beware-of-hallucinated-quotes

beware-of-hallucinated-quotes is a skill for Claude Code from alivirgo/Major-AI-Skills. It costs 26 tokens per session (1,190 once invoked), scanned A, original, MIT.

A checking method for quotations, book references, and academic citations produced by AI. It is designed to catch wording, titles, or identifiers that sound believable but were made up.

In plain words
What is it for?
Use it when preparing articles, books, presentations, or research material that includes quotations or citations.
Why use it?
AI can present invented quotations and references as facts. Checking the attribution before publishing helps prevent false claims and embarrassing source errors.

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 preparing articles, books, presentations, or research material that includes quotations or citations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alivirgo/major-ai-skills/beware-of-hallucinated-quotes
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 beware-of-hallucinated-quotes
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 beware-of-hallucinated-quotes

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/beware-of-hallucinated-quotes"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/beware-of-hallucinated-quotes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,190 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 $0.00026 $0.01190
Opus 5 $0.00013 $0.00595
Sonnet 5 $0.00005 $0.00238
Haiku 4.5 $0.00003 $0.00119

Measured yesterday against content hash 74e136fbc3c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

beware-of-hallucinated-quotes 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/beware-of-hallucinated-quotes/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Beware of Hallucinated Quotes & Citations (AI Skill)

Overview

One of the most insidious failure modes of Large Language Models is the generation of plausible but completely fabricated quotations. Models will effortlessly attribute memorable, eloquent aphorisms to historical figures (Albert Einstein, Winston Churchill, Mark Twain, Steve Jobs) or invent non-existent book titles, chapters, and academic paper DOIs.

This skill details the Attribution & Quotation Grounding Protocol: rules and prompts to force verbatim fidelity and prevent embarrassing attribution errors.


Why AI Fakes Quotations

┌─────────────────────────────────────────────────────────────┐
│                 The Quote Hallucination Trap                │
│                                                             │
│  User: "Give me an inspiring quote by Abraham Lincoln        │
│         about digital technology and adaptability."         │
│                                                             │
│  AI Semantic Synthesis:                                     │
│  "The dogmas of the quiet past are inadequate to the stormy │
│   present... we must think anew and act anew."              │
│   ↳ Model stitches Lincoln's 1862 message to Congress with  │
│     synthetic words about 'modern tools' to fit the prompt. │
│   ↳ Result: Confidently fabricated historical quote.        │
└─────────────────────────────────────────────────────────────┘

The Attribution Grounding Protocol

Before including an AI-generated quotation in a speech, presentation, manuscript, or legal filing, apply these 3 rules:

  1. The Exact-Quote Search: Copy the exact quoted sentence in quotation marks ("...") and search Google Books or Google Scholar. If zero exact matches exist, it is a synthetic fabrication.
  2. Demand Chapter & Primary Source: Require the AI to name the exact book title, publication year, chapter, or primary speech context.
  3. Paraphrase If Unverified: If you cannot verify the exact primary text, rephrase as a conceptual principle rather than a direct quote.

Read the full file on GitHub · 113 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 · -8 tokens per session 74e136fbc3c6
  2. 7d ago First seen · 113 lines · 34 tokens per session scan A c24a070c71c7

Subscribe to this mod's changes

beware-of-hallucinated-quotes is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,190 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

azure-pipelines

Expert knowledge for Azure Pipelines development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when securing agents/secrets, configuring YAML builds, migrating from Jenkins…

MicrosoftDocs/Agent-Skills · 116 tokens

azure-local

Expert knowledge for Azure Local development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when planning Azure Local racks/SDN, disconnected clusters, Arc VMs, GPU workloads, or…

MicrosoftDocs/Agent-Skills · 112 tokens

azure-arc

Expert knowledge for Azure Arc development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when managing Arc-enabled Kubernetes, data services, Edge Volumes, Agentic Retrieval APIs…

MicrosoftDocs/Agent-Skills · 114 tokens

azure-blob-storage

Expert knowledge for Azure Blob Storage development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using Blob tiers, lifecycle/immutability, NFS/SFTP mounts, static sites, or SDK/CLI data workflows, and…

MicrosoftDocs/Agent-Skills · 112 tokens

azure-defender-for-cloud

Expert knowledge for Azure Defender For Cloud development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when securing VMs, containers/AKS, SQL, storage, multi‑cloud connectors, or…

MicrosoftDocs/Agent-Skills · 127 tokens

azure-functions

Expert knowledge for Azure Functions development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when wiring Functions to triggers/bindings, Cosmos/SQL/Service Bus, VNet/private…

MicrosoftDocs/Agent-Skills · 122 tokens