review

review is a command for Claude Code from andrei-isvoran96/claude-skill-lab. It costs 0 tokens per session (568 once invoked), scanned B, original, MIT.

A command that sends the current Git code changes to a separate Claude-based reviewer for an independent review. Git is a tool that records code changes; the command can also include findings from earlier reviews.

In plain words
What is it for?
Reviewing a diff against a chosen integration branch, checking for new bugs or security problems, and keeping review history in .claude/review-history.txt.
Why use it?
It provides a second review of finished changes and reduces repeated warnings by remembering issues already fixed.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Reviewing a diff against a chosen integration branch, checking for new bugs or security problems, and keeping review history in .claude/review-history.txt.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/andrei-isvoran96/claude-skill-lab/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/andrei-isvoran96/claude-skill-lab

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/andrei-isvoran96/claude-skill-lab/review/github.svg)](https://agentmods.dev/commands/andrei-isvoran96/claude-skill-lab/review)
Your own site
<a href="https://agentmods.dev/commands/andrei-isvoran96/claude-skill-lab/review"><img src="https://agentmods.dev/badge/commands/andrei-isvoran96/claude-skill-lab/review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/commands/andrei-isvoran96/claude-skill-lab/review"><img src="https://agentmods.dev/badge/commands/andrei-isvoran96/claude-skill-lab/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 568 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.00568
Opus 5 $0.00000 $0.00284
Sonnet 5 $0.00000 $0.00114
Haiku 4.5 $0.00000 $0.00057

Measured 9d ago against content hash 211a0a00db2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

review scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

REVIEW_HISTORY=$(cat .claude/review-history.txt)
commands/review.md · 57 lines

What it actually says

You have finished writing code. Now invoke a fresh, unbiased code review.

First, check if a previous review history file exists at .claude/review-history.txt. If it does, read its contents — you will include it in the reviewer prompt so previously addressed findings are not re-flagged.

Then run the following command using Bash to spawn an independent Claude reviewer. Dynamically build the prompt as follows:

  1. Start with the base prompt (the system instructions below)
  2. If review history exists, append it as a "PREVIOUSLY FLAGGED AND FIXED" section
  3. Pipe the git diff into the final command
REVIEW_HISTORY=""
if [ -f .claude/review-history.txt ]; then
  REVIEW_HISTORY=$(cat .claude/review-history.txt)
fi

if [ -n "$REVIEW_HISTORY" ]; then
  CONTEXT="

IMPORTANT — PREVIOUSLY FLAGGED AND ALREADY FIXED:
The following issues were flagged in prior reviews and have already been addressed. Do NOT re-flag these. Only report NEW issues not covered below.

${REVIEW_HISTORY}"
else
  CONTEXT=""
fi

(git diff <BASE_BRANCH> -- . ':!*.lock' ':!*.lockb' | head -8000) | claude -p "You are a senior code reviewer. Review the following diff thoroughly and critically. Look for:
- Bugs and logic errors
- Security vulnerabilities
- Performance issues
- Edge cases and error handling gaps
- Code quality and readability concerns

Do NOT assume the author's intent. Only evaluate what the code actually does. Be specific — reference file names and line numbers.

If the code looks good, say so briefly. If there are issues, list them by severity (critical / warning / nitpick).
${CONTEXT}"

After the review output is returned:

  1. Display it to the user in full. Do not summarize or filter the review — show it exactly as received.

  2. Save a summary of the findings to .claude/review-history.txt for future reviews. Write ONLY the issue titles/descriptions (one per line, prefixed with severity). Do NOT include the full review text — keep it concise. Append to the existing file (don't overwrite). Example format:

=== Review 2026-04-09 ===
- [critical] SSRF bypass in thumbnail proxy — scheme not validated
- [warning] Blob URL memory leak in DriveThumbnail on unmount
- [nitpick] params: any violates no-any coding standard
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. 9d ago First seen · 57 lines · 0 tokens per session scan B 211a0a00db2e

Subscribe to this mod's changes

review is a command published in the GitHub repository andrei-isvoran96/claude-skill-lab (1 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 568 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.