review

review is a command for Claude Code from whchoi98/project-init. It costs 10 tokens per session (393 once invoked), scanned A, original, MIT.

A code-review command for the current Git changes, where Git is a system for tracking code history. It checks project rules, bugs, code quality, and test coverage, then reports only issues with a high confidence score.

In plain words
What is it for?
Reviewing unstaged or staged changes, checking the latest commit and branch when there is no diff, and reporting actionable findings with file paths and line numbers.
Why use it?
It focuses review time on likely problems and explains where each problem occurs and how to fix it.

Command for Claude Code

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/whchoi98/project-init/review
Clone the repo
git clone --depth 1 https://github.com/whchoi98/project-init

Made for: 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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/whchoi98/project-init/review.svg)](https://agentmods.dev/commands/whchoi98/project-init/review)
Your own site
<a href="https://agentmods.dev/commands/whchoi98/project-init/review"><img src="https://agentmods.dev/badge/commands/whchoi98/project-init/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 393 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 $0.00393
Opus 5 $0.00005 $0.00197
Sonnet 5 $0.00002 $0.00079
Haiku 4.5 $0.00001 $0.00039

Measured 3d ago against content hash afeea38cc2dc, 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 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.

.claude/commands/review.md · 52 lines

What it actually says

Code Review

Review the current code changes using confidence-based scoring.

Step 1: Get Changes

Determine the scope of review:

  • If $ARGUMENTS specifies files, review those files
  • Otherwise, review unstaged changes: git diff
  • If no unstaged changes, review staged changes: git diff --cached

Step 2: Review

For each changed file, apply the code-review skill criteria:

  • Project guidelines compliance (from CLAUDE.md)
  • Bug detection (logic errors, security, performance)
  • Code quality (duplication, complexity, test coverage)

Step 3: Score and Filter

Rate each issue 0-100. Only report issues with confidence >= 75.

Step 4: Output

Present findings in structured format with file paths, line numbers, and fix suggestions. If no high-confidence issues, confirm code meets standards.

Error Recovery

If no changes found (Step 1)

No diff output means nothing to review. Inform the user:

  • Check if changes are committed: git log -1 --oneline
  • Check if on the right branch: git branch --show-current
  • Suggest specifying files directly: /review path/to/file.md

If CLAUDE.md is missing or empty (Step 2)

Cannot evaluate project guidelines without CLAUDE.md. Suggest:

  • Run /init-project to generate CLAUDE.md
  • Or create a minimal CLAUDE.md with conventions section

If diff is too large (>500 lines)

Focus on high-risk files first:

  1. Files with security-sensitive changes (hooks, scripts)
  2. Files with logic changes (commands, skills)
  3. Files with documentation changes (lower priority)
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. 3d ago First seen · 52 lines · 10 tokens per session scan A afeea38cc2dc

Subscribe to this mod's changes

review is a command published in the GitHub repository whchoi98/project-init (2 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 393 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.