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 thatrebeccarae/claude-marketing --skill cross-platform-auditgit clone --depth 1 https://github.com/thatrebeccarae/claude-marketingWrote 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/thatrebeccarae/claude-marketing/cross-platform-audit)<a href="https://agentmods.dev/skills/thatrebeccarae/claude-marketing/cross-platform-audit"><img src="https://agentmods.dev/badge/skills/thatrebeccarae/claude-marketing/cross-platform-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/thatrebeccarae/claude-marketing/cross-platform-audit"><img src="https://agentmods.dev/badge/skills/thatrebeccarae/claude-marketing/cross-platform-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 | $0.00104 | $0.01847 |
| Opus 5 | $0.00052 | $0.00924 |
| Sonnet 5 | $0.00021 | $0.00369 |
| Haiku 4.5 | $0.00010 | $0.00185 |
Grade A, and why
cross-platform-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 7d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Platform Audit — Unified Paid Media Assessment
Orchestrates parallel scored audits across Google Ads, Meta Ads, and Microsoft Ads, then merges results into a single budget-weighted health score with cross-platform intelligence.
Install
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/cross-platform-audit ~/.claude/skills/
Context Intake (Always Do First)
Before running audits, collect this information. Without it, benchmarks will be generic and recommendations may be wrong.
Ask these questions (combine into one prompt):
- Business type — E-commerce/DTC, SaaS/B2B, Local Service, Lead Gen, Agency, Other
- Monthly ad spend — Total and per-platform breakdown (approximate is fine)
- Primary goal — Revenue/ROAS, Leads/CPA, App Installs, Brand Awareness
- Active platforms — Which platforms are they advertising on? (Google, Meta, Microsoft, others)
- Data available — What can they provide? (exports, screenshots, pasted metrics, MCP access)
Use the provided context to:
- Determine which platform audits to run (skip platforms they don't use)
- Calculate budget share per platform for aggregate scoring
- Calibrate severity based on spend level ($5K/mo gets different advice than $100K/mo)
Orchestration Workflow
Step 1: Collect Context
Gather business type, platforms, budgets, goals, and available data per the intake above.
Step 2: Spawn Parallel Audits
Use the Task tool to run platform audits simultaneously. Each audit task should:
- Load
skills/shared/scoring-system.mdfor the scoring algorithm - Load the platform-specific
CHECKS.mdfor the audit checklist - Load the platform-specific
SKILL.mdandREFERENCE.mdfor diagnostic context - Evaluate each applicable check as PASS, WARNING, or FAIL
- Calculate the platform health score using weighted formula
- Identify Quick Wins
- Write results to a structured output
Spawn these tasks in parallel (adjust based on which platforms the user has):
What ships with it
3 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.
- 7d ago First seen · 185 lines · 104 tokens per session scan A d8de92530075
cross-platform-audit is a skill published in the GitHub repository thatrebeccarae/claude-marketing (134 stars, last pushed 3mo ago), licensed MIT. It adds 104 tokens to every session and 1,847 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
csharp-patterns
C#/.NET: LINQ, async/await, DI, records, nullable refs, ASP.NET Core, EF Core, MediatR. Triggers: C#, .NET, dotnet, ASP.NET, EF Core, LINQ, record type, IServiceCollection.
seo-validate
SEO validator: meta/OG, Schema.org, hreflang, Core Web Vitals, crawlability. Triggers: SEO, meta tags, Schema.org, hreflang, LCP, INP, CLS, Core Web Vitals, sitemap, crawlability.
debug
Systematic debugging via logs, health checks, hypothesis-driven investigation. Triggers: debug, error, trace root cause, fix bug, reproduce symptom, investigation.
ruby-patterns
Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.
research-mastery
Hierarchical retrieval: KB → MCP/Context7 → web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, cite sources.
plan
Breaks features/goals into phased plans with task lists, agent assignments, dependencies. Triggers: plan feature, implementation roadmap, break down task, project phases.