review

review is a command for Claude Code from shalomeir/advisor-opus. It costs 66 tokens per session (1,064 once invoked), scanned A, original, MIT.

A command that sends code changes or architecture decisions to a separate advisor for review. It is meant to complement tests, which check whether code works, by checking for missed issues.

In plain words
What is it for?
Use it to review implementation changes, architecture, test results, and possible oversights; trivial changes can be skipped.
Why use it?
It provides an additional review of non-trivial work before committing, using the task context, diff, and recent command output.

Command for Claude Code

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

Part of the advisor-opus plugin — 3 commands, 1 agent shipped together

Good fit Use it to review implementation changes, architecture, test results, and possible oversights; trivial changes can be skipped.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/shalomeir/advisor-opus/review
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.

Clone the repo
git clone --depth 1 https://github.com/shalomeir/advisor-opus

Made for: Claude Code.

Or install advisor-opus, the plugin that ships this one along with the rest of its 3 commands, 1 agent.

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/shalomeir/advisor-opus/review.svg)](https://agentmods.dev/commands/shalomeir/advisor-opus/review)
Your own site
<a href="https://agentmods.dev/commands/shalomeir/advisor-opus/review"><img src="https://agentmods.dev/badge/commands/shalomeir/advisor-opus/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,064 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.
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 $0.00066 $0.01064
Opus 5 $0.00033 $0.00532
Sonnet 5 $0.00013 $0.00213
Haiku 4.5 $0.00007 $0.00106

Measured 8d ago against content hash 4c0e27f86ae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

plugins/advisor-opus/commands/review.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Route this request to the advisor-opus:opus-advisor subagent with a review-specific framing.

IMPORTANT: The advisor agent starts fresh with NO conversation history. You (the executor) must build the context.

Raw user request: $ARGUMENTS

Context Gathering (executor does this BEFORE spawning the advisor)

The advisor starts with zero context — it cannot see your conversation at all. You must pass it everything it needs.

1. Conversation context (three steps, follow in order)

Step 1 — Task summary (1-2 sentences): Write what the goal was. Example: "User asked to add rate limiting to the API endpoints."

Step 2 — What was done (bullet list, keep short): List approach taken, key decisions, files created/modified and why. Compress into short bullets.

Step 3 — Recent raw output (copy-paste, do NOT summarize): Copy the last 3-5 tool results exactly as they appeared — especially test outputs, error messages, and the final state. The advisor needs the actual text to review accurately. If a tool returned 50 lines, include all 50 lines.

2. Git diff context

  1. Run git status to see untracked/staged files
  2. Run git diff --stat to get the list of changed files and line counts
  3. Run git diff to get the full diff (if very large, use git diff --stat summary only and list the top changed files)
  4. If there are staged changes, also run git diff --cached

If the working tree is clean and there are no staged changes:

  • If $ARGUMENTS is provided, skip the diff requirement and proceed with the review using the arguments as the review target (the user may want to review specific files, architecture, or an already-committed change).
  • If $ARGUMENTS is empty, try the last commit as fallback: run git diff HEAD~1 --stat and git diff HEAD~1. If that produces output, use it as the diff context and note to the advisor: "These are the changes from the most recent commit (already committed)."
  • Only if both $ARGUMENTS is empty AND git diff HEAD~1 produces no useful output, tell the user: "No changes found to review. Try specifying a target: /advisor-opus:review <file, topic, or commit range>"

Read the full file on GitHub · 84 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. 8d ago First seen · 84 lines · 66 tokens per session scan A 4c0e27f86ae7

Subscribe to this mod's changes

review is a command published in the GitHub repository shalomeir/advisor-opus (10 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 1,064 once invoked, about $0.0003 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.