review

review is a command for coding agents from mirinodev/maestro. It costs 0 tokens per session (1,458 once invoked), scanned A, original, MIT.

A command for managing GitHub pull-request reviews from a tool that also works with Git worktrees.

In plain words
What is it for?
Use it to select or open a pull request, create a worktree for it, inspect its diff, open it in a browser, approve it, request changes, assign it, or add comments.
Why use it?
It brings checkout, diff inspection, comments, approval, and change requests into one review workflow.

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/mirinodev/maestro/review
Clone the repo
git clone --depth 1 https://github.com/mirinodev/maestro

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/mirinodev/maestro/review.svg)](https://agentmods.dev/commands/mirinodev/maestro/review)
Your own site
<a href="https://agentmods.dev/commands/mirinodev/maestro/review"><img src="https://agentmods.dev/badge/commands/mirinodev/maestro/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,458 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 $0.00000 $0.01458
Opus 5 $0.00000 $0.00729
Sonnet 5 $0.00000 $0.00292
Haiku 4.5 $0.00000 $0.00146

Measured 3d ago against content hash 12752eff91c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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 3d 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.

docs/commands/review.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔸 review

Command to manage GitHub Pull Request reviews directly from maestro. Provides seamless integration between Git worktrees and GitHub PR review workflows.

Overview

mst review [pr-number] [options]

Usage Examples

Basic Usage

# Interactive PR review selection
mst review

# Review specific PR
mst review 123

# Checkout PR for local review
mst review 123 --checkout

# Show PR diff
mst review 123 --diff

Advanced Usage

# Approve PR with comment
mst review 123 --approve --comment "LGTM! Great work."

# Request changes
mst review 123 --request-changes --comment "Please fix the memory leak"

# Open PR in web browser
mst review 123 --web

# Auto-review flow (checkout, review, comment)
mst review 123 --auto-flow

Options

Option Short Description Default
--checkout Create worktree from PR branch false
--diff Show PR diff false
--web Open PR in web browser false
--approve Approve the PR false
--request-changes Request changes false
--comment <text> Add review comment none
--assign <user> Assign PR to user none
--auto-flow Automated review workflow false

Review Workflow

Interactive Review

# Start interactive review
mst review

Interactive prompts:

? Select a Pull Request to review:
❯ #125 feat: Add dark mode support (enhancement, ui)
  #124 fix: Memory leak in background worker (bug, critical)
  #123 docs: Update API documentation (documentation)

? What would you like to do?
❯ Checkout locally for review
  Show diff
  Open in browser
  Approve
  Request changes

Local Review Process

# 1. Checkout PR for local testing
mst review 123 --checkout

# 2. Test the changes
mst exec pr-123 npm test

# 3. Review code locally
code $(mst where pr-123)

# 4. Submit review
mst review 123 --approve --comment "Tested locally, works great!"

Read the full file on GitHub · 279 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. 3d ago First seen · 279 lines · 0 tokens per session scan A 12752eff91c6

Subscribe to this mod's changes

review is a command published in the GitHub repository mirinodev/maestro (9 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,458 tokens. 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.