pair-review: Skill for Claude Code

.pi/skills/review-roulette/SKILL.md

review-roulette is a skill for Claude Code, Codex from in-the-loop-labs/pair-review. It costs 30 tokens per session (1,218 once invoked), scanned A, original, Apache-2.0.

A review workflow that sends one review task to three randomly chosen reasoning models at the same time, then combines their suggestions into one result.

In plain words
What is it for?
Use it to orchestrate diverse reviews of a task and merge the returned recommendations.
Why use it?
It gathers several independent opinions, which can expose issues a single review might miss.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is in-the-loop-labs/pair-review's own configuration. It tells Claude Code and Codex how to work on pair-review itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pair-review configures →

Reuse

Borrowing it

Nothing to install: this file belongs to in-the-loop-labs/pair-review. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/in-the-loop-labs/pair-review/main/.pi/skills/review-roulette/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/in-the-loop-labs/pair-review

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-roulette

README.md
[![agentmods](https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-roulette/github.svg)](https://agentmods.dev/skills/in-the-loop-labs/pair-review/review-roulette)
Your own site
<a href="https://agentmods.dev/skills/in-the-loop-labs/pair-review/review-roulette"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-roulette/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-roulette

Your own site · 80×15
<a href="https://agentmods.dev/skills/in-the-loop-labs/pair-review/review-roulette"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-roulette.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00030 $0.01218
Opus 5 $0.00015 $0.00609
Sonnet 5 $0.00006 $0.00244
Haiku 4.5 $0.00003 $0.00122

Measured 12d ago against content hash 5b6ec160d9be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-roulette 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 12d 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.

.pi/skills/review-roulette/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Roulette

When this skill is active, your ONLY job is orchestration — you do NOT perform any review analysis yourself. You randomly select 3 reasoning models, dispatch the review to all of them in parallel, and merge the results.

Step 1: Discover Available Reasoning Models

Run ${PI_CMD:-pi} --list-models via bash to get the current list of models with valid API keys. Eligible models are those that show thinking: yes in the output — these are the reasoning-capable / premium models.

Excluded models: Never select openai/o3-pro — it is prohibitively expensive. If it appears in the model list, skip it entirely.

Example reasoning models you might see (provider/model format):

  • anthropic/claude-opus-4-6
  • anthropic/claude-sonnet-4-5 (with thinking)
  • openai/o3
  • openai/o4-mini
  • openai/gpt-5-pro
  • openai/gpt-5.2-pro
  • google/gemini-2.5-pro (with thinking)
  • google/gemini-2.5-flash (with thinking)
  • google/gemini-3.1-pro-preview
  • xai/grok-4

The exact list depends on which API keys are configured. Always check — do not assume models are available.

Step 2: Randomly Select 3 Models

From the eligible reasoning models, pick exactly 3 at random.

CRITICAL — true randomness and diversity:

  • Do NOT always pick the same 3 models. The entire point of review roulette is variety of perspectives across runs.
  • Prefer different providers when possible. If you have reasoning models from Anthropic, OpenAI, Google, and xAI, pick from 3 different providers. Only double up on a provider if fewer than 3 providers have eligible models.
  • Shuffle or randomize your selection each time. Do not default to alphabetical order or any fixed preference.

Step 3: Dispatch the Review in Parallel

Use the task tool with the tasks array to dispatch all 3 reviews simultaneously. Each task object must include:

  1. model: The selected model in provider/model format.
  2. task: The FULL original review prompt/instructions. Each subtask starts fresh with NO conversation history and NO context from the parent. You must forward EVERYTHING you were asked to do — the complete prompt, all instructions, the diff, file contents, any constraints or formatting requirements, the expected JSON output schema, etc. Do not summarize or abbreviate. Pass it all through verbatim.

Read the full file on GitHub · 145 lines

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. 12d ago First seen · 145 lines · 30 tokens per session scan A 5b6ec160d9be

Subscribe to this mod's changes

review-roulette is a skill published in the GitHub repository in-the-loop-labs/pair-review (59 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 1,218 once invoked, about $0.0002 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.