review

review is a command for coding agents from rileyhilliard/agentrc. It costs 10 tokens per session (410 once invoked), scanned A, original, MIT.

A command that starts a thorough review of the current code changes. It checks uncommitted work or compares a feature branch with the main branch, then sends the relevant scope to a code-review specialist.

In plain words
What is it for?
Use it before merging code to review a working tree, branch, or specified scope and to identify issues that need fixing.
Why use it?
It removes the guesswork about which changes should be reviewed. Afterward, it reports whether the changes are approved or lists serious issues as a checklist.

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/rileyhilliard/agentrc/review
Clone the repo
git clone --depth 1 https://github.com/rileyhilliard/agentrc

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/rileyhilliard/agentrc/review.svg)](https://agentmods.dev/commands/rileyhilliard/agentrc/review)
Your own site
<a href="https://agentmods.dev/commands/rileyhilliard/agentrc/review"><img src="https://agentmods.dev/badge/commands/rileyhilliard/agentrc/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 410 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 $0.00010 $0.00410
Opus 5 $0.00005 $0.00205
Sonnet 5 $0.00002 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured 4d ago against content hash d919a3c6e084, 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 4d 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.

.agentrc/commands/review.md · 48 lines

What it actually says

Invoke the ce:code-reviewer agent to perform a comprehensive code review.

If $ARGUMENTS is provided:

  • Use the instructions from the user.

If $ARGUMENTS is empty:

Steps:

  1. Check git status to see if there are uncommitted changes
  2. Check current branch name
  3. Determine what to review:
    • If uncommitted changes exist: Review uncommitted changes
    • If no uncommitted changes exist:
      • Check if on a feature branch (not main/master/develop)
      • Suggest reviewing all changes in current branch against main (or upstream branch)
      • Check the changed files via git diff --name-only $([ "$(git rev-parse --abbrev-ref HEAD)" = "main" ] && echo "HEAD^" || echo "main...HEAD")
      • Ask user what should be reviewed
  4. Invoke the ce:code-reviewer agent with appropriate instructions

Post-Review Workflow

After the code-reviewer agent completes:

  1. If APPROVE: Report the review summary. Done.

  2. If REQUEST CHANGES:

    a. Extract all Critical and Important issues into a checklist:

    Review Findings - [branch/scope]:
    - [ ] [CRITICAL] file.ts:123 - Description
    - [ ] [IMPORTANT] file.ts:456 - Description
    

    b. Ask the user how to proceed using AskUserQuestion:

    • "Fix all issues now" (recommended - fix everything the reviewer found)
    • "Show the full review, I'll handle it"

    c. If fixing: work through the checklist, marking items complete as resolved. After all targeted items are fixed, re-run the code-reviewer agent to verify the fixes don't introduce new issues.

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. 4d ago First seen · 48 lines · 10 tokens per session scan A d919a3c6e084

Subscribe to this mod's changes

review is a command published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 410 once invoked, about $0.0001 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.