A research and content-fixing skill for finding incorrect facts that AI systems state about a brand. It checks the answers, their cited pages, and the brand's approved facts before drafting corrections.

Use it to investigate wrong claims about a company or product, trace their sources, compare AI platforms, and draft changes to correct them.

It helps distinguish a repeated misunderstanding from a single bad answer and identifies which source material may need updating.

wrongclaim — Skill for Claude Code and Codex by ai-search-guru

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 ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool --skill wrongclaim

Clone the repo

git clone --depth 1 https://github.com/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/wrongclaim/github.svg)](https://agentmods.dev/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/wrongclaim)

Your own site

<a href="https://agentmods.dev/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/wrongclaim"><img src="https://agentmods.dev/badge/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/wrongclaim/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/wrongclaim"><img src="https://agentmods.dev/badge/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/wrongclaim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 624 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.

Model	Per session	Once invoked
Fable 5.1	$0.00017	$0.00624
Opus 5.5	$0.00007	$0.00250
Sonnet 5.5	$0.00003	$0.00125
Haiku 4.5	$0.00002	$0.00062

Measured yesterday against content hash ae1a50f2ae11, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wrongclaim 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/wrongclaim/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix wrong claims about us

Find what AI engines get wrong about the brand, where they got it from, and what to change so the next answers are right.

When to use

"ChatGPT says we don't have an API", "AI keeps calling us a free tool", "Find wrong claims about us."
When the person names the wrong claim, start from it; otherwise look for claims first.

What to read

list_mentions, with a search for the subject when the person names one: the answers naming the brand, and their excerpts.
get_mention for each answer that looks wrong: its full text and the pages it cites.
list_ai_answers for the prompts where the claim shows: whether every engine says it, or one.
get_mentions_perception: what AI associates with the brand, to spot a wrong idea that keeps coming back.
list_citations with the external filter: the third-party pages behind those answers.
get_brand_facts: the brand's approved facts (its plans, trial, founding year and the claims it makes), what a person confirmed is true.

Steps

Find the AI answers with wrong facts about the brand, across the tracked platforms. List each claim once, with the engines and prompts that make it.
Check each claim against the brand's facts: its approved facts from get_brand_facts, the person's own words, the facts they confirm, or the brand's pages read in this chat. You don't decide what is true: when none of these says, ask the person, with the claim quoted.
Draft fixes for the brand's own pages: a short, dated passage that states the right fact plainly. When the person wants it kept, save it as a draft with create_draft; the app asks them first when it should. In an agent's run nobody is there to ask: always save it with its tool, and the app holds it for approval where the agent's mode needs it.
Build the outreach list for third-party pages: each page, what it says, and what to ask its owner to correct.
Sending outreach leaves the workspace: the person does it. Chat sends nothing.

Read the full file on GitHub · 48 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.

yesterday First seen · 48 lines · 17 tokens per session scan A ae1a50f2ae11

Subscribe to this mod's changes

wrongclaim is a skill published in the GitHub repository ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool (449 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 624 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-05.

Marketing and SEO Research ai-search-optimization answer answer-engine-optimization chatgpt claude generative-engine-optimization

wrongclaim next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
wrongclaimai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool	Skill	449	yesterday	MIT	A	17	Claude Code, Codex
geo-platform-optimizerasale-ai/seo-geo-skill	Skill	6	2mo ago	none	A	34	Claude Code
ansvisor-aeo-coach-standaloneansvisor/ansvisor	Skill	232	yesterday	MIT	A	148	Claude Code, Codex
geo-loopmverab/eGEOagents	Skill	217	yesterday	MIT	A	62	Claude Code
content-scoringmverab/eGEOagents	Skill	217	yesterday	MIT	A	34	Claude Code
competitive-analysismverab/eGEOagents	Skill	217	yesterday	MIT	A	29	Claude Code
schema-generatormverab/eGEOagents	Skill	217	yesterday	MIT	A	35	Claude Code