agent-tunnel

A plugin that publishes the current Claude Code session so teammates can ask it questions through a Discord bot.

In plain words
What is it for?
Use it to share an active Claude coding session with teammates and receive their questions through Discord.
Why use it?
It lets other people access and discuss the session without needing to work directly in the same local terminal.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add pchalasani/claude-code-tools
agentmods
npx agentmods add plugins/pchalasani/claude-code-tools/agent-tunnel
Clone the repo
git clone --depth 1 https://github.com/pchalasani/claude-code-tools

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agent-tunnel 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 2d 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.

plugins/agent-tunnel/.claude-plugin/plugin.json · 9 lines

What it actually says

{
  "name": "agent-tunnel",
  "version": "1.14.2",
  "description": "Publish the current Claude session via >share so teammates can ask it questions through the agent-tunnel Discord bot",
  "author": {
    "name": "Prasad Chalasani"
  }
}
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. 2d ago First seen · 9 lines scan A 86b8315a453c

Subscribe to this mod's changes

agent-tunnel is a plugin published in the GitHub repository pchalasani/claude-code-tools (1,989 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.

Related

Other plugins, from other repositories

harness-eval

Evaluate AI agent setups for best practices, redundancy, security, and cross-component issues.

redhat-community-ai-tools/harness-eval · not measured

trundle

Turn your solo Claude Code conversation into a turn-based group discussion with codex / gemini / other CLI agents — you stay in as a participant, not a report reader.

PouLJenny/trundle · not measured

agentcrew-dev-skills

The multi-agent orchestration layer for mattpocock-skills: /route classifies and splits a spec's tickets across your Claude and Codex subscriptions, /crew runs them as unattended waves of tmux child agents.

okqixiaobao727-design/agentcrew-dev-skills · not measured

mcp-reconnect

Reconnect MCP servers in Claude Code tmux sessions via automated key injection. No API required — works by driving the /mcp interactive menu through tmux send-keys.

palios-taey/mcp-reconnect · not measured

claudebox

Claude Code running in an isolated Docker container, driven via interactive shell, one-shot exec, an HTTP REST API, an OpenAI-compatible chat/completions adapter, an MCP server, a Telegram bot, and a YAML cron scheduler.

psyb0t/docker-claudebox · not measured

supergoal

Plan and autonomously build a software task end-to-end. Recons the codebase, applies preloaded memory, decomposes into the right number of phases, gets one confirmation, then prepares a single ready-to-paste /goal command — one paste between you and done — that drives execution to completion with built-in retry…

robzilla1738/supergoal · not measured