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 naveedharri/benai-skills --skill ads-auditgit clone --depth 1 https://github.com/naveedharri/benai-skillsWrote 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/naveedharri/benai-skills/ads-audit)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/ads-audit"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/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/naveedharri/benai-skills/ads-audit"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/ads-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.01016 |
| Opus 5 | $0.00038 | $0.00508 |
| Sonnet 5 | $0.00015 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00102 |
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 12d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Multi-Platform Ads Audit
Process
- Collect account data — request exports, screenshots, or API access
- Detect business type — analyze account signals per ads orchestrator
- Identify active platforms — determine which platforms are in use
- Delegate to subagents (if available, otherwise run inline sequentially):
audit-google— Conversion tracking, wasted spend, structure, keywords, ads, settings (G01-G74)audit-meta— Pixel/CAPI health, creative fatigue, structure, audience (M01-M46)audit-creative— LinkedIn, TikTok, Microsoft creative checks + cross-platform synthesisaudit-tracking— LinkedIn, TikTok, Microsoft tracking + cross-platform tracking healthaudit-budget— LinkedIn, TikTok, Microsoft budget/bidding + cross-platform allocationaudit-compliance— All-platform compliance, settings, performance benchmarks
- Score — calculate per-platform and aggregate Ads Health Score (0-100)
- Report — generate prioritized action plan with Quick Wins
Data Collection
Ask the user for available data. Accept any combination:
- Google Ads: account export, Change History, Search Terms Report
- Meta Ads: Ads Manager export, Events Manager screenshot, EMQ scores
- LinkedIn Ads: Campaign Manager export, Insight Tag status
- TikTok Ads: Ads Manager export, Pixel/Events API status
- Microsoft Ads: account export, UET tag status, import validation results
If no exports available, audit from screenshots or manual data entry.
Scoring
Read ads/references/scoring-system.md for full algorithm.
Per-Platform Weights
| Platform | Category Weights |
|---|---|
| Conversion 25%, Waste 20%, Structure 15%, Keywords 15%, Ads 15%, Settings 10% | |
| Meta | Pixel/CAPI 30%, Creative 30%, Structure 20%, Audience 20% |
| Tech 25%, Audience 25%, Creative 20%, Lead Gen 15%, Budget 15% | |
| TikTok | Creative 30%, Tech 25%, Bidding 20%, Structure 15%, Performance 10% |
| Microsoft | Tech 25%, Syndication 20%, Structure 20%, Creative 20%, Settings 15% |
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.
- 12d ago First seen · 110 lines · 76 tokens per session scan A 99e4a502f137
ads-audit is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 8d ago), licensed MIT. It adds 76 tokens to every session and 1,016 once invoked, about $0.0004 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
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.