review-diff

review-diff is a skill for Claude Code, Codex from decodingai-magazine/building-a-coding-agent-from-scratch-course. It costs 16 tokens per session (207 once invoked), scanned A, original, Apache-2.0.

A guide for reviewing uncommitted changes in a Git working directory, the folder containing the current version of a code project.

In plain words
What is it for?
Use it to inspect both unstaged and staged differences, report specific file-and-line findings, separate blockers from suggestions, and give a merge verdict. It does not edit or commit code.
Why use it?
It helps find bugs, missed edge cases, and unnecessary complexity before the changes are merged.

Skill for Claude CodeCodex

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 skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/review-diff
Any agent
npx skills add decodingai-magazine/building-a-coding-agent-from-scratch-course --skill review-diff
Clone the repo
git clone --depth 1 https://github.com/decodingai-magazine/building-a-coding-agent-from-scratch-course

Made for: Claude Code, Codex.

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-diff

README.md
[![agentmods](https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/review-diff.svg)](https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/review-diff)
Your own site
<a href="https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/review-diff"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/review-diff.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 207 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 $0.00016 $0.00207
Opus 5 $0.00008 $0.00103
Sonnet 5 $0.00003 $0.00041
Haiku 4.5 $0.00002 $0.00021

Measured 5d ago against content hash 2d0236f3e5ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-diff 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 5d 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.

src/decode/skills/builtin/review-diff/SKILL.md · 17 lines

What it actually says

You review the current working-tree changes for defects and unnecessary complexity. You do not edit the code and you do not commit — you report.

  1. Read the change with git diff (and git diff --cached for staged work). Ground every comment in a specific file:line you actually read.
  2. Review against two lenses, in order:
    • Correctness — logic errors, unhandled edge cases, broken invariants, regressions in adjacent code paths, missing error handling.
    • Over-engineering — speculative abstractions, dead code, indirection with a single caller, and changes larger than the problem requires. Prefer the smallest change that works.
  3. Separate blocking problems from optional suggestions, and end with a one-line verdict: ready to merge, or the specific blockers that must be fixed first.
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. 5d ago First seen · 17 lines · 16 tokens per session scan A 2d0236f3e5ac

Subscribe to this mod's changes

review-diff is a skill published in the GitHub repository decodingai-magazine/building-a-coding-agent-from-scratch-course (352 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 207 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.