uno: Command for Claude Code

.claude/commands/review-panel.md

review-panel is a command for Claude Code from unoplatform/uno. It costs 46 tokens per session (1,835 once invoked), scanned A, original, Apache-2.0.

A command that coordinates eight specialist reviews of a code change or selected scope. The reviewers examine areas such as architecture, security, quality, performance, and contracts.

In plain words
What is it for?
Running a broad review of working-tree changes, a branch, a pull request, or another defined code scope.
Why use it?
It brings several types of code review into one consolidated report. It can determine whether to review uncommitted work, the current branch, or a specified revision range.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

This is unoplatform/uno's own configuration. It tells Claude Code how to work on uno 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 uno configures →

About the project

Uno Platform is an open-source .NET development platform that lets developers build native mobile, web, desktop, and embedded applications from one C# and XAML codebase. It is intended for .NET developers who want to share application code across multiple operating systems and device types. The catalogue entries support development workflows for Uno Platform with skills, agents, commands, and instructions.

unoplatform/uno · 10,038 stars · on GitHub · platform.uno

Reuse

Borrowing it

Nothing to install: this file belongs to unoplatform/uno. 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/unoplatform/uno/master/.claude/commands/review-panel.md
Clone the repo
git clone --depth 1 https://github.com/unoplatform/uno

Made for: Claude Code.

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-panel

README.md
[![agentmods](https://agentmods.dev/badge/commands/unoplatform/uno/review-panel.svg)](https://agentmods.dev/commands/unoplatform/uno/review-panel)
Your own site
<a href="https://agentmods.dev/commands/unoplatform/uno/review-panel"><img src="https://agentmods.dev/badge/commands/unoplatform/uno/review-panel.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,835 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 5.1 $0.00046 $0.01835
Opus 5 $0.00023 $0.00918
Sonnet 5 $0.00009 $0.00367
Haiku 4.5 $0.00005 $0.00184

Measured 6d ago against content hash 8375d35f695c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-panel 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 6d 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.

.claude/commands/review-panel.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are orchestrating an eight-agent review panel on this repo (the Uno Platform framework). Do not do the review yourself — your job is to pin down the scope, dispatch all eight reviewer subagents in parallel, synthesize their findings into one consolidated report, then capture any lesson the panel learns.

1. Resolve scope

Argument from the user: $ARGUMENTS

  • If the argument is non-empty, use it as the scope verbatim. If it looks like a PR reference (#123, PR 123, a github.com PR URL), resolve the diff via gh pr diff / gh pr view. Otherwise treat it as a git revision range (e.g. HEAD~1, master..HEAD) or a free-form description.
  • If the argument is empty, auto-resolve in this order:
    1. Run git status --porcelain. If there are any staged, unstaged, or untracked changes, the scope is "uncommitted changes (working tree + index + untracked)".
    2. Otherwise run git rev-parse --abbrev-ref HEAD. If the current branch is not the trunk (master or main), the scope is "current branch vs trunk". This repo's trunk is master; resolve the base with git merge-base --fork-point master HEAD and capture the output as <base>; the scope range is then the explicit <base>..HEAD. If --fork-point exits with empty stdout (typical after a rebase or across divergent histories), fall back to the literal range master..HEAD. git merge-base returns a single commit SHA, not a range — never pass it alone to git diff / git log (that would include unrelated ancestor history); always compose the two-dot range form before diffing.
    3. Otherwise stop with a one-line message: "Nothing to review — clean working tree on trunk. Pass a scope argument."

2. Gather scope detail

Collect — but do not analyze — the concrete change surface so each reviewer sees the same brief:

  • File list with stat summary (git diff --stat <range> or git status --porcelain + untracked)
  • Commit list if a range is in play (git log --oneline <range>)
  • Full commit messages if a range is in play (git log --format="--- commit %H%n%s%n%n%b" <range>) — pass these verbatim to quality, contract, and jerome so they can evaluate requirement alignment, intentional vs accidental contract changes, and whether the change actually matches its stated intent
  • Branch name and base

Read the full file on GitHub · 72 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. 6d ago First seen · 72 lines · 46 tokens per session scan A 8375d35f695c

Subscribe to this mod's changes

review-panel is a command published in the GitHub repository unoplatform/uno (10,038 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 1,835 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.