Pair Programming
Run structured AI pair-programming sessions with role switching, live review, and tests instead of ad-hoc codegen.
Overview
Pair Programming is an agent skill most often used in Build (also Ship review and testing) that runs multi-mode AI pair sessions with live verification and integrated testing.
Install
npx skills add https://github.com/ruvnet/ruflo --skill pair-programmingWhat is this skill?
- Seven collaboration modes: driver, navigator, switch, TDD, review, mentor, debug
- Real-time verification with quality scoring and rollback on failed checks
- Automatic role switching plus continuous security and performance review
- Session persistence: auto-save, recovery, export, and sharing
- Requires Claude Flow CLI (`npm install -g claude-flow@alpha`) and a Git repo
- 7 collaboration modes: driver, navigator, switch, TDD, review, mentor, debug
Adoption & trust: 640 installs on skills.sh; 58.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are coding with an agent but lack structured roles, continuous review, and automatic quality gates so bugs and weak patterns slip through.
Who is it for?
Solo builders using Claude Flow who want TDD, mentoring, or debug sessions with enforced review—not single-shot codegen.
Skip if: Teams without Claude Flow CLI or Git who only need a one-off snippet without session management or verification overhead.
When should I use this skill?
You want AI pair programming with role management, real-time verification, or integrated TDD/review/debug—not unstructured codegen.
What do I get? / Deliverables
You finish sessions with reviewed, tested changes, persisted context, and documented quality scores—ready for commit or a dedicated ship-phase review skill.
- Reviewed code changes with quality/truth scores
- Generated or updated tests with coverage notes
- Exportable pair-programming session record
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is build/agent-tooling because the skill’s core job is collaborative implementation with an agent while you ship features. It orchestrates driver/navigator workflows, TDD, and debugging around agent-assisted coding—not a one-off integration hook.
Where it fits
Navigator mode reviews API changes for security while the agent implements endpoints in driver mode.
Switch mode alternates UI implementation and accessibility checks without losing session state.
TDD mode generates tests and tracks coverage before you tag a release.
Review mode runs continuous best-practice and performance analysis on a PR-sized diff.
How it compares
Structured pair-programming workflow with modes and scoring—not a lightweight linter skill or a single-purpose MCP tool.
Common Questions / FAQ
Who is pair programming for?
Indie and solo developers on Claude Flow who want navigator-style oversight, TDD, or mentor/debug flows while the agent drives implementation.
When should I use pair programming?
During build for feature work and refactors; in ship for review and TDD before merge; when learning a codebase in mentor mode; when debugging with traced verification.
Is pair programming safe to install?
It expects shell, network, and repo access via Claude Flow—review the Security Audits panel on this page before enabling in production repos.
SKILL.md
READMESKILL.md - Pair Programming
# Pair Programming Collaborative AI pair programming with intelligent role management, real-time quality monitoring, and comprehensive development workflows. ## What This Skill Does This skill provides professional pair programming capabilities with AI assistance, supporting multiple collaboration modes, continuous verification, and integrated testing. It manages driver$navigator roles, performs real-time code review, tracks quality metrics, and ensures high standards through truth-score verification. **Key Capabilities:** - **Multiple Modes**: Driver, Navigator, Switch, TDD, Review, Mentor, Debug - **Real-Time Verification**: Automatic quality scoring with rollback on failures - **Role Management**: Seamless switching between driver$navigator roles - **Testing Integration**: Auto-generate tests, track coverage, continuous testing - **Code Review**: Security scanning, performance analysis, best practice enforcement - **Session Persistence**: Auto-save, recovery, export, and sharing ## Prerequisites **Required:** - Claude Flow CLI installed (`npm install -g claude-flow@alpha`) - Git repository (optional but recommended) **Recommended:** - Testing framework (Jest, pytest, etc.) - Linter configured (ESLint, pylint, etc.) - Code formatter (Prettier, Black, etc.) ## Quick Start ### Basic Session ```bash # Start simple pair programming claude-flow pair --start ``` ### TDD Session ```bash # Test-driven development claude-flow pair --start \ --mode tdd \ --test-first \ --coverage 90 ``` --- ## Complete Guide ### Session Control Commands #### Starting Sessions ```bash # Basic start claude-flow pair --start # Expert refactoring session claude-flow pair --start \ --agent senior-dev \ --focus refactor \ --verify \ --threshold 0.98 # Debugging session claude-flow pair --start \ --agent debugger-expert \ --focus debug \ --review # Learning session claude-flow pair --start \ --mode mentor \ --pace slow \ --examples ``` #### Session Management ```bash # Check status claude-flow pair --status # View history claude-flow pair --history # Pause session $pause [--reason <reason>] # Resume session $resume # End session claude-flow pair --end [--save] [--report] ``` ### Available Modes #### Driver Mode You write code while AI provides guidance. ```bash claude-flow pair --start --mode driver ``` **Your Responsibilities:** - Write actual code - Implement solutions - Make immediate decisions - Handle syntax and structure **AI Navigator:** - Strategic guidance - Spot potential issues - Suggest improvements - Real-time review - Track overall direction **Best For:** - Learning new patterns - Implementing familiar features - Quick iterations - Hands-on debugging **Commands:** ``` $suggest - Get implementation suggestions $review - Request code review $explain - Ask for explanations $optimize - Request optimization ideas $patterns - Get pattern recommendations ``` #### Navigator Mode AI writes code while you provide direction. ```bash claude-flow pair --start --mode navigator ``` **Your Responsibilities:** - Provide high-level direction - Review generated code - Make architectural decisions - Ensure business requirements **AI Driver:** - Write implementation code - Handle syntax details - Implement your guidance - Manage boilerplate - Execute refactoring **Best For:** - Rapid prototyping - Boilerplate generation - Learning from AI patterns - Exploring solutions **Commands:** ``` $implement - Direct implementation $refactor - Request refactoring $test - Generate tests $document - A