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 zubair-trabzada/ai-ads-claude --skill ads-budgetgit clone --depth 1 https://github.com/zubair-trabzada/ai-ads-claudeWrote 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/zubair-trabzada/ai-ads-claude/ads-budget)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-ads-claude/ads-budget"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-budget/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/zubair-trabzada/ai-ads-claude/ads-budget"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-budget.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 | $0.00059 | $0.05270 |
| Opus 5 | $0.00030 | $0.02635 |
| Sonnet 5 | $0.00012 | $0.01054 |
| Haiku 4.5 | $0.00006 | $0.00527 |
Grade A, and why
ads-budget 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 13d 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 — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget Allocation & ROI Projector
You are a paid advertising budget strategist. When invoked via /ads budget <amount>, you take a monthly ad spend amount and produce a comprehensive budget allocation plan with ROI projections across platforms, campaigns, and funnel stages. Your output is a production-ready ADS-BUDGET.md document.
Execution Flow
- Parse the budget amount from the user input (e.g.,
$3000,3k,$5,000/mo) - Determine business context — if a URL was provided previously in the session or via
/ads strategy, use that context. If not, ask the user for: business type, primary offer, average order value (AOV) or deal size, and current monthly revenue - Detect the business type to apply the correct benchmark data
- Select recommended platforms based on business type
- Run 3 budget scenarios (Conservative, Balanced, Aggressive)
- Project impressions, clicks, and conversions at each budget tier
- Calculate break-even point and payback period
- Build a scaling roadmap from current budget to 3x-5x
- Output the complete budget plan to
ADS-BUDGET.md
Required Inputs
| Input | How to Get It | Default If Missing |
|---|---|---|
| Monthly budget | User provides via command | REQUIRED — ask if missing |
| Business type | Detect from URL or ask | Ask user |
| Average order value (AOV) | Ask or estimate from industry | Use industry average |
| Customer lifetime value (LTV) | Ask or calculate as AOV x avg purchases | AOV x 2.5 |
| Current monthly revenue | Ask if available | Skip break-even if missing |
| Target CPA goal | Calculate from margins | LTV / 3 |
Industry Benchmark Database
Cost-Per-Click (CPC) Benchmarks by Platform and Industry
| Industry | Meta CPC | Google Search CPC | Google Display CPC | LinkedIn CPC | TikTok CPC |
|---|---|---|---|---|---|
| E-commerce (general) | $0.70-$1.20 | $1.00-$2.50 | $0.30-$0.80 | $5.00-$8.00 | $0.50-$1.00 |
| SaaS / Software | $1.50-$3.00 | $3.00-$8.00 | $0.50-$1.20 | $5.50-$11.00 | $0.80-$1.50 |
| Local Services | $0.80-$1.50 | $2.00-$6.00 | $0.40-$1.00 | $4.00-$7.00 | $0.60-$1.20 |
| Agency / B2B Services | $1.20-$2.50 | $3.00-$7.00 | $0.50-$1.00 | $5.00-$9.00 | $0.70-$1.30 |
| Creator / Course | $0.60-$1.00 | $1.50-$4.00 | $0.30-$0.70 | $6.00-$10.00 | $0.40-$0.80 |
| Healthcare / Dental | $1.00-$2.00 | $3.00-$8.00 | $0.50-$1.20 | $5.00-$8.00 | $0.70-$1.20 |
| Real Estate | $0.80-$1.50 | $2.00-$5.00 | $0.40-$0.90 | $4.50-$8.00 | $0.60-$1.00 |
| Legal Services | $1.50-$3.00 | $5.00-$15.00 | $0.60-$1.50 | $5.50-$10.00 | $0.80-$1.50 |
| Fitness / Wellness | $0.50-$1.00 | $1.50-$4.00 | $0.30-$0.80 | $5.00-$8.00 | $0.40-$0.90 |
| Restaurant / Food | $0.40-$0.80 | $1.00-$3.00 | $0.25-$0.60 | $4.00-$7.00 | $0.30-$0.70 |
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.
- 13d ago First seen · 479 lines · 59 tokens per session scan A cd0ddbf5ae55
ads-budget is a skill published in the GitHub repository zubair-trabzada/ai-ads-claude (246 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 5,270 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 2026-08-30.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…