diff-review

diff-review is a skill for Claude Code from Rezenders/scientific_writing_agent. It costs 67 tokens per session (918 once invoked), scanned A, original, Apache-2.0.

A focused review of changes made to manuscript files. It examines a Git diff—the record of added and removed lines—instead of reviewing the entire section.

In plain words
What is it for?
Use it after targeted edits, reviewer-driven revisions, or a writing session, with current, staged, specified, or manually supplied changes.
Why use it?
It provides quicker feedback on whether a specific edit introduced inconsistencies, unsupported claims, or broken surrounding prose.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/rezenders/scientific_writing_agent/diff-review
Any agent
npx skills add Rezenders/scientific_writing_agent --skill diff-review
Clone the repo
git clone --depth 1 https://github.com/Rezenders/scientific_writing_agent

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 diff-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/diff-review.svg)](https://agentmods.dev/skills/rezenders/scientific_writing_agent/diff-review)
Your own site
<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/diff-review"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/diff-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 918 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 $0.00067 $0.00918
Opus 5 $0.00034 $0.00459
Sonnet 5 $0.00013 $0.00184
Haiku 4.5 $0.00007 $0.00092

Measured 5d ago against content hash cfba40ffaea2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

diff-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 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.

.claude/skills/diff-review/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diff Review

Targeted review of manuscript changes. Scopes the review to what actually changed rather than auditing the entire section. Faster and more precise than /section-review for incremental edits.

When to Use

  • After editing one or more passages in response to a reviewer comment
  • After a writing session, before committing to git
  • When you want fast feedback on a specific change without a full section audit

Not For

  • First-draft review of a newly written section → use /section-review
  • Pre-submission audit of the full manuscript → use /full-manuscript-audit
  • When the diff spans most of a section → use /section-review instead

Inputs Required

Provide one of:

  1. Auto (default): nothing — Claude runs git diff and parses it
  2. Staged only: say "staged" — Claude runs git diff --cached
  3. Specific range: a commit ref or range (e.g. HEAD~1, abc123..HEAD)
  4. Manual: paste the diff directly if not in a git repo

Workflow

Phase 1 — Get and Parse the Diff

Run git diff (or the specified variant) to obtain the current changes.

For each changed hunk, extract:

  • File name and line range
  • Removed text (what it said before)
  • Added text (what it says now)
  • Surrounding unchanged lines (±5 lines for context)

Skip non-manuscript file changes. Note .bib changes separately but do not run prose review on them.

If the diff is very large (more than 20 hunks), warn the user and suggest running /section-review on the affected section(s) instead.


Phase 2 — Targeted Consistency Audit

For each changed passage, invoke consistency-auditor with:

  • The added text
  • The ±5 lines of surrounding context

Ask: "Does this change introduce any new terminology drift, macro drift, acronym inconsistency, or contradiction with the rest of the manuscript? Report only issues introduced or made worse by this specific change. File:line evidence required. Do not report pre-existing issues in the surrounding unchanged text."

Read the full file on GitHub · 118 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 · 118 lines · 67 tokens per session scan A cfba40ffaea2

Subscribe to this mod's changes

diff-review is a skill published in the GitHub repository Rezenders/scientific_writing_agent (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 918 once invoked, about $0.0003 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.

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