mcp-open-advertising: Instructions file for Claude Code

CLAUDE.md

mcp-open-advertising CLAUDE.md is an instructions file for Claude Code from cesteral/mcp-open-advertising. It costs 4,731 tokens per session, scanned B, original, Apache-2.0.

Project instructions for Cesteral, a platform made of separate MCP servers for optimizing advertising through different ad-platform APIs. It explains the repository layout, commands, and monorepo workflow; a monorepo stores multiple related packages in one repository.

In plain words
What is it for?
Use it to install dependencies, build, type-check, test, clean, run a server locally, or work on one advertising-server package.
Why use it?
It helps the coding agent work across many packages without confusing package-level commands, shared code, or dependency order.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is cesteral/mcp-open-advertising's own configuration. It tells Claude Code how to work on mcp-open-advertising 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 mcp-open-advertising configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cesteral/mcp-open-advertising. 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/cesteral/mcp-open-advertising/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/cesteral/mcp-open-advertising

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 mcp-open-advertising CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cesteral/mcp-open-advertising/claude-md.svg)](https://agentmods.dev/instructions/cesteral/mcp-open-advertising/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cesteral/mcp-open-advertising/claude-md"><img src="https://agentmods.dev/badge/instructions/cesteral/mcp-open-advertising/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,731 This file is loaded in full into every session.
When invoked 4,731 The same file — it is already loaded in full.
Security scan B 2 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 $0.04731 $0.04731
Opus 5 $0.02365 $0.02365
Sonnet 5 $0.00946 $0.00946
Haiku 4.5 $0.00473 $0.00473

Measured 7d ago against content hash 3e5279805993, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

mcp-open-advertising CLAUDE.md scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST http://localhost:<port>/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","method":"ping","id":1}'

Makes network callslowCapability

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

curl -X POST http://localhost:<port>/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","method":"ping","id":1}'
CLAUDE.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (claude.ai/code) when working in this repository. The public fleet overview — server list, ports, API versions, tool counts — lives in README.md. This file covers how the repo is structured and how to work in it: architecture patterns, conventions, gotchas, and cross-cutting subsystems.

Project Overview

Cesteral is an AI-native programmatic advertising optimization platform built on independent MCP (Model Context Protocol) servers — one per ad platform — plus a shared workspace package. Each server is purpose-built around the platform's API client and auth model.

Essential Commands

pnpm install        # Install dependencies
pnpm run build      # Build all packages (Turborepo, dependency-ordered)
pnpm run typecheck  # Type check all packages
pnpm run test       # Run all tests
pnpm run clean      # Clean build artifacts

./scripts/dev-server.sh <server-name>            # Run a server locally on its correct port (e.g. dv360-mcp)
cd packages/<server-name> && pnpm run dev:http   # Or run directly
# Single package: cd packages/<server-name> && pnpm run <build|test|typecheck>

Critical: When modifying @cesteral/shared, rebuild all packages with pnpm run build — Turborepo handles dependency order and the workspace:* protocol propagates the changes.

Monorepo Architecture

pnpm workspace monorepo managed by Turborepo. Workspace: @cesteral/shared (types, utilities, auth) + @cesteral/contract-schema (canonical shape of the cesteral.* annotations, dry-run/snapshot response schemas, and the manifest — the source of truth @cesteral/shared re-exports) + @cesteral/contract-hash (canonical tool-definition hash) + one package per MCP server.

  • Build pipeline: build^build (deps first), typecheck/test depend on ^build
  • ES modules, Target: ES2022, moduleResolution: bundler
  • Each MCP server exposes tools via MCP for external AI agents (Claude Desktop, etc.)

Read the full file on GitHub · 204 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 · 204 lines · 4,731 tokens per session scan B 3e5279805993

Subscribe to this mod's changes

mcp-open-advertising CLAUDE.md is an instructions file published in the GitHub repository cesteral/mcp-open-advertising (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 4,731 tokens to every session, about $0.0237 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

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