do-review

A command that reviews recent code changes before you commit them. It can review uncommitted changes, selected Git commits, or the current branch compared with the main branch.

In plain words
What is it for?
Use it for general code review, selected commit ranges, branch changes, and optional security checks.
Why use it?
It helps find problems in a change set before those changes are saved in Git history.

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/b33eep/claude-code-setup/do-review
Clone the repo
git clone --depth 1 https://github.com/b33eep/claude-code-setup
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 2,267 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 $0.02267
Opus 5 $0.00000 $0.01133
Sonnet 5 $0.00000 $0.00453
Haiku 4.5 $0.00000 $0.00227

Measured 2d ago against content hash e6a59c1e11df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do-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 2d 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.

commands/do-review.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Do Review: Code Review via comprehensive-review

Trigger a code review on your recent changes using the comprehensive-review plugin. This is Step 3 in the Development Flow — review before committing.

Usage

/do-review                    # Review all uncommitted changes
/do-review HEAD~3..HEAD       # Review a specific commit range
/do-review --branch           # Review current branch vs main
/do-review --security         # Include security audit
/do-review --full             # Run all 3 review agents (alias for --security)

Tasks

1. Validate arguments and determine review scope

Parse arguments into scope and agent flags:

  • Scope args (mutually exclusive): commit range (e.g. HEAD~3..HEAD), --branch, or no args
  • Agent flags (optional, combinable with any scope): --security, --full

Unrecognized argument (not a scope arg or agent flag):

Usage: /do-review [HEAD~N..HEAD | --branch] [--security | --full]

Stop here. Do not proceed.

Based on scope:

Invocation Scope Git command
/do-review (no scope args) All uncommitted changes git diff HEAD
/do-review HEAD~3..HEAD Specific commit range git diff HEAD~3..HEAD
/do-review --branch Current branch vs main git diff main...HEAD

Run the appropriate git diff command.

If no changes found:

Nothing to review. No changes detected.

Stop here. Do not proceed.

If large changeset (20+ files or 500+ lines):

Large changeset: [N] files, ~[M] lines changed.
Review may be less thorough. Continue as-is, or narrow the scope?
[Continue] / [Specify files or range]

If user narrows scope, re-run with the adjusted scope.

2. Prepare review context

Gather context for the review agents:

  1. Get the diff — output of the git diff command from step 1
  2. List changed files — extract file paths from the diff
  3. Load coding standards — for each changed file, check if a matching coding standards skill exists:
    • Identify file extensions in the changeset
    • Read matching skills from ~/.claude/skills/ (follow the Skill Loading table in global CLAUDE.md)
    • Collect relevant standards content
  4. Read project context — tech stack and current task from project CLAUDE.md (About section, Tech Stack, Current Status)

Read the full file on GitHub · 324 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. 2d ago First seen · 324 lines · 0 tokens per session scan A e6a59c1e11df

Subscribe to this mod's changes

do-review is a command published in the GitHub repository b33eep/claude-code-setup (56 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,267 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 2026-08-30.