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 account-structure-reviewgit 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/account-structure-review)<a href="https://agentmods.dev/skills/thatrebeccarae/claude-marketing/account-structure-review"><img src="https://agentmods.dev/badge/skills/thatrebeccarae/claude-marketing/account-structure-review/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/account-structure-review"><img src="https://agentmods.dev/badge/skills/thatrebeccarae/claude-marketing/account-structure-review.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 | $0.00081 | $0.05720 |
| Opus 5 | $0.00041 | $0.02860 |
| Sonnet 5 | $0.00016 | $0.01144 |
| Haiku 4.5 | $0.00008 | $0.00572 |
Grade A, and why
account-structure-review 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 — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Account Structure Review — Google + Meta
Expert-level guidance for evaluating paid media account structure against goals, budget, and conversion volume thresholds. Identifies structural anti-patterns that fragment data, starve budgets, or block algorithms from learning.
Install
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/account-structure-review ~/.claude/skills/
Core Capabilities
Structural Anti-Pattern Detection
- Over-segmentation: Too many campaigns/ad sets splitting data and budget below learning thresholds
- Under-segmentation: Everything in one campaign, can't isolate performance by intent or funnel stage
- Budget fragmentation: Daily budgets too low to exit learning phase or sustain delivery
- Targeting overlap: Multiple campaigns competing in same auctions, bidding against yourself
- Objective mismatch: Using Traffic when you need Conversions, mixing lead gen and ecommerce goals in one campaign
Google-Specific Structure Auditing
- Campaign type separation (Search ≠ Display ≠ Shopping ≠ PMax)
- Ad group theme coherence (SKAGs are dead, STAGs with 5-15 keywords)
- Match type strategy alignment per campaign intent
- PMax cannibalizing branded Search
- Shared budgets causing cross-campaign interference
- Search Partners eating budget without conversions
- Automated bid strategies applied to low-volume campaigns
Meta-Specific Structure Auditing
- CBO vs ABO alignment with goals and budget levels
- Advantage+ Shopping adoption readiness
- Prospecting vs retargeting separation
- Funnel exclusions (retargeting excludes purchasers, prospecting excludes retargeting audiences)
- Advantage+ Audience stability (broad targeting with signal-based constraints)
- Campaign duplication testing without isolation
- Multiple ad sets in prospecting CBO campaigns (common waste vector)
Consolidation Decision Framework
- How to merge campaigns without losing historical data
- Campaign experiments for migration testing (Google) or 50/50 A/B tests (Meta)
- Incremental changes vs wholesale restructure
- Sequencing: What to consolidate first, what to defer
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.
- 12d ago First seen · 471 lines · 81 tokens per session scan A da43e792e037
account-structure-review is a skill published in the GitHub repository thatrebeccarae/claude-marketing (137 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 5,720 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
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.
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.
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.