quick-review

quick-review is a command for Claude Code from d-padmanabhan/agent-engineering-handbook. It costs 10 tokens per session (654 once invoked), scanned A, original, MIT.

A command for a fast local review of changed code. It checks the current branch, recent commits, critical code-quality and security issues, and the branch diff.

In plain words
What is it for?
Quickly reviewing branch changes and running critical checks for languages and tools such as Python, JavaScript, Bash, Go, Terraform, and secret detection.
Why use it?
It gives rapid feedback during short development cycles by focusing on serious problems instead of performing a full review.

Command for Claude Code

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

Good fit Quickly reviewing branch changes and running critical checks for languages and tools…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/d-padmanabhan/agent-engineering-handbook/quick-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/d-padmanabhan/agent-engineering-handbook

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 quick-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/d-padmanabhan/agent-engineering-handbook/quick-review.svg)](https://agentmods.dev/commands/d-padmanabhan/agent-engineering-handbook/quick-review)
Your own site
<a href="https://agentmods.dev/commands/d-padmanabhan/agent-engineering-handbook/quick-review"><img src="https://agentmods.dev/badge/commands/d-padmanabhan/agent-engineering-handbook/quick-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 654 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00010 $0.00654
Opus 5 $0.00005 $0.00327
Sonnet 5 $0.00002 $0.00131
Haiku 4.5 $0.00001 $0.00065

Measured 6d ago against content hash 9d8bb7102d96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

quick-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 6d 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/quick-review.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QUICK REVIEW MODE ACTIVATED

You are now in QUICK REVIEW phase - a streamlined review for rapid iteration cycles.

[!NOTE] For comprehensive analysis, use /self-review instead. This command focuses on critical issues only.

Phase 1: Quick Context

  1. Branch Status:

    • Current branch (git branch --show-current)
    • Files changed (git diff main...HEAD --name-only | wc -l)
    • Diff summary (git diff main...HEAD --stat)
  2. Recent Commits:

    • Last 3 commits (git log --oneline -3 main..HEAD)

Phase 2: Critical Checks Only

Run only the most critical checks:

Python:

  • ruff check . (critical errors only)
  • mypy . or ty . (type errors)
  • bandit -r . -ll (high severity security issues)

Bash/Shell:

  • shellcheck (errors only, no warnings)

Go:

  • golangci-lint run --fast (critical issues)
  • govulncheck ./... (vulnerabilities)

JavaScript/TypeScript:

  • eslint . --max-warnings=0 (errors only)

Terraform:

  • terraform validate
  • tflint (errors only)

General:

  • gitleaks detect --source . (secrets)

Phase 3: Critical Issues Only

Analyze git diff main...HEAD for:

Critical Issues (Must Fix)

  • Security: Hardcoded secrets, injection risks, OWASP Top 10 violations
  • Bugs: Logic errors, null pointer risks, data loss scenarios
  • Breaking changes: API modifications without migration path

Skip Recommended/Optional issues for speed.

Phase 4: Quick Report

## Quick Review Summary

**Files Changed:** [count]
**Commits:** [count]

## Critical Issues Found
[File:line] Issue description
- Fix: [Brief suggestion]

## Status
✅ Ready for PR / ⚠️ Critical issues found

Phase 5: Quick Fixes (Optional)

If user requests fixes:

  • Apply formatters only (ruff format, gofmt, terraform fmt)
  • Re-stage formatted files
  • Re-run critical checks

Constraints

⚠️ DO NOT:

  • Modify files outside the current diff
  • Perform unrelated Git operations
  • Commit or push without explicit authorization
  • Run comprehensive analysis (use /self-review for that)

Read the full file on GitHub · 119 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. 6d ago First seen · 119 lines · 10 tokens per session scan A 9d8bb7102d96

Subscribe to this mod's changes

quick-review is a command published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 7d ago), licensed MIT. It adds 10 tokens to every session and 654 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 2026-08-30.