JoaoBerne

JoaoBerne/cli-bridge-mcp

Plugin Claude Code

Consult a council of AI CLIs (Gemini, GPT, Mistral, opencode, Ollama…) — ban-safe, no API keys, budget-capped.

JoaoBerne/cli-bridge-mcp

Instructions file CodexOpenCode

Instructions for JoaoBerne/cli-bridge-mcp, covering agent guide — cli-bridge, what this is, layout, rules for changes and commands.

JoaoBerne/cli-bridge-mcp

Instructions file

Instructions for JoaoBerne/cli-bridge-mcp, a project described as: Your AI assistant, but it can phone a friend — an MCP server that consults a council of other AI CLIs. Ban-safe (no API keys, no token extraction), local cost cap, and it ships the eval that tests its own claim.

JoaoBerne/cli-bridge-mcp

Plugin Claude Code

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.

JoaoBerne/cli-bridge-mcp

Skill Claude CodeCodex

Ask several other AI CLIs (Gemini, GPT, Mistral, opencode, Ollama…) the same question in parallel and compare their answers — a second opinion from models outside Claude.

JoaoBerne/cli-bridge-mcp

Skill Claude CodeCodex

Multi-model code review of the current git diff — several AI CLIs review independently, findings are deduplicated and confidence-ranked by cross-model agreement.

JoaoBerne/cli-bridge-mcp

Skill Claude CodeCodex

Cross-model security review of the current git diff — independent AI CLIs hunt vulnerabilities; decorrelated models catch what a single reviewer misses.

JoaoBerne/cli-bridge-mcp

Skill Claude CodeCodex

First-run cli-bridge onboarding — see which AI CLIs are installed, set the cost profile and spend caps, and learn what the council can do.

JoaoBerne/cli-bridge-mcp

MCP server Claude CodeCodexCursor +2

Consult a council of AI CLIs (Gemini, GPT, Claude, Mistral, Qwen, Copilot, OpenCode…) from inside any MCP client — free and ban-safe. Runs locally from the cli-bridge-mcp Python package. Needs 3 environment variables to run.