Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Pair Programming

ASecurity

Implement a turn-based Driver-Navigator pair programming workflow. One agent (Driver) focuses on implementation and writes code, while the other (Navigator) reviews, validates, and suggests improvements in real time. Roles can swap dynamically based on tasks. Triggers: "페어 프로그래밍", "공동 작업", "드라이버 네비게이터", "pair programming", "driver navigator", "collaborative coding".

10 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsgit

Works with

mcp

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add fritzprix/libr-agent --skill pair-programming --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pair Programming?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Pair Programming
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fritzprix-pair-programming/badge)](https://www.skillsdirectory.com/skills/fritzprix-pair-programming)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: pair-programming
description: >
  Implement a turn-based Driver-Navigator pair programming workflow. One agent (Driver)
  focuses on implementation and writes code, while the other (Navigator) reviews, validates,
  and suggests improvements in real time. Roles can swap dynamically based on tasks.
  Triggers: "페어 프로그래밍", "공동 작업", "드라이버 네비게이터", "pair programming", "driver navigator", "collaborative coding".
---

# Pair Programming

The Pair Programming pattern binds two sessions to a shared workspace (`workspaceOverride`) where one acts as the Driver (editing files, implementing logic) and the other acts as the Navigator (reviewing code, checking architecture, guiding steps) in a turn-based collaborative loop.

## Driver-Navigator Loop

```
┌────────────────────────────────────────────────────────┐
│                   Shared Workspace                     │
│               (Same Workspace Override)                │
└──────────────────────────┬─────────────────────────────┘
             ┌─────────────┴─────────────┐
             ▼                           ▼
      [ Driver Session ] ◄────────► [ Navigator Session ]
        - Write code and implement   - Review design, guide structure
        - Direct file modifications  - Provide feedback (turn-based)
```

## 5-Stage Workflow

1. **Session Selection**: Inspect existing child sessions and reuse an Idle Driver/Navigator session with the matching assistant ID and exact workspace contract through `agent__messageToSession`. Use `reset=true` when beginning a fresh pairing task. Start a new session only when no compatible pair member exists or the required role/workspace differs.
2. **Workspace Configuration**: Ensure both sessions share the exact same `workspaceOverride` directory.
3. **Assign Roles**: Allocate the Driver role to a code-generation model and the Navigator role to an analysis-focused model.
4. **Turn-based Interaction**:
   - The Driver implements a section of code and writes a summary of the edits for the Navigator.
   - The Navigator runs `view_file` or `git diff` on the workspace, checks for issues, and sends feedback/next instructions to the Driver.
5. **Role Rotation**: Swap roles when moving between tasks (e.g., swapping to write test suites). See [role-rotation.md](references/role-rotation.md).
6. **Validation**: Run the final project test pipeline to verify correctness.

---

## 🛠️ MCP Tools Guide

- **Turn Coordination**: The parent session collects the Driver's changes summary and forwards them to the Navigator via `agent__messageToSession` to invoke the next turn, maintaining a lock-step loop.

## References

- [Role rotation](references/role-rotation.md)
- [Turn protocol](references/turn-protocol.md)
- [Diff review checklist](references/diff-review-checklist.md)

Attribution

fritzprixfritzprix
View sourceMore from fritzprix →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →