geo-content-signals

geo-content-signals is an agent for Claude Code from greglas75/zuvo. It costs 34 tokens per session (6,251 once invoked), scanned A, original, MIT.

A read-only reviewer for website content that affects GEO, meaning how well AI search systems can find, understand, and cite it.

In plain words
What is it for?
Use it to review llms.txt, headings, answer-first content, citations, HTML structure, content chunking, and GEO-related anti-patterns.
Why use it?
It identifies unclear structure, weak headings, missing citation signals, and other patterns that can make content harder for automated systems to use. It applies page-type rules and reports findings without editing files.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Part of the zuvo plugin — 56 skills, 47 agents, 5 hooks shipped together

Good fit Use it to review llms.txt, headings, answer-first content, citations, HTML structure, content chunking, and GEO-related anti-patterns.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/greglas75/zuvo/geo-content-signals
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.

Clone the repo
git clone --depth 1 https://github.com/greglas75/zuvo

Made for: Claude Code.

Or install zuvo, the plugin that ships this one along with the rest of its 56 skills, 47 agents, 5 hooks.

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 geo-content-signals

README.md
[![agentmods](https://agentmods.dev/badge/agents/greglas75/zuvo/geo-content-signals.svg)](https://agentmods.dev/agents/greglas75/zuvo/geo-content-signals)
Your own site
<a href="https://agentmods.dev/agents/greglas75/zuvo/geo-content-signals"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/geo-content-signals.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,251 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 $0.00034 $0.06251
Opus 5 $0.00017 $0.03125
Sonnet 5 $0.00007 $0.01250
Haiku 4.5 $0.00003 $0.00625

Measured 7d ago against content hash a145b834c4f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

geo-content-signals 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 7d ago.

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/geo-audit/agents/geo-content-signals.md · 696 lines

How it starts

The opening of the file, as written. The whole thing — 696 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: GEO Content Signals (Group C)

Model: Sonnet | Type: Explore (read-only)

Evaluate GEO content dimensions: G3 (llms.txt & AI Discovery), G6 (Structured HTML & Chunkability), G9 (BLUF & Answer Blocks), G10 (Heading Structure), G11 (Citation Signals), G12 (Anti-patterns).


Mandatory File Loading

Read before any work begins:

  1. ../../../shared/includes/codesift-setup.md -- CodeSift discovery and tool selection
  2. ../../../shared/includes/geo-check-registry.md -- canonical check slugs
  3. ../../../shared/includes/seo-page-profile-registry.md -- profile-aware heuristics and enforcement downgrades

Read ../../../shared/includes/geo-check-registry.md for canonical check slugs. Use ONLY slugs from this registry in findings[].check. Read ../../../shared/includes/seo-page-profile-registry.md for profile-aware thresholds and enforcement downgrades.

Print the checklist:

CORE FILES LOADED:
  1. codesift-setup.md             -- [READ | MISSING -> STOP]
  2. geo-check-registry.md         -- [READ | MISSING -> STOP]
  3. seo-page-profile-registry.md  -- [READ | MISSING -> STOP]

If any file is missing, STOP.


Setup

  • Run CodeSift discovery per codesift-setup.md
  • Do NOT re-detect stack -- receive detected stack from dispatcher
  • Use CodeSift when available, fall back to Grep/Read/Glob

Input (from dispatcher)

  • detected_stack: string (astro | nextjs | hugo | wordpress | react | html)
  • content_format: string (markdown | database | none)
  • content_profile: string (auto | marketing | docs | blog | ecommerce | app-shell)
  • file_paths: string[] (content directory paths, markdown/HTML pages, page list)
  • codesift_repo: string | null (repo identifier if CodeSift available)
  • mode: string (full | quick | content-only | geo)
  • selected_dimensions: string[] (e.g., ["G3", "G6", "G9", "G10", "G11", "G12"])
  • cms_detected: string | null (e.g., "wordpress", "contentful", "sanity", null)
  • lang: string (default: "en", optional: "pl") -- language for anti-pattern detection in G12
  • content_profile_reason: string | null (why the dispatcher chose the active profile when content_profile != auto)

Read the full file on GitHub · 696 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. 7d ago First seen · 696 lines · 34 tokens per session scan A a145b834c4f8

Subscribe to this mod's changes

geo-content-signals is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 6,251 once invoked, about $0.0002 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 2026-08-31.