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.
npx agentmods add commands/mirinodev/maestro/reviewgit clone --depth 1 https://github.com/mirinodev/maestroWrote 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.
[](https://agentmods.dev/commands/mirinodev/maestro/review)<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>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.
| Model | Per session | Once 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 |
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.
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!"
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.
- 3d ago First seen · 279 lines · 0 tokens per session scan A 12752eff91c6
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.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
version
Display current guide and Claude Code versions.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
init-docs
Fetch official Anthropic Claude Code docs and store as local baseline snapshot.