Borrowing it
Nothing to install: this file belongs to askads/mcp-vk-ads. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/askads/mcp-vk-ads/main/CLAUDE.mdgit clone --depth 1 https://github.com/askads/mcp-vk-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/askads/mcp-vk-ads/claude-md)<a href="https://agentmods.dev/instructions/askads/mcp-vk-ads/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-vk-ads/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/askads/mcp-vk-ads/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-vk-ads/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01418 | $0.01418 |
| Opus 5 | $0.00709 | $0.00709 |
| Sonnet 5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
mcp-vk-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 8d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — mcp-vk-ads
MCP server for the VK Ads (VK Реклама) API (TypeScript, stdio). Tools wrap the REST
endpoints; raw_request is the escape hatch for everything without a dedicated tool.
Commands
npm run dev # run from source (tsx watch)
npm test # unit tests, no network
npm run typecheck # types for src + tests
npm run build # emit dist/
npm run smoke # live READ-ONLY calls (needs VK_ADS_TOKEN)
More detail in docs/DEVELOPMENT.md. Tool list: docs/TOOLS.md.
Architecture
src/client.ts— HTTP client overhttps://ads.vk.com/api(override withVK_ADS_API_BASE): Bearer auth, AbortController timeout (covers reading the body), SSRF guard (buildUrlrefuses a path resolving off the API origin), retry/backoff (honorsRetry-After) — 429 for any method, but 5xx and network errors ONLY for idempotent GET (a retried POST could duplicate a create),getAlloffset/count pagination,VkAdsError(status, body). No sandbox, no quota header, no async report polling.src/tools/*.ts— one file per area (account,adPlans,adGroups,banners,statistics,raw), each exportsregister<Name>Tools(server, client).src/tools/util.ts— shared helpers (see conventions below).src/index.ts— wires everyregister*into the McpServer.src/telemetry.ts— anonymous usage pings (ids/names/versions only, never data or arguments; fire-and-forget, must never block or throw; opt-outASKADS_TELEMETRY=0).startup_failedis the exception:sendBlockingawaits it, because the caller exits right after and a fire-and-forget ping would die in flight. Itsreasonis a closed vocabulary (missing_token, …) — never a variable's name or value.src/config.ts— env → config; throwsConfigError(with areasoncode) instead of exiting, soindex.tscan report the drop-off before dying.
Conventions (do not break)
- Money is in account currency (rubles) as the API returns it — VK Ads has no micro-units, so there is nothing to convert; pass and return amounts as-is.
- Status changes loop per object via
setStatusForIds, not a batch call — VK Ads mutates one object perPOST v2/{entity}/{id}.json. Any per-id failure surfaces the whole result asisError. raw_requestis read-gated by HTTP method: GET runs freely; any POST/DELETE is a write and requiresconfirmWrite=true(isReadMethodis true only for GET).- Validate inputs with zod in
inputSchema(dates via theisoDate()factory — a fresh schema per field, so the generated JSON schema has no shared$ref). - Pagination: single-page tools cap
limitatMAX_PAGE_LIMIT(250) via zod (.max(250)ininputSchema);autoPaginateusesgetAllatMAX_PAGE_LIMIT, caps the total atMAX_AUTO_ITEMS(token-bounded payload) and flags_truncatedinstead of silently cutting. - Runtime guidance for the consuming model goes in the tool
description, not in this file — the external agent never reads CLAUDE.md. API gotchas belong in the tool's description.
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.
- 8d ago First seen · 90 lines · 1,418 tokens per session scan A 8202ed4478b5
mcp-vk-ads CLAUDE.md is an instructions file published in the GitHub repository askads/mcp-vk-ads (5 stars, last pushed 18d ago), licensed MIT. It adds 1,418 tokens to every session, about $0.0071 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
data-scientist copilot-instructions.md
Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.
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.
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.
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).
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).
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.