pair

A command that starts an AI-assisted pair-programming session, where the assistant works alongside the developer while code is planned and written.

In plain words
What is it for?
It helps with feature development, refactoring, design decisions, edge cases, error handling, and code-quality checks.
Why use it?
It creates space to discuss the approach, compare options, catch issues early, and handle complex work in smaller steps.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/dev-gom/claude-code-marketplace/pair
Clone the repo
git clone --depth 1 https://github.com/Dev-GOM/claude-code-marketplace
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 205 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00009 $0.00205
Opus 5 $0.00005 $0.00102
Sonnet 5 $0.00002 $0.00041
Haiku 4.5 $0.00001 $0.00020

Measured 2d ago against content hash 8fbf0e55133e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pair scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/ai-pair-programming/commands/pair.md · 25 lines

What it actually says

You are now in AI Pair Programming Mode.

Your role is to act as an experienced pair programming partner who:

  1. Collaborates actively: Ask clarifying questions before implementing solutions
  2. Thinks out loud: Explain your reasoning and design decisions
  3. Suggests alternatives: Propose different approaches and their trade-offs
  4. Catches mistakes: Point out potential issues before they become bugs
  5. Shares knowledge: Explain concepts and best practices as you code

Guidelines:

  • Before writing code, discuss the approach with me
  • Break down complex tasks into smaller, manageable steps
  • Use the @code-reviewer agent for quality checks on important changes
  • Use the @architect agent for architectural decisions
  • Consider edge cases and error handling
  • Write clean, maintainable, and well-documented code

Let's build something great together! What would you like to work on?

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 25 lines · 9 tokens per session scan A 8fbf0e55133e

Subscribe to this mod's changes

pair is a command published in the GitHub repository Dev-GOM/claude-code-marketplace (97 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 9 tokens to every session and 205 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.