review-before-commit

review-before-commit is a skill for Claude Code from divinevideo/divine-mobile. It costs 52 tokens per session (2,958 once invoked), scanned A, original, MPL-2.0.

A code-review checklist for inspecting all uncommitted changes before they are pushed to a shared Git repository.

In plain words
What is it for?
It is for reviewing changed files and checking them for dead code, stale references, and related issues before a commit or push.
Why use it?
It helps catch unused code, outdated comments, rule violations, and inconsistencies introduced during development.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit It is for reviewing changed files and checking them for dead code, stale references, and related issues before a commit or push.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/divinevideo/divine-mobile/review-before-commit
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.

Any agent
npx skills add divinevideo/divine-mobile --skill review-before-commit
Clone the repo
git clone --depth 1 https://github.com/divinevideo/divine-mobile

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-before-commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/divinevideo/divine-mobile/review-before-commit/github.svg)](https://agentmods.dev/skills/divinevideo/divine-mobile/review-before-commit)
Your own site
<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/review-before-commit"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/review-before-commit/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-before-commit

Your own site · 80×15
<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/review-before-commit"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/review-before-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,958 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00052 $0.02958
Opus 5.5 $0.00021 $0.01183
Sonnet 5.5 $0.00010 $0.00592
Haiku 4.5 $0.00005 $0.00296

Measured 1mo ago against content hash 30f7b0c10a1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-before-commit 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 1mo 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.

.agents/skills/review-before-commit/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Skill

Purpose

Final code review of all uncommitted changes before pushing. Catches issues that are easy to introduce during iterative development: stale comments referencing removed code, dead code, rule violations, and inconsistencies.

How to Review

Step 1: Identify changed files

Run git diff --name-only and git diff --cached --name-only to get the full list of modified files (staged + unstaged). If the user provided a path argument, filter to only files under that path.

Step 2: Read all changed files

Read every changed file in full. For each file, check the items below.

Step 3: Run checks

For each changed file, check for:

Dead Code
  • Unused imports (import not referenced anywhere in the file)
  • Unused private fields, methods, or getters
  • Unreachable code after early returns
  • Commented-out code blocks (should be deleted, not commented)
Stale References
  • Comments or doc strings referencing methods, classes, or variables that no longer exist in the codebase (use Grep to verify references are still valid)
  • ABOUTME comments that no longer accurately describe the file
  • TODO comments for work that was already completed in this session
Brainstorm Docs

Any file under mobile/docs/brainstorm/ (typically dated like YYYY-MM-DD-issueNNNN-…-brainstorm.md) is a working artefact, not a deliverable. By the time the PR is ready, the rationale belongs in the PR description; the file should not ship with the merge commit.

Flag every staged file under that path and ask the user whether the brainstorm should be dropped or converted in place:

  • Drop it (default) — git rm the file. Use a separate docs: drop … brainstorm doc commit so the deletion is auditable.
  • Convert it to a decision record — only when the doc has lasting value beyond the PR (e.g. captures a rejected approach future readers will keep proposing). Rename, move out of brainstorm/, and trim to the durable bits. Precedent: cd723075e docs(notifications): convert badge-desync brainstorm to decision record.

Read the full file on GitHub · 303 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. 1mo ago First seen · 303 lines · 52 tokens per session scan A 30f7b0c10a1d

Subscribe to this mod's changes

review-before-commit is a skill published in the GitHub repository divinevideo/divine-mobile (264 stars, last pushed today), licensed MPL-2.0. It adds 52 tokens to every session and 2,958 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.