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 skills add sergeylopukhov/vk-ads-mcp-all-in-one --skill codex-skillgit clone --depth 1 https://github.com/sergeylopukhov/vk-ads-mcp-all-in-oneWrote 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/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill)<a href="https://agentmods.dev/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill"><img src="https://agentmods.dev/badge/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill/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/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill"><img src="https://agentmods.dev/badge/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill.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 | $0.00070 | $0.01369 |
| Opus 5 | $0.00035 | $0.00685 |
| Sonnet 5 | $0.00014 | $0.00274 |
| Haiku 4.5 | $0.00007 | $0.00137 |
Grade A, and why
vk-ads-mcp 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 11d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VK Ads MCP
Use only public tools exposed by the installed vk-ads server. Do not invent
tool names, provider fields, object IDs, or results.
Core procedure
- For the first advertising operation, call
vk_ads_connection_check. Skip it for community-only work because those tools use a separate Core VK token. - Infer safe missing parameters from read tools and the conversation. Ask only when a value cannot be inferred reliably or changes the user's decision.
- For analysis, establish the object hierarchy and reporting period before interpreting metrics. Prefer complete periods and disclose partial data.
- Call write tools only when the user explicitly requests that exact change.
- Before every supported write, call
vk_ads_action_preparewith the intended action and the exact input. ReadActionReadiness; do not infer missing provider requirements from a failed write. - If
ready=false, report the concrete missing or incompatible condition. Apply asuggestedPatchto a related object only after separate user confirmation whenrequiresConfirmation=true. - When
ready=true, use one narrow write call with the same input. Never cycle through creatives or repeat a write based on a guess. Reread the result when supported. - Never expose tokens, client secrets, identifier-file contents, lead contacts, respondent answers, or raw private provider payloads.
- Respond in Russian unless the user requests another language.
Live status
Treat the installed release's docs/tools.md as the status authority.
- A
✅tool may be used normally within the rules above. - A
⛔️read tool may be attempted when useful, but disclose its status before use and report the result without describing the tool as available. - Do not use a
⛔️write tool as a routine solution. The OAuth recovery exceptions below still require an explicit user request. Do not use other⛔️write tools. - Never treat an expected failure, empty mutation, or
remoderated=falseas success.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 115 lines · 70 tokens per session scan A 59f1da817a23
vk-ads-mcp is a skill published in the GitHub repository sergeylopukhov/vk-ads-mcp-all-in-one (0 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,369 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…