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.
git 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/rules/thatrebeccarae/claude-marketing/wasted-spend-finder)<a href="https://agentmods.dev/rules/thatrebeccarae/claude-marketing/wasted-spend-finder"><img src="https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/wasted-spend-finder/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/rules/thatrebeccarae/claude-marketing/wasted-spend-finder"><img src="https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/wasted-spend-finder.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 | $0.00044 | $0.02137 |
| Opus 5 | $0.00022 | $0.01069 |
| Sonnet 5 | $0.00009 | $0.00427 |
| Haiku 4.5 | $0.00004 | $0.00214 |
Grade A, and why
wasted-spend-finder 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 11d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wasted Spend Finder
Identify and categorize wasted ad spend across Google Ads and Meta platforms. Produces uploadable exclusion lists with thematic categorization.
Core Capabilities
Google Ads Waste Detection
- Search Term Waste — zero-conversion terms above spend threshold
- Placement Waste — Display Network sites/apps and YouTube channels with no conversions
- Keyword-Level Waste — low conversion rate keywords relative to spend
Meta Ads Waste Detection
- Placement Waste — Audience Network apps, low-quality inventory
- Audience Segment Waste — lookalike/interest targeting with poor performance
- Creative Waste — high frequency + zero conversions, creative fatigue
Waste Thresholds
Spend Threshold Formula
Waste threshold = Average CPA x Multiplier
Multiplier by campaign type:
- Search (branded): 2x CPA
- Search (non-brand): 3x CPA
- Display: 3x CPA
- Meta (all): 2.5x CPA
A search term, placement, or audience segment is flagged as waste when:
- Spend exceeds the threshold AND
- Conversions = 0 AND
- Minimum click threshold is met
Minimum Click Thresholds
| Campaign Type | Min Clicks Before Flagging |
|---|---|
| Search (branded) | 50 |
| Search (non-brand) | 25 |
| Display / GDN | 15 |
| YouTube | 20 |
| Meta Feed | 20 |
| Meta Stories | 15 |
| Meta Audience Network | 10 |
Conversion Rate Minimums
Flag keywords/placements performing below these floors:
| Campaign Type | Min Conversion Rate |
|---|---|
| Search (branded) | 8% |
| Search (non-brand) | 1.5% |
| Display | 0.3% |
| YouTube | 0.2% |
| Meta Feed | 0.5% |
| Meta Stories | 0.3% |
Negative Keyword Categorization
Classify wasted search terms into themes for organized exclusion:
| Theme | Pattern | Match Type |
|---|---|---|
| Competitor terms | Brand names, product names | Exact / Phrase |
| Informational intent | how to, what is, tutorial, guide, definition | Phrase |
| Wrong product/service | Related but non-target products | Phrase / Exact |
| Geographic irrelevance | Wrong cities, states, countries | Exact |
| Job/career searches | jobs, salary, hiring, career, resume | Phrase |
| Free/cheap intent | free, cheap, discount, coupon, deal | Phrase |
| Irrelevant modifiers | DIY, homemade, kids, old, used | Phrase |
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.
- 11d ago First seen · 304 lines · 44 tokens per session scan A 54e0934f2b68
wasted-spend-finder is a cursor rule published in the GitHub repository thatrebeccarae/claude-marketing (136 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 2,137 once invoked, about $0.0002 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.