pair

A pair-programming command that makes Claude pause after a chosen number of edits so a person can review them. The person can approve, reject with a reason, check status, or end the session.

In plain words
What is it for?
Use it for supervised coding sessions where edits should be checked in small groups.
Why use it?
It keeps a human involved during multi-step changes instead of allowing all edits to proceed without review.

Skill for Claude CodeCodex

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 skills/gowtham012/claude-plugins/pair
Any agent
npx skills add gowtham012/Claude-plugins --skill pair
Clone the repo
git clone --depth 1 https://github.com/gowtham012/Claude-plugins

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 363 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 $0.00020 $0.00363
Opus 5 $0.00010 $0.00181
Sonnet 5 $0.00004 $0.00073
Haiku 4.5 $0.00002 $0.00036

Measured 2d ago against content hash e645acbc5881, 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.

pair-mode/skills/pair/SKILL.md · 38 lines

What it actually says

Argument

$ARGUMENTS


Instructions

If the argument is "end" or "stop", call mcp__pair-mode__end_pair with cwd = current working directory and report the result.

If the argument is "approve", call mcp__pair-mode__approve with cwd = current working directory and report the result.

If the argument starts with "reject", call mcp__pair-mode__reject with cwd = current working directory and reason = the rest of the argument. Report the result.

If the argument is "status", call mcp__pair-mode__get_status with cwd = current working directory and report the result.

Otherwise, parse the argument as a number for max_edits_before_pause (default 3 if empty or not a number).

Call mcp__pair-mode__start_pair with:

  • cwd = current working directory
  • max_edits_before_pause = the parsed number

Report the result. Then tell the user:

Pair session started. Claude will pause after every N edits for your review.

When paused, respond with:

  • "approve" — accept the edits and continue
  • "reject " — request revisions
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 · 38 lines · 20 tokens per session scan A e645acbc5881

Subscribe to this mod's changes

pair is a skill published in the GitHub repository gowtham012/Claude-plugins (5 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 363 once invoked, about $0.0001 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 2026-08-31.