Enables Claude Code to collaborate with multiple AI backends (Codex, Gemini, Ollama, Claude) through structured Q&A rallies, second-opinion calls, and iterative refinement rounds. Developers can delegate tasks to backend agents, get feedback loops, and synthesize results across models.
Structured Q&A rally between the host orchestrating model and a backend model. Both sides must always reply with ANSWER and QUESTION prefixes. Seeded by topic, runs for N rounds.
Ask Codex, Gemini, Claude, or Ollama for a second opinion through the phone-a-friend CLI while preserving the user's request in --prompt.
Iterative refinement — delegates tasks to backend(s) via agent teams, reviews, iterates up to MAX_ROUNDS rounds, synthesizes result.
Structured Q&A rally between the host orchestrating model and a backend model. Both sides must always reply with ANSWER and QUESTION prefixes. Seeded by topic, runs for N rounds.
Ask Codex, Gemini, Claude, or Ollama for a second opinion through the phone-a-friend CLI while preserving the user's request in --prompt.
Iterative multi-model refinement from inside Codex. Runs N rounds of parallel relays through phone-a-friend to friend backends (Claude, Gemini, OpenCode, Ollama), synthesizes between rounds, and converges on a final answer. No subagent spawn, no Agent Teams primitive: pure Bash orchestration plus the model's own synthesis.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
phone-a-friend is a CLI orchestration layer for AI coding agents.
Relay tasks to any backend, spin up multi-model teams, or run persistent multi-agent sessions.
| Mode | What it does | Best for |
|---|---|---|
| Relay | One-shot delegation to Codex, Gemini, Ollama, Claude, or OpenCode | Quick second opinions, code reviews, analysis |
| Team | Iterative multi-backend refinement over N rounds | Collaborative review, converging on a solution |
| Agentic | Persistent multi-agent sessions with @mention routing | Autonomous collaboration, adversarial review, deep analysis |
| Feature | Claude Code | OpenCode | Codex |
|---|---|---|---|
/phone-a-friend (single + parallel multi-backend relay) | ✓ | ✓ | ✓ |
/curiosity-engine (Q&A rally) | ✓ | ✓ | ✓ |
/phone-a-team (iterative multi-model team) | ✓ | — | ✓ |
| Plugin marketplace install | ✓ | — | ✓ |
CLI plugin install (phone-a-friend plugin install --<host>) | ✓ | ✓ | ✓ |
| Skill auto-discovery | ✓ | ✓ | ✓ |
Recursion guard (PHONE_A_FRIEND_HOST=<host>) | n/a | ✓ | ✓ |
Claude /phone-a-team orchestrates rounds via the Agent Teams primitive (TeamCreate + Task + SendMessage). Codex /phone-a-team is pure Bash orchestration directly from the skill body, with Codex's own model handling the synthesis between rounds. OpenCode has no comparable primitive and replicates /phone-a-team by running repeated /phone-a-friend calls manually.
[!IMPORTANT] Codex users: Codex's default
workspace-writesandbox blocks subprocess access to the macOS Keychain (where Claude stores OAuth tokens) and OAuth refresh network paths (Gemini). With the default sandbox, relays to Claude fail with a misleadingNot logged inand Gemini hangs until the timeout. Two workarounds today, both with tradeoffs:Option A — Lower the sandbox. Per-session (preferred): launch Codex with
codex --sandbox danger-full-access. Persistent (convenient but removes sandbox protections from every Codex session, not just PaF relays): add an alias to~/.zshrcor~/.bashrc:alias codex='codex --sandbox danger-full-access'Option B — Use API keys. Skips OAuth entirely, works in any sandbox:
export ANTHROPIC_API_KEY=... export GEMINI_API_KEY=...A portable-auth path via
claude setup-tokenis planned for the Claude side. Gemini OAuth refresh inside the sandbox is a separate open issue with no planned fix yet — until then, Option B is the only Gemini-safe path that keeps the sandbox intact.
Prerequisites: Node.js 22.13+ and at least one backend:
Install:
npm install -g @freibergergarcia/phone-a-friend
phone-a-friend # first run shows a guided menu — choose Setup
The setup wizard detects your backends, offers to install detected host integrations, and verifies everything works.
Claude Code marketplace (commands and skills only):
/plugin marketplace add freibergergarcia/phone-a-friend
/plugin install phone-a-friend@phone-a-friend-marketplace
To update: /plugin marketplace update phone-a-friend-marketplace then /plugin update phone-a-friend@phone-a-friend-marketplace.
[!NOTE] Marketplace install ships only the slash commands and skills. For the full CLI (agentic mode and TUI), install via
npm install -g @freibergergarcia/phone-a-friend.
OpenCode commands and skills:
If you use OpenCode, install the same Phone-a-Friend skills plus thin slash-command shims into your OpenCode config:
phone-a-friend plugin install --opencode
npx claudepluginhub freibergergarcia/phone-a-friendPersistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.