agentmods.dev

notion-geo-audit: Instructions file for Claude Code

CLAUDE.md

notion-geo-audit CLAUDE.md is an instructions file for Claude Code from nycsav/notion-geo-audit. It costs 1,248 tokens per session, scanned A, original, MIT.

A project instruction guide for notion-geo-audit, a free tool that checks how visible a website is to AI search systems such as ChatGPT, Claude, Perplexity, and Gemini.

In plain words
What is it for?
Use it when developing, building, deploying, or auditing the notion-geo-audit website and its API.
Why use it?
It gives the agent the project’s architecture, public interfaces, repository details, and deployment context so changes fit the existing system.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is nycsav/notion-geo-audit's own configuration. It tells Claude Code how to work on notion-geo-audit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything notion-geo-audit configures →

not rated 0repo 2mo ago A scan 1,248 tokens original MIT
View source ↗ nycsav/notion-geo-audit geo.ensolabs.ai
Reuse

Borrowing it

Nothing to install: this file belongs to nycsav/notion-geo-audit. 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/nycsav/notion-geo-audit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nycsav/notion-geo-audit

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.

agentmods badge for notion-geo-audit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nycsav/notion-geo-audit/claude-md/github.svg)](https://agentmods.dev/instructions/nycsav/notion-geo-audit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nycsav/notion-geo-audit/claude-md"><img src="https://agentmods.dev/badge/instructions/nycsav/notion-geo-audit/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.

agentmods 80×15 button for notion-geo-audit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nycsav/notion-geo-audit/claude-md"><img src="https://agentmods.dev/badge/instructions/nycsav/notion-geo-audit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,248 This file is loaded in full into every session.
When invoked 1,248 The same file — it is already loaded in full.
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 $0.01248 $0.01248
Opus 5 $0.00624 $0.00624
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured 9d ago against content hash 976322edceeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

notion-geo-audit CLAUDE.md 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 9d 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.

CLAUDE.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

notion-geo-audit — Project Guide

What this is

Free, open-source GEO (Generative Engine Optimization) audit tool by Enso Labs. Scores any website's AI-search visibility (ChatGPT, Claude, Perplexity, Gemini) /100 with copy-paste fixes. Built Jun 12 2026 for the Notion Community Showcase; mission: give communities free AI-visibility tooling.

Live surfaces (all launched, public)

  • Site: https://geo.ensolabs.ai — interactive in-browser audit (dark AI-terminal design, Jun 12 PM redesign) + tools page (4 no-code generators) + presentation deck (13 slides) + "Ask geo-audit" chatbot + architecture map. Self-audit score: 100/100 (dogfooded 50→100; re-verified after redesign).
  • API: /api/audit?url= (15 checks + per-engine breakdown + notionSite flag) and /api/representation?url= (live Perplexity check, rate-limited 1/min/IP + 300/day; PERPLEXITY_API_KEY set in Vercel env, Production).
  • Repo: https://github.com/nycsav/notion-geo-audit — PUBLIC, MIT, 14 topics. Local folder name is geo-audit, repo name is notion-geo-audit.
  • Notion hub: 📡 "geo-audit — Community GEO Demo" (page 37d0bdff-e59e-815d-aa7e-eefdba8dc23c) with sub-pages: DIY connect guide, instruction manual, SEO/GEO checklist, 🏁 GEO Scoreboard template (PUBLISHED + duplicate-as-template ON: square-denim-cf9.notion.site/GEO-Scoreboard-... — subdomain rename to ensolabs pending, update links everywhere after).
  • Results DB (demo): data source 4e47fbf4-1dd1-44fb-94f9-6c1797c6d241 · Template scoreboard DB: data source 2c048e4a-b884-46f4-a26e-626f00ccec63

Architecture

  • src/snapshot.ts → fetch site's public files · src/checks.ts → 15 checks, 4 pillars (crawlability/structure/content/connectivity) · src/report.ts → score + markdown/terminal output · src/representation.ts → optional Perplexity "how does AI describe you" (needs PERPLEXITY_API_KEY in gitignored .env)
  • src/cli.ts — npx tsx src/cli.ts <url> [--md out.md|--json|--representation]
  • src/mcp.ts — MCP server (tools: audit_site, check_ai_representation), wired via project .mcp.json; loads .env itself so keys never sit in client config
  • scripts/notion-sync.ts — audit → row in Notion DB (needs NOTION_TOKEN + NOTION_DATABASE_ID in .env)
  • worker/ — Notion Worker, DEPLOYED Jun 12 (worker id 019ebd2a-f6ee-7260-9016-7cb7bd5abecf, name geo-audit, Enso Labs workspace). auditSite tool live in Notion's runtime — verified via ntn workers exec auditSite -d '{"url":"..."}'. Uses real SDK shape: worker.tool(name, {title, description, schema: j.object(...), execute}) from @notionhq/workers + schema-builder. Lite engine = strict pass/fail (scores lower than full engine). Redeploy: cd worker && ntn workers deploy. v2: worker.sync() managed scoreboard DB.
  • docs/ — the Vercel-deployed static site (deploys from this subfolder)

Read the full file on GitHub · 40 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. 9d ago First seen · 40 lines · 1,248 tokens per session scan A 976322edceeb

Subscribe to this mod's changes

notion-geo-audit CLAUDE.md is an instructions file published in the GitHub repository nycsav/notion-geo-audit (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,248 tokens to every session, about $0.0062 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.

Claude CodeMarketing and SEOaeoai-searchclaudegenerative-engine-optimizationgeo
Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens