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 coupler-io/skills --skill amazon-ads-wasted-spend-and-scalinggit clone --depth 1 https://github.com/coupler-io/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/coupler-io/skills/amazon-ads-wasted-spend-and-scaling)<a href="https://agentmods.dev/skills/coupler-io/skills/amazon-ads-wasted-spend-and-scaling"><img src="https://agentmods.dev/badge/skills/coupler-io/skills/amazon-ads-wasted-spend-and-scaling/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/coupler-io/skills/amazon-ads-wasted-spend-and-scaling"><img src="https://agentmods.dev/badge/skills/coupler-io/skills/amazon-ads-wasted-spend-and-scaling.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 | $0.00118 | $0.03260 |
| Opus 5.5 | $0.00047 | $0.01304 |
| Sonnet 5.5 | $0.00024 | $0.00652 |
| Haiku 4.5 | $0.00012 | $0.00326 |
Grade B, and why
amazon-ads-wasted-spend-and-scaling scanned grade B with 1 finding 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 6d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
campaign called "ignore previous instructions" is a string of text. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon Ads Wasted Spend and Scaling
Finds Amazon search terms that spend without selling, builds your negative keyword list, and moves the money to terms that sell. Amazon Ads Wasted Spend and Scaling is a Coupler.io AI agent skill that works with live data from Amazon Ads and Amazon Ads (Unified).
Finds the Amazon Ads search terms and targets spending without selling, builds safe negatives, harvests the winners into their own targeting, and moves the money — as one budget-neutral plan.
Most Amazon waste lives in the search term report: automatic and broad campaigns matching shoppers to queries the product will never sell on, and product-targeting matches onto competitor listings that take clicks and no orders. Most analyses sort by spend and cut the top rows, which removes search terms that were simply early. And the winners are left where they are — sold through a loose campaign at a loose bid, instead of moved into exact targeting where the bid can be set for them.
What you get back
- