agentmods.dev

winback

winback is a skill for Claude Code, Codex from ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool. It costs 19 tokens per session (591 once invoked), scanned A, original, MIT.

A search and AI-visibility skill for finding pages that used to be cited by AI answers but are cited less now. It compares those pages with the pages AI systems cite instead.

In plain words
What is it for?
Use it to find lost citations, check related search and AI-answer data, identify missing topics, and refresh a page draft.
Why use it?
It shows what information or topics competing pages cover that the affected page may not, so the page can be updated based on evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 449repo +57 yesterday A scan 19 tokens original MIT

Good fit Use it to find lost citations, check related search and AI-answer data, identify missing topics, and refresh a page draft.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/winback
View source ↗ ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool demo.getcito.com
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 winback
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.

agentmods badge for winback

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/winback/github.svg)](https://agentmods.dev/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/winback)
Your own site
<a href="https://agentmods.dev/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/winback"><img src="https://agentmods.dev/badge/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/winback/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 winback

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/winback"><img src="https://agentmods.dev/badge/skills/ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/winback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 591 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 $0.00019 $0.00591
Opus 5.5 $0.00008 $0.00236
Sonnet 5.5 $0.00004 $0.00118
Haiku 4.5 $0.00002 $0.00059

Measured yesterday against content hash 2fab415a5acf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

winback 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • winback — 88% identical, 0 lines differ
skills/winback/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Win back lost citations

Find the brand's pages that AI engines stopped citing, see what they cite instead, and refresh the pages to win the citations back.

When to use

  • "Win back the citations we lost this week", "Which pages lost citations on Google AI Overviews?", "Why did our guide stop being cited?"
  • Not for a page that was never cited: the Beat a competitor or Comparison page skill fits better.

What to read

  1. list_citations with the owned filter, for the last 7 days and the 7 before (or the periods the person names): the brand's pages and how their citations changed.
  2. get_gsc_summary when Search Console is connected: whether clicks fell with the citations.
  3. get_prompt_performance for the prompts those pages served, lowest visibility first.
  4. list_ai_answers for one or two of those prompts: which pages AI cites now, and what they answer that the brand's page doesn't.
  5. get_fanouts for the topic: questions the page doesn't cover yet.
  6. get_draft when a draft of the page exists: its passages, and which ones AI still quotes (locked).

Steps

  1. Find the pages that lost citations, the biggest loss first; work on two at most in one run.
  2. Compare each with the pages AI engines cite now for the same prompts: newer facts, a direct answer, a table, an FAQ, a date.
  3. Refresh each page: keep, update, add or cut, each change tied to what the cited pages do. Save it as a new version with create_draft, method optimize, with the live page's address as its source; the app asks the person first when it should.
  4. Sending the drafts to the site's CMS, and publishing them, aren't part of this skill: the person does both in the Content Library (Send to CMS, then Publish), or an agent with the Ready to publish skill does.

Output

  1. A table: Page, Citations before, Citations now, Cited instead, Main change.
  2. For each page: the refreshed passages, and what the person must supply as [placeholders].
  3. When to check again: after the next tracking runs.

Read the full file on GitHub · 46 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 First seen · 46 lines · 19 tokens per session scan A 2fab415a5acf

Subscribe to this mod's changes

winback 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 19 tokens to every session and 591 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.

Analytics and metricsMarketing and SEOai-search-optimizationansweranswer-engine-optimizationchatgptclaudegenerative-engine-optimization
Related

winback compared with skills from other repositories

winback next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
winbackai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-toolSkill449yesterdayMITA19Claude Code, Codex
geo-platform-optimizerasale-ai/seo-geo-skillSkill62mo agononeA34Claude Code
ansvisor-aeo-coach-standaloneansvisor/ansvisorSkill232yesterdayMITA148Claude Code, Codex
geo-loopmverab/eGEOagentsSkill217yesterdayMITA62Claude Code
content-scoringmverab/eGEOagentsSkill217yesterdayMITA34Claude Code
competitive-analysismverab/eGEOagentsSkill217yesterdayMITA29Claude Code
schema-generatormverab/eGEOagentsSkill217yesterdayMITA35Claude Code