budget-guard

budget-guard is a skill for Claude Code from theYahia/WWmcp. It costs 18 tokens per session (649 once invoked), scanned A, original, MIT.

A VK Ads budget-monitoring workflow. VK Ads is an advertising platform; this checks active campaigns over the last seven days and calculates their click and impression results.

In plain words
What is it for?
Use it to flag campaigns above a cost-per-click limit or with almost no clicks, then stop them or lower their budgets.
Why use it?
It helps find campaigns spending money without enough clicks before changing them. It also requires confirmation before pausing a campaign or reducing its budget.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to flag campaigns above a cost-per-click limit or with almost no clicks, then stop them or lower their budgets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/theyahia/wwmcp/budget-guard
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.

Any agent
npx skills add theYahia/WWmcp --skill budget-guard
Clone the repo
git clone --depth 1 https://github.com/theYahia/WWmcp

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 budget-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/theyahia/wwmcp/budget-guard/github.svg)](https://agentmods.dev/skills/theyahia/wwmcp/budget-guard)
Your own site
<a href="https://agentmods.dev/skills/theyahia/wwmcp/budget-guard"><img src="https://agentmods.dev/badge/skills/theyahia/wwmcp/budget-guard/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.

agentmods 80×15 button for budget-guard

Your own site · 80×15
<a href="https://agentmods.dev/skills/theyahia/wwmcp/budget-guard"><img src="https://agentmods.dev/badge/skills/theyahia/wwmcp/budget-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 649 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00018 $0.00649
Opus 5 $0.00009 $0.00324
Sonnet 5 $0.00004 $0.00130
Haiku 4.5 $0.00002 $0.00065

Measured 6d ago against content hash 625008048191, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

budget-guard 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.

servers/vk-ads/.claude/skills/budget-guard/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/budget-guard — Stop the bleeding

Algorithm

  1. Call get_account. Note the remaining balance — this is the runway. (Balance needs the OAuth scope read_payments.)
  2. Call list_campaigns with status: "active".
  3. Call get_statistics with object_type: "campaigns", ids = the active campaign ids (max 200), period: "day", and date_from / date_to covering the last 7 days (YYYY-MM-DD, range at most 92 days).
  4. For each campaign compute CPC (spend / clicks) and CTR (clicks / shows) — VK calls impressions shows. Amounts are already in the cabinet currency; do not divide by 100.
  5. Flag a campaign when it exceeds the user's CPC threshold, or when it has spent money with near-zero clicks. State the numbers — never flag on a hunch.
  6. Show the flagged list and ask for confirmation before changing anything.
  7. On confirmation, per campaign either:
    • update_campaign with campaign_id and action: "stop" to pause it, or
    • update_campaign with campaign_id and budget_limit / budget_limit_day to cut its budget instead.
  8. Call list_campaigns again to confirm the new state.
  9. If one campaign is the problem but not all of it, drill down: list_ad_groups with campaign_ids, then get_statistics with object_type: "ad_groups".

Response format

## VK Ads budget guard

**Balance**: 84,000 ₽
**Last 7 days spend**: 41,200 ₽ → runway ≈ 14 days

### Flagged (CPC over 15 ₽)
| Campaign | Spend 7d | Clicks | CPC | Action |
|----------|----------|--------|-----|--------|
| Осенняя распродажа | 28,400 ₽ | 812 | 34.98 ₽ | stopped |
| Тест видео | 6,200 ₽ | 41 | 151.22 ₽ | budget_limit → 5,000 ₽ |

Projected saving: ~24,000 ₽ / week.

Notes

  • Budgets are in the cabinet currency (roubles for RUB), not kopecks.
  • action accepts activate, stop and delete. Stopping is reversible — say so, it makes the decision easier. delete is not.
  • Never stop a campaign without explicit confirmation, even when the numbers are damning.
  • update_campaign is annotated destructive: the client may prompt the user before it runs.

Read the full file on GitHub · 61 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 · 61 lines · 18 tokens per session scan A 625008048191

Subscribe to this mod's changes

budget-guard is a skill published in the GitHub repository theYahia/WWmcp (29 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 649 once invoked, about $0.0001 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 2026-09-06.

Related

Other skills, from other repositories

javascript-typescript

Professional JavaScript and TypeScript development skill covering modern ES6+, TypeScript, Node.js, Express, React, testing frameworks, and best practices. Use this skill when developing JavaScript/TypeScript applications, building React/Node.js projects, implementing RESTful APIs, or need guidance on modern JS/TS…

ProjAnvil/MindForge · 69 tokens

okx-cex-earn

A tool for managing several earning products on OKX, including savings, lending, staking, DeFi, Dual Investment, and AutoEarn. These products can use deposited cryptocurrency to generate returns, with terms that vary by product.

okx/agent-trade-kit · 274 tokens

okx-cex-smartmoney

An OKX tool for studying activity from high-performing traders, sometimes called “smart money.” It shows trader rankings, positions, trades, past results, and combined signals.

okx/agent-trade-kit · 200 tokens

adding-a-command

Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing. Use when user says add command, new CLI command, create subcommand, or adds files to src/commands/. Do NOT use for modifying existing…

caliber-ai-org/ai-setup · 76 tokens

typescript-patterns

TypeScript types: generics, discriminated unions, Zod, satisfies, branded types. Triggers: TypeScript, TS, generics, Zod, satisfies, strict mode.

softspark/ai-toolkit · 42 tokens

aba-precision-protocol

FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.

dcostenco/prism-coder · 48 tokens