code-review

code-review is a command for coding agents from dykyi-roman/awesome-claude-code. It costs 38 tokens per session (1,732 once invoked), scanned A, original, MIT.

A code-review command that compares a Git branch with the main branch and reports issues at a chosen level of detail. It can also check whether the changes match a task description.

In plain words
What is it for?
Use it to review a whole branch or a selected file or folder, with low, medium, or high review depth, and receive a structured report with severity levels and a final verdict.
Why use it?
It helps you inspect branch changes systematically before merging, so missed problems or work that does not meet the task are easier to spot.

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/dykyi-roman/awesome-claude-code/code-review
Clone the repo
git clone --depth 1 https://github.com/dykyi-roman/awesome-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 code-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/code-review.svg)](https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/code-review)
Your own site
<a href="https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/code-review"><img src="https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00038 $0.01732
Opus 5 $0.00019 $0.00866
Sonnet 5 $0.00008 $0.00346
Haiku 4.5 $0.00004 $0.00173

Measured today against content hash 9883c33f53d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 today.

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.

commands/code-review.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Command

Perform comprehensive code review on branch changes with configurable depth levels.

Input Parsing

Parse $ARGUMENTS to extract branch, path, level, and optional task description:

Format: [branchpath] [level] [-- task-description]

Arguments:
- branch: Branch to review (auto-detected vs path)
- path: File or folder to filter (auto-detected vs branch)
- level: Review depth - high|medium|low (optional, default: high)
- -- task-description: Task description for matching analysis (optional)
- Target: Always main/master (auto-detected)

Examples:
- /acc:code-review                                   # current branch, whole project, high
- /acc:code-review feature/payment                   # branch, whole project
- /acc:code-review src/Domain                        # current branch, only src/Domain
- /acc:code-review feature/payment src/Domain        # branch + path
- /acc:code-review src/Domain medium                 # current branch, path, medium
- /acc:code-review feature/auth src/Auth -- JWT      # full format
- /acc:code-review medium                            # current branch, medium
- /acc:code-review feature/payment low -- task       # branch, low + task matching

Parsing rules:

  1. Split $ARGUMENTS by -- (space-dash-dash-space)
  2. First part = arguments, Second part = task description
  3. In arguments, search for high|medium|low → this is level (default: high)
  4. For each remaining argument:
    • If exists as file/folder (test -e) → this is path
    • Otherwise → this is branch
  5. Default branch: current via git branch --show-current
  6. Default path: . (whole project)
  7. Target → auto-detect main/master via git symbolic-ref refs/remotes/origin/HEAD

Pre-flight Checks

  1. Verify git repository:

    git rev-parse --git-dir
    

    If not a git repo, report error and stop.

  2. Determine review mode:

    Check each non-level argument:

    # If argument is a file or folder
    test -e "[argument]" && echo "PATH" || echo "BRANCH"
    

Read the full file on GitHub · 236 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. today First seen · 236 lines · 0 tokens per session scan A 9883c33f53d6

Subscribe to this mod's changes

code-review is a command published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 19d ago), licensed MIT. It adds 38 tokens to every session and 1,732 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 2026-09-03.