Plugin

gemini-pair-pipeline

Name: gemini-pair-pipeline
Author: gantisstorm

Multi-agent orchestration for complex coding tasks with Gemini MCP (jamubc/gemini-mcp-tool). Scouts gather raw context, planners synthesize XML architectural instructions for gemini-3-flash-preview. Returns full plan with per-file instructions. Iterative discovery with user checkpoints and parallel execution. Orchestrator manages all context (Gemini is fully one-shot).

Component Overview

/orchestrate

Commands

code-scout, doc-scout +3

Agents

code-quality, gemini-cli

Skills

Hooks

MCP Servers

LSP Servers

Output Styles

Themes

Monitors

Install

npx claudepluginhub GantisStorm/claude-code-repoprompt-codex-plugins --plugin gemini-pair-pipeline

Component Details

Commands (1)

Core Principles

/orchestrate

Start a Gemini Pair Pipeline session for complex multi-file tasks

Agents (5)

code-scout

/code-scout

Investigates codebase and returns raw context for planner agents.

doc-scout

/doc-scout

Researches external documentation and returns raw context for planner agents.

plan-coder

/plan-coder

Implements a single file by parsing full plan for its instructions, then verifies and fixes errors.

planner-continue

/planner-continue

Synthesizes context into XML architectural instructions for Gemini CLI. Uses session continuation for context.

planner-start

/planner-start

Synthesizes context into XML architectural instructions for Gemini CLI. Returns full plan for coders.

Skills (2)

code-quality

/skills/code-quality

Run code quality checks. Use after making code changes, before commits, or when asked to check code quality.

gemini-cli

/skills/gemini-cli

Reference for Gemini CLI usage patterns. Consult before calling gemini via Bash.

README

The Pair Planning Framework

A pluggable multi-agent planning framework for Claude Code. Swap planning engines (Claude, RepoPrompt, Codex, Gemini) while keeping the same discovery agents and execution patterns.

The Core Insight: All planning engines follow the same meta-pattern: Discovery → Planning → Execution. The framework standardizes discovery (code-scout, doc-scout) and execution (plan-coder) while making the planning layer pluggable. This means you can switch between Claude's speed, RepoPrompt's file intelligence, Codex's reasoning depth, or Gemini's stateless simplicity - all using identical workflows.

Core Concept: Pluggable Planning

┌───────────────────────────────────────────────────────────────────────┐
│                     PAIR PLANNING FRAMEWORK                           │
│                                                                       │
│   DISCOVERY (same for all)          PLANNING (choose one)             │
│   ────────────────────────          ─────────────────────             │
│                                                                       │
│   ┌─────────────┐                   ┌─────────────────────────────┐   │
│   │ code-scout  │                   │     Claude    (pair-*)      │   │
│   │ (codebase)  │                   ├─────────────────────────────┤   │
│   └──────┬──────┘    CONTEXT        │   RepoPrompt  (repoprompt-*)│   │
│          │          ─────────►      ├─────────────────────────────┤   │
│   ┌──────┴──────┐                   │     Codex     (codex-*)     │   │
│   │  doc-scout  │                   ├─────────────────────────────┤   │
│   │ (external)  │                   │     Gemini    (gemini-*)    │   │
│   └─────────────┘                   └──────────────┬──────────────┘   │
│                                                    │                  │
│                                                    │ PLAN             │
│                                                    ▼                  │
│                                                                       │
│   EXECUTION (same for all)                                            │
│   ────────────────────────                                            │
│                                                                       │
│   ┌─────────────┐  ┌─────────────┐  ┌─────────────┐                   │
│   │ plan-coder  │  │ plan-coder  │  │ plan-coder  │  (parallel)       │
│   │   file 1    │  │   file 2    │  │   file 3    │                   │
│   └─────────────┘  └─────────────┘  └─────────────┘                   │
└───────────────────────────────────────────────────────────────────────┘

The framework provides:

Shared agents: code-scout, doc-scout, plan-coder (same implementation across plugins)
Pluggable planners: Swap between Claude, RepoPrompt (rp-cli), Codex CLI, or Gemini CLI
Two execution patterns: Pipeline (iterative) or Swarm (one-shot)

Execution Patterns

The framework offers two execution patterns that work with any planning engine.

Pipeline Pattern (Iterative, Human-in-the-Loop)

┌────────────────────────────────────────────────────────────────────────┐
│                       ITERATIVE DISCOVERY LOOP                         │
│                                                                        │
│  code-scout ───► CHECKPOINT ───► doc-scout ───► CHECKPOINT ───► ...    │
│  (background)         │         (background)         │                 │
│       │          User decides         │         User decides           │
│       ▼         "Add research"        ▼        "Complete"              │
│  TaskOutput           │          TaskOutput          │                 │
│       │               │               │              │                 │
│       └───────────────┴───────────────┴──────────────┘                 │
│                               │                                        │
│                       context_package                                  │
└───────────────────────────────┼────────────────────────────────────────┘
                                │
                                ▼
                     ┌────────────────────┐
                     │      PLANNER       │
                     │    (pluggable)     │
                     └─────────┬──────────┘
                               │
               ┌───────────────┼───────────────┐
               ▼               ▼               ▼
        ┌────────────┐  ┌────────────┐  ┌────────────┐
        │ plan-coder │  │ plan-coder │  │ plan-coder │  (background)
        │   file1    │  │   file2    │  │   file3    │
        └──────┬─────┘  └──────┬─────┘  └──────┬─────┘
               │               │               │
               └───────────────┼───────────────┘
                               ▼
                          TaskOutput
                        (collect all)

View full README on GitHub

Similar Plugins

prompts.chat

159.9k

490

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.

