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.
npx skills add alivirgo/Major-AI-Skills --skill always-verify-numbers-and-linksgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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.
[](https://agentmods.dev/skills/alivirgo/major-ai-skills/always-verify-numbers-and-links)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/always-verify-numbers-and-links"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/always-verify-numbers-and-links/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.
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/always-verify-numbers-and-links"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/always-verify-numbers-and-links.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.01441 |
| Opus 5 | $0.00015 | $0.00720 |
| Sonnet 5 | $0.00006 | $0.00288 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
always-verify-numbers-and-links 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Always Verify Numbers and Web Links (AI Skill)
Overview
Large Language Models (LLMs) do not compute math or maintain an internal web directory in real time - they predict the most probable sequence of tokens. As a result, AI assistants can invent plausible-looking URLs, 404 links, outdated statistics, and subtly incorrect arithmetic with complete grammatical confidence.
This skill outlines the Grounding & Verification Protocol: a strict set of operating rules to validate figures, test web endpoints, and force AI models to ground their claims in verifiable data.
Why AI Hallucinates Numbers & Links
┌─────────────────────────────────────────────────────────────┐
│ The Hallucination Trap │
│ │
│ User Asks: "What is the URL for the IRS form 1099-MISC?" │
│ │
│ AI Internal Probability: │
│ "https://www.irs.gov/forms-pubs/about-form-1099-misc" (92%)│
│ ↳ Plausible URL structure generated purely from token patterns │
│ ↳ Result in 35% of cases: HTTP 404 (Page Not Found) │
└─────────────────────────────────────────────────────────────┘
- Token Stitching: The model synthesizes domain names, paths, and slugs based on common internet grammar rather than checking live DNS records.
- Arithmetic Estimation: Without a dedicated Python execution environment or calculator plugin, multi-step math (especially compound percentages and multi-digit multiplication) is approximated via semantic probability, frequently leading to calculation drift.
- Temporal Blind Spots: Outdated dates, pricing tiers, and changed support numbers are confidently cited from stale training weights.
The 4-Point Grounding Audit
Before using any AI-generated figure or URL in production, emails, presentations, or contracts, run through this checklist:
[ ] 1. CLICK-TEST: Did you click the URL directly in an incognito window?
[ ] 2. SOURCE-CHECK: Is the stat attributed to a named primary source (e.g. "BLS 2024 Report") rather than a generic claim ("Studies show...")?
[ ] 3. CALC-RUN: Did you re-run the final math formula through a calculator or Python snippet?
[ ] 4. RECENCY-VERIFY: Does the date match the current quarter or fiscal year?
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.
- yesterday Changed · -7 tokens per session 1f67198459c9
- 7d ago First seen · 132 lines · 36 tokens per session scan A d306a6ba2dcf
always-verify-numbers-and-links is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 1,441 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.
Other skills, from other repositories
android-ui-verification-v2
Android UI Verification Skill workflow skill. Use this skill when the user needs Automated end-to-end UI testing and verification on an Android Emulator using ADB and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
android-ui-verification
Android UI Verification Skill workflow skill. Use this skill when the user needs Automated end-to-end UI testing and verification on an Android Emulator using ADB and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
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…
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…
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…
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…