cli-bridge

A bridge to AI command-line programs already installed on the computer, allowing them to provide second opinions or review code together. A command-line program runs through a text-based terminal.

In plain words
What is it for?
Use it for additional opinions, multi-model code reviews, or delegated build work through supported AI command-line tools.
Why use it?
It makes it possible to compare several AI tools without manually copying the same task between them, while using the tools’ normal command-line interfaces.

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 JoaoBerne/cli-bridge-mcp
agentmods
npx agentmods add plugins/joaoberne/cli-bridge-mcp/plugin
Clone the repo
git clone --depth 1 https://github.com/JoaoBerne/cli-bridge-mcp

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

cli-bridge 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 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.

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.

plugin/.claude-plugin/plugin.json · 17 lines

What it actually says

{
  "name": "cli-bridge",
  "displayName": "cli-bridge — council of AI CLIs",
  "description": "Consult your already-installed AI CLIs (Gemini, GPT/Codex, Mistral, opencode, Ollama…) as a council: second opinions, multi-model review, safe delegated builds. Ban-safe (spawns official CLIs, no API keys, no token extraction), with enforced spend caps.",
  "author": { "name": "JoaoBerné" },
  "homepage": "https://github.com/JoaoBerne/cli-bridge-mcp",
  "repository": "https://github.com/JoaoBerne/cli-bridge-mcp",
  "license": "Apache-2.0",
  "keywords": ["mcp", "multi-model", "council", "code-review", "delegation"],
  "mcpServers": {
    "cli-bridge": {
      "command": "uvx",
      "args": ["cli-bridge-mcp"]
    }
  }
}
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 · 17 lines scan A 8d45ea822e05

Subscribe to this mod's changes

cli-bridge is a plugin published in the GitHub repository JoaoBerne/cli-bridge-mcp (2 stars, last pushed 1mo ago), licensed Apache-2.0. 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 2026-08-31.