What is voyage-geo-agent CLAUDE.md?

A development guide for Voyage GEO, an open-source tool that measures how AI services such as ChatGPT, Claude, Gemini, and Perplexity mention and recommend brands. GEO means improving visibility in AI-generated answers, similar to SEO for search engines.

Use it to run a full brand-visibility analysis or a category leaderboard, and to understand the Python pipeline and provider structure when developing the tool.

It explains the project's purpose, its five-stage analysis process, and the commands an agent can use to run brand research or compare brands in a category.

How onvoyage-ai/voyage-geo-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to onvoyage-ai/voyage-geo-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/onvoyage-ai/voyage-geo-agent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/onvoyage-ai/voyage-geo-agent

Made for: Claude Code.

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/instructions/onvoyage-ai/voyage-geo-agent/claude-md/github.svg)](https://agentmods.dev/instructions/onvoyage-ai/voyage-geo-agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/onvoyage-ai/voyage-geo-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/onvoyage-ai/voyage-geo-agent/claude-md/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/instructions/onvoyage-ai/voyage-geo-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/onvoyage-ai/voyage-geo-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,806 This file is loaded in full into every session.

When invoked 1,806 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.01806	$0.01806
Opus 5	$0.00903	$0.00903
Sonnet 5	$0.00361	$0.00361
Haiku 4.5	$0.00181	$0.00181

Measured 11d ago against content hash fa6309c1e6ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

voyage-geo-agent CLAUDE.md scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

bash <(curl -fsSL https://raw.githubusercontent.com/onvoyage-ai/voyage-geo-agent/main/install-skills.sh)

CLAUDE.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voyage GEO — Development Guide

What This Is

Voyage GEO is an open source GEO (Generative Engine Optimization) tool, designed to be used through Claude Code. It analyzes how AI models (ChatGPT, Claude, Gemini, Perplexity) reference and recommend brands. Think of it as SEO analytics, but for AI search engines.

How to Use (AI Agent Skills)

Skills work with Claude Code, OpenClaw, and any agent supporting SKILL.md. Install with:

bash <(curl -fsSL https://raw.githubusercontent.com/onvoyage-ai/voyage-geo-agent/main/install-skills.sh)

Two slash commands:

/geo-run — Full GEO analysis. Handles setup, brand research, query generation, execution, analysis, and reporting.
/geo-leaderboard — Category-wide brand comparison. Ranks all brands in a category by AI visibility.

Start with /geo-run.

Architecture

Python pipeline-based tool with 5 stages:

[Brand Input] → Research → Generate Queries → Run Against AI Models → Analyze Results → Generate Reports

Key Patterns

Provider plugin system — BaseProvider ABC in src/voyage_geo/providers/base.py
Pipeline + RunContext — stages run sequentially, each saving output to disk
Registry pattern — providers, analyzers, query strategies are all pluggable
Pydantic v2 models — src/voyage_geo/config/schema.py is the single source of truth for config types
File-based storage — each run is a self-contained directory under data/runs/
VADER sentiment — production-grade sentiment analysis via vaderSentiment
Async throughout — all providers use async SDKs (AsyncOpenAI, AsyncAnthropic, google-genai async)

Directory Layout

src/voyage_geo/
  __init__.py           # Package root + version
  cli.py                # CLI entry (Typer + Rich)
  config/               # Pydantic schemas, defaults, config loader
  core/                 # Engine, pipeline, context, errors
  providers/            # AI model providers (openai, anthropic, google, perplexity)
  stages/               # 5 pipeline stages
    research/           # Stage 1: Brand research + web scraping
    query_generation/   # Stage 2: Generate search queries (4 AI-powered strategies)
    execution/          # Stage 3: Run queries against providers
    analysis/           # Stage 4: Analyze results (6 analyzers)
    reporting/          # Stage 5: Generate reports (HTML/JSON/CSV/Markdown + plotly charts)
  storage/              # File-based persistence
  types/                # Shared Pydantic type definitions
  utils/                # Text helpers, Rich progress displays

Read the full file on GitHub · 140 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.

11d ago First seen · 140 lines · 1,806 tokens per session scan A fa6309c1e6ee

Subscribe to this mod's changes

voyage-geo-agent CLAUDE.md is an instructions file published in the GitHub repository onvoyage-ai/voyage-geo-agent (382 stars, last pushed 6mo ago), licensed MIT. It adds 1,806 tokens to every session, about $0.0090 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics Marketing and SEO

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

voyage-geo-agent: Instructions file for Claude Code