ask-what-changed-only

ask-what-changed-only is a skill for Claude Code from alivirgo/Major-AI-Skills. It costs 22 tokens per session (1,046 once invoked), scanned A, original, MIT.

A prompting method that asks an AI to return only the changed lines or sentences, rather than rewriting the whole document. A diff is a compact description of what was removed and added.

In plain words
What is it for?
It is for editing source code, articles, or other text when only a small part needs changing, including requests for Git-style diffs.
Why use it?
Full rewrites use extra output and make small changes hard to review. Showing only the change makes the result easier to inspect and apply.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the major-ai-skills plugin — 147 skills, 8 plugins shipped together

Good fit It is for editing source code, articles, or other text when only a small part needs changing, including requests for Git-style diffs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alivirgo/major-ai-skills/ask-what-changed-only
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.

Any agent
npx skills add alivirgo/Major-AI-Skills --skill ask-what-changed-only
Clone the repo
git clone --depth 1 https://github.com/alivirgo/Major-AI-Skills

Made for: Claude Code.

Or install major-ai-skills, the plugin that ships this one along with the rest of its 147 skills, 8 plugins.

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 ask-what-changed-only

README.md
[![agentmods](https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ask-what-changed-only/github.svg)](https://agentmods.dev/skills/alivirgo/major-ai-skills/ask-what-changed-only)
Your own site
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/ask-what-changed-only"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ask-what-changed-only/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ask-what-changed-only

Your own site · 80×15
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/ask-what-changed-only"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ask-what-changed-only.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00022 $0.01046
Opus 5 $0.00011 $0.00523
Sonnet 5 $0.00004 $0.00209
Haiku 4.5 $0.00002 $0.00105

Measured yesterday against content hash 9eda32dd690d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ask-what-changed-only 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 yesterday.

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/ask-what-changed-only/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ask AI for Changes Only (The Delta/Diff Protocol) (AI Skill)

Overview

When asking an AI to tweak a sentence in a 1,500-word article or fix one function in a 400-line script, default model behavior is to regenerate the entire document from start to finish.

This creates two major problems:

  1. Severe Token Waste: Generates thousands of unnecessary output tokens ($$$ and slow generation time).
  2. Review Nightmare: You have to re-read the entire document just to find what tiny phrase or line actually changed.

The Delta / Diff Protocol instructs the model to output only the exact modified chunks, with clear before-and-after references or standard Git-style diffs.


Full Regeneration vs. Delta Output

┌─────────────────────────────────────────────────────────────┐
│                 Full Rewrite vs. Delta Output               │
│                                                             │
│  Full Document Regeneration:                                │
│  • 1,200 tokens generated                                   │
│  • 25 seconds wait time                                     │
│  • User must manually hunt for changes                      │
│                                                             │
│  Delta / Diff Output:                                       │
│  • 85 tokens generated (93% token reduction)                │
│  • 2 seconds generation time                                │
│  • Visual instant clarity on what changed                   │
└─────────────────────────────────────────────────────────────┘

Master Delta Prompt Templates

Pattern 1: The Unified Diff Directive (Code & Configs)

Use this for codebases, YAML, JSON, or configuration files:

Here is my code file: [PASTE CODE].

Task: [DESCRIBE THE REFACTOR / FIX].

Output Rules:
1. Do NOT reprint the entire file.
2. Provide ONLY a standard unified `diff` block showing `-` for removed lines and `+` for added lines.
3. Include 2 lines of unchanged context above and below each modification.

Read the full file on GitHub · 129 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. yesterday Changed · -15 tokens per session 9eda32dd690d
  2. 7d ago First seen · 129 lines · 37 tokens per session scan A de88c08010f6

Subscribe to this mod's changes

ask-what-changed-only is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 1,046 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 2026-09-05.

Related

Other skills, from other repositories

ax-extract-workflow

Reconstruct workflow behind a past coding-agent artifact using local ax sessions/commits/skills/tool traces. Use when asked how X was built.

sickn33/agentic-awesome-skills · 35 tokens

app-store-changelog-v2

App Store Changelog workflow skill. Use this skill when the user needs Generate user-facing App Store release notes from git history since the last tag and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

diegosouzapw/awesome-omni-skills · 56 tokens

azure-repos

Expert knowledge for Azure Repos development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing Git/TFVC repos, branch/PR policies, CLI/IDE integrations, CodeQL/scanning, or…

MicrosoftDocs/Agent-Skills · 115 tokens

bitbucket-automation

Automate Bitbucket repositories, pull requests, branches, issues, and workspace management via Rube MCP (Composio). Always search tools first for current schemas.

rootcastleco/rei-skills · 38 tokens

app-store-changelog

App Store Changelog workflow skill. Use this skill when the user needs Generate user-facing App Store release notes from git history since the last tag and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

diegosouzapw/awesome-omni-skills · 54 tokens

commit-convention

Professional Commit Convention Expert skill. Improve code delivery speed and developer workflows through automation and modern tooling.

AtulPurohit/Antigravity-Awesome-Skills · 23 tokens