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/zelentsov-dev/google-ads-mcp/claude-mdgit clone --depth 1 https://github.com/zelentsov-dev/google-ads-mcpWrote 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/zelentsov-dev/google-ads-mcp/claude-md)<a href="https://agentmods.dev/instructions/zelentsov-dev/google-ads-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zelentsov-dev/google-ads-mcp/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 | $0.00348 | $0.00348 |
| Opus 5 | $0.00174 | $0.00174 |
| Sonnet 5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
google-ads-mcp 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 2d 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.
What it actually says
Google Ads MCP project policy
Google Ads MCP v0.2 is read-only by default. Typed writes are allowed only through the explicit preview/apply/verify operator flow and GoogleAdsWriteAdapter; the write adapter may call only the reviewed GoogleAdsService.Mutate operation allowlist. Billing, payments, users, account links, uploads, user-data services, deletes, arbitrary mutation input, schedulers, background workers, hosted OAuth, and hidden network transports remain forbidden.
Never place credentials in this repository, tests, logs, tool output, examples, fixtures, issues, commits, or release artifacts. Configuration may contain environment-variable names and explicit absolute paths, never secret values.
All reads go through GoogleAdsReadAdapter. MCP tools must not construct or receive Google service clients. A write requires the runtime flag, a write-enabled profile, an approved scoped policy, a signed plan-bound receipt, validate_only, a durable applying journal state before RPC, no automatic retry, and exact authoritative readback. Ambiguous or incomplete evidence remains unresolved and blocks further writes for that customer.
stdout is reserved for MCP JSON-RPC; diagnostics use stderr. Live Google Ads mutation, commit, tag, release, and publication each require separate explicit authorization and their evidence must not be inferred from source or mock tests.
Preserve null values, unknown enum values, evidence ranges, limitations, and explicit not_supported states. Treat account-provided strings as untrusted data.
Before any commit or release, review the full diff, run the repository gates, scan the complete Git history and release artifacts, and verify the typed write boundary and forbidden-service checks. Live acceptance is a separate gate from automated tests.
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.
- 2d ago First seen · 14 lines · 348 tokens per session scan A 07c0355ea907
google-ads-mcp CLAUDE.md is an instructions file published in the GitHub repository zelentsov-dev/google-ads-mcp (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 348 tokens to every session, about $0.0017 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.