diff-review

diff-review is a command for coding agents from alberduris/skills. It costs 19 tokens per session (396 once invoked), scanned A, original, MIT.

A command that turns a Git code change review into a broadsheet newspaper-style HTML report.

In plain words
What is it for?
Use it to review uncommitted changes, branches, commits, pull requests, or commit ranges, including changed files, public APIs, tests, documentation, and summary metrics.
Why use it?
It gathers the full change scope and context before explaining why the changes exist, making review findings easier to read.

Command

Part of the newspaper-explainer plugin — 1 skill, 8 commands 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 commands/alberduris/skills/diff-review
Clone the repo
git clone --depth 1 https://github.com/alberduris/skills

Or install newspaper-explainer, the plugin that ships this one along with the rest of its 1 skill, 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 diff-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/alberduris/skills/diff-review.svg)](https://agentmods.dev/commands/alberduris/skills/diff-review)
Your own site
<a href="https://agentmods.dev/commands/alberduris/skills/diff-review"><img src="https://agentmods.dev/badge/commands/alberduris/skills/diff-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 396 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 $0.00019 $0.00396
Opus 5 $0.00010 $0.00198
Sonnet 5 $0.00004 $0.00079
Haiku 4.5 $0.00002 $0.00040

Measured 4d ago against content hash f8cc2a096e6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

plugins/newspaper-explainer/skills/newspaper-explainer/commands/diff-review.md · 15 lines

What it actually says

Load the newspaper-explainer skill. Read ./templates/broadsheet.html and ./references/css-patterns.md to absorb the canonical structure, CSS class vocabulary, and palette. Then generate a broadsheet newspaper edition reviewing a diff.

Determine what to diff from $1: a) branch name means working tree vs that branch, b) commit hash means that specific commit via git show, c) HEAD means uncommitted changes only, d) PR number (e.g. #42) means gh pr diff, e) range (e.g. abc..def) means diff between two commits, f) no argument defaults to main. Gather ALL facts before writing HTML: run git diff --stat and --name-status for scope, read every changed file in full, identify new public API surface, check whether CHANGELOG and docs need updates, reconstruct decision rationale from commit messages or conversation history.

The LEAD STORY covers the core insight — WHY these changes exist, what problem they solve, not just what changed. The floating INSET BOX carries KPI metrics (lines added/removed, files changed, new modules). SECONDARY STORIES cover individual areas of change (UI, API, data layer, tests, config) as separate articles. The SIDEBAR reports housekeeping status (changelog updated, docs current, test coverage). LETTERS AND CORRESPONDENCE reconstructs the design decisions as dialogue — what was decided, why, what alternatives were considered. The DISPATCH BOARD surfaces action items: missing tests, documentation gaps, follow-up work needed. Code review findings (good patterns, bugs, tech debt) run as editorial analysis within the relevant articles.

NEVER EVER fabricate facts — every claim must be traceable to actual git output or file contents. Write to ~/.agent/newspapers/ and open in the browser.

Ultrathink.

$@

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. 4d ago First seen · 15 lines · 19 tokens per session scan A f8cc2a096e6c

Subscribe to this mod's changes

diff-review is a command published in the GitHub repository alberduris/skills (18 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 396 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.