copy-relevant-paragraph-only

copy-relevant-paragraph-only is a skill for Claude Code from alivirgo/Major-AI-Skills. It costs 22 tokens per session (963 once invoked), scanned A, original, MIT.

A method for giving an AI agent only the paragraphs relevant to a question instead of an entire long document. It is also called context sniping: supplying a small excerpt with brief background.

In plain words
What is it for?
Use it when asking about a contract, manual, article, or other long document and you need to choose the one to three passages that answer the question.
Why use it?
Pasting whole documents uses extra input space and can make important details harder for an AI to focus on. Selecting the relevant passages reduces unrelated information and confusion.

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 Use it when asking about a contract, manual, article, or other long document and you need to choose the one to three passages that answer the question.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alivirgo/major-ai-skills/copy-relevant-paragraph-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 copy-relevant-paragraph-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 copy-relevant-paragraph-only

README.md
[![agentmods](https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/copy-relevant-paragraph-only/github.svg)](https://agentmods.dev/skills/alivirgo/major-ai-skills/copy-relevant-paragraph-only)
Your own site
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/copy-relevant-paragraph-only"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/copy-relevant-paragraph-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 copy-relevant-paragraph-only

Your own site · 80×15
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/copy-relevant-paragraph-only"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/copy-relevant-paragraph-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 963 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 $0.00963
Opus 5 $0.00011 $0.00481
Sonnet 5 $0.00004 $0.00193
Haiku 4.5 $0.00002 $0.00096

Measured yesterday against content hash 8328e3e7755c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

copy-relevant-paragraph-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/copy-relevant-paragraph-only/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copy Relevant Paragraph Only (Context Sniping) (AI Skill)

Overview

When users have a question about a contract, manual, or article, the common reflex is to paste the entire 20-page document.

However, LLMs suffer from the "Lost in the Middle" effect - attention is sharpest at the very beginning and very end of a prompt, but degrades significantly in the middle of giant context dumps. Pasting entire documents also wastes thousands of input tokens and slows down generation speed.

Context Sniping is the practice of copying only the specific 1 to 3 relevant paragraphs along with a single line of background framing.


Document Dumping vs. Context Sniping

┌─────────────────────────────────────────────────────────────┐
│                 Document Dump vs. Context Snipe             │
│                                                             │
│  Document Dump (Pasting 15,000 words):                      │
│  • High input token cost                                    │
│  • Model suffers from "Lost in the Middle" attention loss   │
│  • Higher risk of confusing unrelated clauses               │
│                                                             │
│  Context Snipe (Pasting 250 words):                         │
│  • 98% token savings                                        │
│  • 100% focused attention on the exact target sentence      │
│  • Instant, laser-accurate response                         │
└─────────────────────────────────────────────────────────────┘

Master Context Sniping Prompt Templates

Pattern 1: The Sniped Clause Audit (Legal / Policy)

Context: I am reviewing our SaaS vendor agreement regarding data deletion upon termination.

Here is the exact paragraph from Section 11.2:
"[PASTE ONLY THE 1-2 TARGET PARAGRAPHS]"

Question:
Does the vendor automatically delete our data within 30 days of contract termination, or do we have to submit a written request? Explain based strictly on the text above.

Read the full file on GitHub · 101 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 · -18 tokens per session 8328e3e7755c
  2. 7d ago First seen · 101 lines · 40 tokens per session scan A ed60f341f475

Subscribe to this mod's changes

copy-relevant-paragraph-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 963 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

ai-engineering-toolkit

AI Engineering Toolkit workflow skill. Use this skill when the user needs 6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching and the operator…

diegosouzapw/awesome-omni-skills · 81 tokens

agent-memory-mcp-v2

Agent Memory Skill workflow skill. Use this skill when the user needs A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions) and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing…

diegosouzapw/awesome-omni-skills · 62 tokens

akf-trust-metadata-v2

AKF — The AI Native File Format workflow skill. Use this skill when the user needs The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing and the operator should preserve…

diegosouzapw/awesome-omni-skills · 100 tokens

azure-document-intelligence

Expert knowledge for Azure AI Document Intelligence development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when designing custom models, calling AnalyzeDocument APIs, running containers/offline, or migrating…

MicrosoftDocs/Agent-Skills · 117 tokens

azure-content-understanding

Expert knowledge for Azure Content Understanding in Foundry Tools development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when designing Content Understanding analyzers, RAG document flows…

MicrosoftDocs/Agent-Skills · 131 tokens

kb-import

Import knowledge from existing documents into structured KB entries. Reads source documents (Markdown, PDF, DOCX, plain text), extracts key information, and creates properly formatted KB entries with YAML frontmatter.

techwolf-ai/ai-first-toolkit · 42 tokens