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.
npx agentmods add instructions/nicofains1/agentic-ads/claude-mdgit clone --depth 1 https://github.com/nicofains1/agentic-adsWrote 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.
[](https://agentmods.dev/instructions/nicofains1/agentic-ads/claude-md)<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>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 | $0.01337 | $0.01337 |
| Opus 5 | $0.00668 | $0.00668 |
| Sonnet 5 | $0.00267 | $0.00267 |
| Haiku 4.5 | $0.00134 | $0.00134 |
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.
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:
- Advertiser side: Brands publish ads via MCP tools (budget, targeting, creative, pricing model)
- 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 │
└──────────────────┘
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.
- 6d ago First seen · 110 lines · 1,337 tokens per session scan A 1bc48ec4023b
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.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.