bro-review-before-i-screw-up

bro-review-before-i-screw-up is a command for Claude Code from dinnovos/dinnovos-marketplace. It costs 32 tokens per session (2,249 once invoked), scanned A, original, MIT.

A read-only review command that examines pending code changes for bugs, quality problems, security risks and possible improvements before a commit.

In plain words
What is it for?
Use it to audit staged, unstaged or untracked changes across supported programming languages, or to confirm that the working directory is clean.
Why use it?
It gathers the full relevant diff and project guidance so problems can be found before changes are committed.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; mentions AGENTS.md.

Part of the bro-code-tools plugin — 8 commands shipped together

Good fit Use it to audit staged, unstaged or untracked changes across supported programming languages, or to confirm that the working directory is clean.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dinnovos/dinnovos-marketplace/bro-review-before-i-screw-up
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/dinnovos/dinnovos-marketplace

Made for: Claude Code.

Or install bro-code-tools, the plugin that ships this one along with the rest of its 8 commands.

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 bro-review-before-i-screw-up

README.md
[![agentmods](https://agentmods.dev/badge/commands/dinnovos/dinnovos-marketplace/bro-review-before-i-screw-up/github.svg)](https://agentmods.dev/commands/dinnovos/dinnovos-marketplace/bro-review-before-i-screw-up)
Your own site
<a href="https://agentmods.dev/commands/dinnovos/dinnovos-marketplace/bro-review-before-i-screw-up"><img src="https://agentmods.dev/badge/commands/dinnovos/dinnovos-marketplace/bro-review-before-i-screw-up/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 bro-review-before-i-screw-up

Your own site · 80×15
<a href="https://agentmods.dev/commands/dinnovos/dinnovos-marketplace/bro-review-before-i-screw-up"><img src="https://agentmods.dev/badge/commands/dinnovos/dinnovos-marketplace/bro-review-before-i-screw-up.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,249 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00032 $0.02249
Opus 5 $0.00016 $0.01125
Sonnet 5 $0.00006 $0.00450
Haiku 4.5 $0.00003 $0.00225

Measured 12d ago against content hash 41502db89a24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

bro-review-before-i-screw-up scanned grade A 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 12d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| Python | f-strings in queries | `os.system(f"cmd {input}")` | N/A |
plugins/bro-code-tools/commands/bro-review-before-i-screw-up.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Complete Pre-Commit Review

Exhaustively analyze all pending changes before committing. Detect critical issues, evaluate code quality and suggest concrete improvements. Multi-language support.

Step 1: Identify Pending Changes

Run these commands to get the current state:

# Modified files (tracked)
git diff --name-only HEAD

# New files (untracked)
git ls-files --others --exclude-standard

# Staged files
git diff --cached --name-only

If there are no changes

If all commands return empty, stop and respond:

✅ Clean working directory

No pending changes to review. Nothing to audit.

Don't continue if there are no files to review.

Step 2: Get Complete Context

# Full diff of unstaged changes
git diff HEAD

# Diff of staged changes (if any)
git diff --cached

# See project structure for context
ls -la

# Detect stack
cat package.json pyproject.toml go.mod Cargo.toml composer.json Gemfile 2>/dev/null

# Project standards
cat CLAUDE.md AGENTS.md 2>/dev/null

If CLAUDE.md, AGENTS.md, README.md or project configuration files (.eslintrc, tsconfig.json, etc.) exist, read them to understand project standards.

Step 3: Analysis by Categories

Review each modified file looking for problems in these categories, ordered by priority:


P0 - CRITICAL: Bugs and Logic Errors

Problems that will cause production failures:

  • Uninitialized variables or access to null/undefined properties
  • Impossible conditions or inverted logic
  • Off-by-one errors in iterations and boundaries
  • Race conditions in asynchronous code
  • Uncaught exceptions that can crash the application
  • Memory leaks or unreleased resources (connections, listeners, timers)
  • Incorrect types that will pass at runtime but fail
  • Inconsistent states that corrupt data
Examples by language:
Language Problem Example
JS/TS null/undefined without check user.profile.name without optional chaining
Python Mutable default args def f(lst=[])
Go Ignored error result, _ := fn()
Rust unwrap() in production value.unwrap()
PHP Weak comparison $a == "0" vs $a === "0"

Read the full file on GitHub · 308 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. 12d ago First seen · 308 lines · 32 tokens per session scan A 41502db89a24

Subscribe to this mod's changes

bro-review-before-i-screw-up is a command published in the GitHub repository dinnovos/dinnovos-marketplace (2 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 2,249 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.