Stats

Version1.3.0

Parent Repo Stars2

MaintenanceGood

AddedJan 1, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Available In

claude-code-repoprompt-codex-plugins2

Safety Signals

Caution

Uses power tools

Uses Bash, Write, or Edit tools

Categories

development

Back to Plugins

gemini-pair-pipeline

The Pair Planning Framework

A pluggable multi-agent planning framework for Claude Code. Swap planning engines (Claude, RepoPrompt, Codex, Gemini) while keeping the same discovery agents and execution patterns.

The Core Insight: All planning engines follow the same meta-pattern: Discovery → Planning → Execution. The framework standardizes discovery (code-scout, doc-scout) and execution (plan-coder) while making the planning layer pluggable. This means you can switch between Claude's speed, RepoPrompt's file intelligence, Codex's reasoning depth, or Gemini's stateless simplicity - all using identical workflows.

Core Concept: Pluggable Planning

┌───────────────────────────────────────────────────────────────────────┐ │ PAIR PLANNING FRAMEWORK │ │ │ │ DISCOVERY (same for all) PLANNING (choose one) │ │ ──────────────────────── ───────────────────── │ │ │ │ ┌─────────────┐ ┌─────────────────────────────┐ │ │ │ code-scout │ │ Claude (pair-*) │ │ │ │ (codebase) │ ├─────────────────────────────┤ │ │ └──────┬──────┘ CONTEXT │ RepoPrompt (repoprompt-*)│ │ │ │ ─────────► ├─────────────────────────────┤ │ │ ┌──────┴──────┐ │ Codex (codex-*) │ │ │ │ doc-scout │ ├─────────────────────────────┤ │ │ │ (external) │ │ Gemini (gemini-*) │ │ │ └─────────────┘ └──────────────┬──────────────┘ │ │ │ │ │ │ PLAN │ │ ▼ │ │ │ │ EXECUTION (same for all) │ │ ──────────────────────── │ │ │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │ │ plan-coder │ │ plan-coder │ │ plan-coder │ (parallel) │ │ │ file 1 │ │ file 2 │ │ file 3 │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ │ └───────────────────────────────────────────────────────────────────────┘

The framework provides:

Shared agents: code-scout, doc-scout, plan-coder (same implementation across plugins)

Pluggable planners: Swap between Claude, RepoPrompt (rp-cli), Codex CLI, or Gemini CLI

Two execution patterns: Pipeline (iterative) or Swarm (one-shot)

Execution Patterns

The framework offers two execution patterns that work with any planning engine.

Pipeline Pattern (Iterative, Human-in-the-Loop)

┌────────────────────────────────────────────────────────────────────────┐ │ ITERATIVE DISCOVERY LOOP │ │ │ │ code-scout ───► CHECKPOINT ───► doc-scout ───► CHECKPOINT ───► ... │ │ (background) │ (background) │ │ │ │ User decides │ User decides │ │ ▼ "Add research" ▼ "Complete" │ │ TaskOutput │ TaskOutput │ │ │ │ │ │ │ │ │ └───────────────┴───────────────┴──────────────┘ │ │ │ │ │ context_package │ └───────────────────────────────┼────────────────────────────────────────┘ │ ▼ ┌────────────────────┐ │ PLANNER │ │ (pluggable) │ └─────────┬──────────┘ │ ┌───────────────┼───────────────┐ ▼ ▼ ▼ ┌────────────┐ ┌────────────┐ ┌────────────┐ │ plan-coder │ │ plan-coder │ │ plan-coder │ (background) │ file1 │ │ file2 │ │ file3 │ └──────┬─────┘ └──────┬─────┘ └──────┬─────┘ │ │ │ └───────────────┼───────────────┘ ▼ TaskOutput (collect all)

gemini-pair-pipeline

Component Overview

Install

Component Details

Commands (1)

Agents (5)

Skills (2)

README

The Pair Planning Framework

Core Concept: Pluggable Planning

Execution Patterns

Pipeline Pattern (Iterative, Human-in-the-Loop)

Similar Plugins

prompts.chat

gemini-pair-pipeline

Component Overview

Install

Component Details

Commands (1)

Agents (5)

Skills (2)

README

The Pair Planning Framework

Core Concept: Pluggable Planning

Execution Patterns

Pipeline Pattern (Iterative, Human-in-the-Loop)

Similar Plugins

prompts.chat

agent-teams

claude-code-toolkit

plugin-dev

dotnet-skills

beads