web-diff-review

A tool for opening code changes in Difit, a web-based interface for reviewing differences between versions of files. It can show a diff for human review or add review findings as comments.

In plain words
What is it for?
Use it after code changes, for comparing commits or branches, or for reviewing a pull request with comments and explanations attached to the changed lines.
Why use it?
It gives developers a readable place to inspect changes and discuss specific lines instead of reviewing raw version-control output alone.

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/longbkit/clisbot/web-diff-review
Any agent
npx skills add longbkit/clisbot --skill web-diff-review
Clone the repo
git clone --depth 1 https://github.com/longbkit/clisbot

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,431 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 $0.00066 $0.01431
Opus 5 $0.00033 $0.00715
Sonnet 5 $0.00013 $0.00286
Haiku 4.5 $0.00007 $0.00143

Measured 2d ago against content hash cd0b40019198, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-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 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.

skills/web-diff-review/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Diff Review

Use this skill when a diff should be reviewed in difit.

This single skill covers both common difit workflows:

  • ask the user to review current changes or a specific diff in difit
  • review the diff first, then launch difit with findings or explanations preloaded as inline comments

Pick The difit Command First

Before running commands, choose <difit-command> using this rule:

  • If command -v difit succeeds, use difit.
  • Otherwise, use npx difit.
  • If falling back to npx difit would require network access in a sandboxed environment without network permission, request the required approval first.

Decide Which Review Mode Fits

Choose one of these modes:

  1. user-review mode Use this when the goal is to hand the diff to the user for review after code changes.

  2. preloaded-review mode Use this when the user wants review findings, code explanations, or guided comments already attached inside difit.

Defaulting rules:

  • If the user asks to review, audit, explain, or highlight issues in a diff or PR, default to preloaded-review mode.
  • If the user only wants to open, show, or share the diff as a review surface, default to user-review mode.
  • If there are no concrete findings worth attaching to lines, prefer user-review mode even when the request sounds review-oriented.

Choose The Diff Target

Use the smallest truthful diff target for the request.

Common launch forms:

  • review uncommitted changes: <difit-command> .
  • review the HEAD commit: <difit-command>
  • review staged changes: <difit-command> staged
  • review unstaged changes only: <difit-command> working
  • review a specific commit: <difit-command> <target>
  • compare two commits or branches: <difit-command> <target> [compare-with]
  • review a GitHub PR URL: <difit-command> --pr <url>
  • pass stdin diff input: diff -u file1.txt file2.txt | <difit-command>
  • force stdin mode explicitly when needed: diff -u file1.txt file2.txt | <difit-command> -

Read the full file on GitHub · 138 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 138 lines · 66 tokens per session scan A cd0b40019198

Subscribe to this mod's changes

web-diff-review is a skill published in the GitHub repository longbkit/clisbot (114 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,431 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.