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-auditgit 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-audit)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-ads-claude/ads-audit"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-audit/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-audit"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-audit.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 | $0.00016 | $0.03703 |
| Opus 5 | $0.00008 | $0.01852 |
| Sonnet 5 | $0.00003 | $0.00741 |
| Haiku 4.5 | $0.00002 | $0.00370 |
Grade A, and why
ads-audit 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Performance Auditor
Skill Purpose
Analyze existing ad campaign performance from user-provided data (screenshots, descriptions, or metrics). Evaluate key performance indicators against industry benchmarks, detect creative fatigue and audience overlap, identify budget waste, and provide prioritized optimization recommendations ranked by expected impact. This is a diagnostic tool — it tells you what is working, what is broken, and what to fix first.
When to Use
- User wants to audit their existing ad campaigns
- User shares ad performance data (screenshots, CSV, or described metrics)
- User asks "why aren't my ads working?" or "how can I improve my ads?"
- User wants to know if their ad spend is efficient
- User has been running ads for 7+ days and wants a performance check
- Triggered by
/ads auditor/ads audit <platform>
Data Collection
Step 1: Gather Performance Data
Ask the user to provide their ad data in any of these formats:
Option A: Key Metrics (Manual Input) Ask for these metrics per campaign/ad set:
| Metric | What to Ask |
|---|---|
| Platform | Which platform (Meta, Google, TikTok, LinkedIn, etc.)? |
| Campaign Objective | What's the campaign optimized for (awareness, traffic, conversions, leads)? |
| Time Period | How long has this campaign been running? Date range? |
| Spend | Total amount spent in this period |
| Impressions | Total impressions |
| Reach | Unique people reached (if available) |
| Clicks | Total clicks (link clicks, not all clicks) |
| CTR | Click-through rate (or calculate from impressions/clicks) |
| CPC | Cost per click |
| Conversions | Total conversions (purchases, leads, sign-ups) |
| Conversion Rate | Landing page conversion rate |
| CPA/CPL | Cost per acquisition or cost per lead |
| ROAS | Return on ad spend (revenue / spend) |
| Frequency | Average times each person saw the ad |
| Ad Creative Type | Image, video, carousel, etc. |
Option B: Screenshot Analysis If the user shares screenshots of their ad dashboard:
- Extract all visible metrics from the screenshot
- Note which metrics are missing
- Ask follow-up questions for critical missing data
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 · 347 lines · 16 tokens per session scan A bd62da93b476
ads-audit is a skill published in the GitHub repository zubair-trabzada/ai-ads-claude (246 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 3,703 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 2026-08-30.
Other skills, from other repositories
sql-sentinel
Audit SQL for the cost & performance anti-patterns that burn warehouse credits. Catches SELECT , full-table scans, non-sargable predicates, Cartesian joins, NULL-trap NOT IN, and 17 more rules. Scores warehouse health 0-100 and outputs a prioritized cost-reduction plan for BigQuery, Snowflake, Redshift, and Postgres.
squirrelscan
Skill "squirrelscan" from squirrelscan/squirrelscan, covering squirrelscan cli, links, install, command overview and quickstart.
audit-website
Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories (260+ rules), returns an LLM-optimized report, then drives an iterative fix loop, mapping issues to source files, applying fixes, and re-auditing…
Website Audit
Comprehensive website auditing skill using Lighthouse, PageSpeed Insights, and web performance APIs to audit performance, accessibility, SEO, best practices, and security.
performant-code
Writing efficient code that handles large data and tight constraints.
hermes-self-evaluation
Use this skill when the user asks to audit, review, or optimize Hermes's own performance — analyzing session data, skills, configuration, costs, and usage patterns to identify improvements, automation opportunities, and system optimizations.