diffity-review

A code-review tool for examining changes in a Git repository and leaving comments on specific lines or on the whole change.

In plain words
What is it for?
Review working-tree changes or a comparison such as a main branch against a feature branch, focusing on security, performance, naming, errors, types, or logic.
Why use it?
It keeps review feedback attached to the exact code it discusses. It can also track replies, resolutions, and dismissed comments.

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

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,111 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 $0.00015 $0.03111
Opus 5 $0.00008 $0.01555
Sonnet 5 $0.00003 $0.00622
Haiku 4.5 $0.00002 $0.00311

Measured 2d ago against content hash b9973777771e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diffity-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 2d 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.

packages/skills/diffity-review/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diffity Review Skill

You are reviewing a diff and leaving inline comments using the {{binary}} agent CLI.

Arguments

  • ref (optional): Git ref to review (e.g. main..feature, HEAD~3). Defaults to working tree changes. When both ref and focus are provided, use both (e.g. /diffity-review main..feature security).
  • focus (optional): Focus the review on a specific area. One of: security, performance, naming, errors, types, logic. If omitted, review everything.

CLI Reference

{{binary}} agent diff
{{binary}} agent list [--status open|resolved|dismissed] [--json]
{{binary}} agent comment --file <path> --line <n> [--end-line <n>] [--side new|old] --body "<text>"
{{binary}} agent general-comment --body "<text>"
{{binary}} agent resolve <id> [--summary "<text>"]
{{binary}} agent dismiss <id> [--reason "<text>"]
{{binary}} agent reply <id> --body "<text>"
  • --file, --line, --body are required for comment
  • --end-line defaults to --line (single-line comment)
  • --side defaults to new
  • general-comment creates a diff-level comment not tied to any file or line
  • <id> accepts full UUID or 8-char prefix

Prerequisites

  1. Check that {{binary}} is available: run which {{binary}}. If not found, {{install_hint}}.

Instructions

Step 1: Ensure diffity is running for the correct ref (without opening browser)

The review needs a running session whose ref matches the requested ref. A ref mismatch causes "file not in current diff" errors when adding comments.

  1. Run {{binary}} list --json to get all running instances. Parse the JSON output and find the entry whose repoRoot matches the current repo.
  2. If a matching entry exists, compare its ref field against the requested ref:
    • The registry stores "work" for working-tree sessions and the user-provided ref string (e.g. "main", "HEAD~3") for named refs.
    • If refs match → reuse the session, note the port, and continue to Step 2.
    • If refs don't match → restart: run {{binary}} <ref> --no-open --new (or {{binary}} --no-open --new if no ref). The --new flag kills the old session and starts a fresh one. Use Bash tool with run_in_background: true. Wait 2 seconds, then verify with {{binary}} list --json and note the port.
    • If no ref was requested and the running session's ref is not "work" → restart with {{binary}} --no-open --new (the running session is for a named ref, but we need working-tree).
  3. If no session is running for this repo, start one in the background:
    • Command: {{binary}} <ref> --no-open (or {{binary}} --no-open if no ref)
    • Use Bash tool with run_in_background: true
    • Wait 2 seconds, then verify with {{binary}} list --json and note the port.

Read the full file on GitHub · 216 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. 2d ago First seen · 216 lines · 15 tokens per session scan A b9973777771e

Subscribe to this mod's changes

diffity-review is a skill published in the GitHub repository nilbuild/diffity (762 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 3,111 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.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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