review-changes

review-changes is a skill for Claude Code, Codex from sleeyax/promptfiles. It costs 72 tokens per session (3,079 once invoked), scanned A, original, MIT.

A read-only code review of the commits on a branch, carried out by two independent reviewers whose findings are combined into one report.

In plain words
What is it for?
Reviewing a branch before opening a merge request or asking for a self-review before pushing. It is not intended for checking one file or reviewing every edit automatically.
Why use it?
It helps catch different kinds of problems before changes are pushed, without changing the code itself. You decide what to do about the findings.

Skill for Claude CodeCodex

Part of the sleeyax-skills plugin — 17 skills, 2 agents shipped together

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/sleeyax/promptfiles/review-changes
Any agent
npx skills add sleeyax/promptfiles --skill review-changes
Clone the repo
git clone --depth 1 https://github.com/sleeyax/promptfiles

Made for: Claude Code, Codex.

Or install sleeyax-skills, the plugin that ships this one along with the rest of its 17 skills, 2 agents.

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-changes

README.md
[![agentmods](https://agentmods.dev/badge/skills/sleeyax/promptfiles/review-changes.svg)](https://agentmods.dev/skills/sleeyax/promptfiles/review-changes)
Your own site
<a href="https://agentmods.dev/skills/sleeyax/promptfiles/review-changes"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/review-changes.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,079 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 5.1 $0.00072 $0.03079
Opus 5 $0.00036 $0.01540
Sonnet 5 $0.00014 $0.00616
Haiku 4.5 $0.00007 $0.00308

Measured 5d ago against content hash 43b56a286f62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

review-changes 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.

skills/review/review-changes/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Changes

Scope: $ARGUMENTS

Review a set of changes — the current branch's commits unless told otherwise — with a user-chosen reviewer and report what they found. The skill is read-only end to end: it never edits, stages, or commits anything. Acting on the findings is the user's call.

By default the review runs two reviewers simultaneously — Codex and Claude Code — because different models catch different things. Their reports are merged into one deduplicated verdict.

The skill runs in whichever harness the user invoked it from (Claude Code, Codex, …) and offers the reviewers that harness can actually drive. Every reviewer is read-only — either an in-process subagent or a CLI subprocess.

It's also the reviewing engine other skills call instead of rolling their own — see Called by another skill.

Hard rules

  • Nothing here writes. Never edit, stage, commit, or push — not even a finding that looks trivially safe to fix. Report it and stop.
  • Reviewers run independently. Never feed one reviewer's findings to the other, and never let one wait on the other — the value is in two uncorrelated opinions.
  • The reviewer-choice gate is a real stop: ask, then wait for the answer. Use the AskUserQuestion tool when it's available in the session; where it isn't (e.g. Codex), ask in plain text with the same numbered options and stop until the user replies. Never assume an answer.
  • Don't dump the full diff into a prompt or hand it to the reviewer as one blob. Give the reviewer the base ref and let it run git diff / read files itself.
  • Never spawn a reviewer that can edit: an in-process subagent gets read-only tools, and a reviewer CLI is launched with its write tools denied. A reviewer that can't be constrained is not an option — pick another one.

Called by another skill

Another skill can call this one to do its reviewing — review-mr does, to review a merge request's diff. Hand the merged findings back to the caller as a value instead of printing a summary for the user, and let it decide what to do with them.

Read the full file on GitHub · 162 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. 5d ago First seen · 162 lines · 72 tokens per session scan A 43b56a286f62

Subscribe to this mod's changes

review-changes is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 6d ago), licensed MIT. It adds 72 tokens to every session and 3,079 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens