aeo-radar CLAUDE.md

aeo-radar CLAUDE.md is an instructions file for coding agents from hellowalt/aeo-radar. It costs 1,181 tokens per session, scanned A, original, MIT.

A developer guide for an AEO Radar project, an application that crawls websites and analyzes how brands appear in answers from AI platforms. It documents the TypeScript, browser automation, database, dashboard, and common commands.

In plain words
What is it for?
Use it when working on crawling, prompt seeding, past-run analysis, SQLite schema changes, or the local web dashboard.
Why use it?
It gives a coding agent the project's structure and operating instructions so it can run the crawler, analysis, database updates, and dashboard correctly.

Instructions file

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.

agentmods
npx agentmods add instructions/hellowalt/aeo-radar/claude-md
Clone the repo
git clone --depth 1 https://github.com/hellowalt/aeo-radar

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 aeo-radar CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hellowalt/aeo-radar/claude-md.svg)](https://agentmods.dev/instructions/hellowalt/aeo-radar/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hellowalt/aeo-radar/claude-md"><img src="https://agentmods.dev/badge/instructions/hellowalt/aeo-radar/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,181 This file is loaded in full into every session.
When invoked 1,181 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.01181 $0.01181
Opus 5 $0.00590 $0.00590
Sonnet 5 $0.00236 $0.00236
Haiku 4.5 $0.00118 $0.00118

Measured 4d ago against content hash 5f124d59ff52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aeo-radar 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 4d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **CLI:** TypeScript + tsx, Playwright (stealth plugin), Claude CLI via `execSync`
CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Dev playbook for AEO Radar

Context for Claude Code (or any LLM assistant) working on this repo. Keep it short; if the code answers the question, don't repeat the answer here.

Tech stack

  • CLI: TypeScript + tsx, Playwright (stealth plugin), Claude CLI via execSync
  • DB: SQLite via Prisma 7 (file at data/aeo.db)
  • Dashboard: Next.js 16 + React 19 + Ant Design 6 + Recharts (port 3003)
  • Package manager: npm

Common commands

# Crawl (defaults to headless)
npx tsx src/cli.ts run                 # ChatGPT
npx tsx src/cli.ts run chatgpt --visible  # debug with visible browser

# Seeding & analysis
npx tsx src/cli.ts seed                # generate prompts from brand.ts
npx tsx src/cli.ts analyze <runId>     # re-run analysis on a past run

# Database
npm run db:push                        # apply schema changes to SQLite

# Dashboard
cd web && npm run dev                  # http://localhost:3003

Source layout

src/
├── cli.ts                  # Entry point (run / analyze / seed)
├── types.ts                # LLM_PLATFORMS + shared types
├── config/
│   └── brand.ts            # ← single source of truth for brand/keywords
├── crawlers/
│   ├── base.ts             # Stealth + challenge detection + persistent profile
│   └── chatgpt.ts          # DOM selectors: #prompt-textarea, stop-button
├── pipeline/
│   ├── runner.ts           # Orchestrates prompts × platforms × analysis
│   └── analyzer.ts         # Claude CLI → structured JSON
├── prompts/
│   └── generator.ts        # Seeds keywords/prompts from brand.ts
└── db/
    └── prisma.ts           # Prisma singleton

prompts/
├── generator-template.md   # Claude template for prompt generation
└── analysis-template.md    # Claude template for answer analysis

web/                        # Next.js dashboard
├── src/app/                # Pages + API routes
├── src/components/         # KPI cards, charts, tables, settings
└── src/lib/theme.ts        # Grayscale tokens, AntD ConfigProvider

Read the full file on GitHub · 96 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. 4d ago First seen · 96 lines · 1,181 tokens per session scan A 5f124d59ff52

Subscribe to this mod's changes

aeo-radar CLAUDE.md is an instructions file published in the GitHub repository hellowalt/aeo-radar (25 stars, last pushed 2mo ago), licensed MIT. It adds 1,181 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.