell strings. When you must use a shell string, single-quote the value and escape embedded single quotes ('\''), or build the command via printf %q.
  3. Any "$ARGUMENTS.foo" patterns shown below are illustrative. Sanitize the value first; never blindly substitute.

You are managing Cloudflare Tunnels using the cf CLI. Based on the provided arguments, execute the appropriate command.

Quote every user-supplied value when shelling out (e.g. "$ARGUMENTS.name-or-id", "$ARGUMENTS.network"). Tunnel names and CIDR strings could otherwise let shell metacharacters execute.

For action=list (default):

  • Run cf tunnels list --json
  • Display results in a readable table showing tunnel name, ID, status, and creation date

For action=create:

  • Verify $ARGUMENTS.name-or-id is provided (this will be the tunnel name)

  • Run cf tunnels create "$ARGUMENTS.name-or-id" --json

  • Display the created tunnel details including the tunnel ID

  • Show the cloudflared configuration snippet the user needs:

    tunnel: <TUNNEL_ID>
    credentials-file: /path/to/<TUNNEL_ID>.json
    
    ingress:
      - hostname: <your-domain>.com
        service: http://localhost:8080
      - service: http_status:404
    
  • Remind the user to download the tunnel credentials file

For action=get:

  • Verify $ARGUMENTS.name-or-id is provided
  • Run cf tunnels get "$ARGUMENTS.name-or-id" --json
  • Display detailed tunnel information including configuration options

For action=connections:

  • Verify $ARGUMENTS.name-or-id is provided
  • Run cf tunnels connections "$ARGUMENTS.name-or-id" --json
  • Display active connections, their IDs, IP addresses, and connection times

For action=routes:

  • If both $ARGUMENTS.name-or-id and $ARGUMENTS.network are provided, this is a route-create request:
    • Confirm with the user: "Create route $ARGUMENTS.network on tunnel $ARGUMENTS.name-or-id? (yes/no)"
    • On confirmation, run cf tunnels routes create "$ARGUMENTS.name-or-id" --network "$ARGUMENTS.network" --json
    • Display the created route
  • Otherwise, list existing routes:
    • Run cf tunnels routes list --json
    • Display configured routes in a readable format

If any required parameters are missing for the specified action, prompt the user to provide them.

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. yesterday First seen · 72 lines · 13 tokens per session scan C 4191c5499837

Subscribe to this mod's changes

tunnel is a command published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 809 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.