agentic-ads CLAUDE.md

agentic-ads CLAUDE.md is an instructions file for Claude Code from nicofains1/agentic-ads. It costs 1,337 tokens per session, scanned A, original, MIT.

Project instructions for agentic-ads, an MCP server that lets brands provide advertisements inside AI-agent conversations and lets agent developers earn commissions from them.

In plain words
What is it for?
Use them when changing the agentic-ads project. Check or update the behavioral specification before modifying business logic or adding features.
Why use it?
They provide the project’s agreed rules for advertising flows, pricing, access, matching, transport, and data storage. Keeping those rules as the source of truth helps prevent code from drifting from the specification.

Instructions file for Claude Code

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

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/nicofains1/agentic-ads/claude-md
Clone the repo
git clone --depth 1 https://github.com/nicofains1/agentic-ads

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 agentic-ads CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nicofains1/agentic-ads/claude-md.svg)](https://agentmods.dev/instructions/nicofains1/agentic-ads/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nicofains1/agentic-ads/claude-md"><img src="https://agentmods.dev/badge/instructions/nicofains1/agentic-ads/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,337 This file is loaded in full into every session.
When invoked 1,337 The same file — it is already loaded in full.
Security scan A 0 findings. 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 5.1 $0.01337 $0.01337
Opus 5 $0.00668 $0.00668
Sonnet 5 $0.00267 $0.00267
Haiku 4.5 $0.00134 $0.00134

Measured 6d ago against content hash 1bc48ec4023b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agentic-ads 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 6d 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 · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Ads

What is this?

An MCP server that enables advertising in AI agent conversations. Two sides:

  1. Advertiser side: Brands publish ads via MCP tools (budget, targeting, creative, pricing model)
  2. Consumer side: AI agents (initially OpenClaw bots) query the MCP for relevant ads to show users contextually

The bot developer earns a commission when ads are consumed (shown, clicked, or converted).

⚠️ Behavioral Specification — Source of Truth

bulloak.md es la especificación completa del comportamiento del MCP. Antes de modificar cualquier lógica de negocio, consultar bulloak.md. Cuando se agrega una feature nueva, actualizar bulloak.md PRIMERO.

Cubre:

  • Todos los flows de publisher (advertiser) y consumer (developer)
  • Expected behavior de cada tool (happy path + error paths)
  • Pricing models (CPC/CPM/CPA) con montos exactos
  • Auth, rate limiting, access control
  • Matching algorithm, ranking formula, keyword extraction
  • Transport (stdio + HTTP), sesiones, health check
  • DB schema, constraints, indices

Regla: Si el código contradice bulloak.md, el código está mal.

Vision

Think "Google AdSense for AI agents." Adidas publishes a shoe ad with a $100 budget. Alice asks her OpenClaw bot to help find sneakers. The bot searches the web AND queries our MCP. If there's a relevant ad, the bot weaves it naturally into the response: "Here's the Nike you wanted, and I also found these Adidas at a better price!" If Alice clicks or buys, the bot developer earns a cut.

Architecture Overview

┌─────────────┐     MCP Tools      ┌──────────────────┐     MCP Tools      ┌──────────────┐
│  Advertiser  │ ──────────────────▶│  Agentic Ads MCP │◀────────────────── │ Consumer Bot  │
│  (Brand/API) │  create_campaign   │     Server       │  search_ads        │  (OpenClaw)   │
│              │  create_ad         │                  │  report_event      │              │
│              │  get_analytics     │  - Matching      │  get_guidelines    │  Shows ads   │
└─────────────┘                    │  - Billing       │                    │  to users    │
                                   │  - Auth & Rate   │                    └──────────────┘
                                   │  - Analytics     │
                                   └──────────────────┘

Read the full file on GitHub · 110 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. 6d ago First seen · 110 lines · 1,337 tokens per session scan A 1bc48ec4023b

Subscribe to this mod's changes

agentic-ads CLAUDE.md is an instructions file published in the GitHub repository nicofains1/agentic-ads (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,337 tokens to every session, about $0.0067 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.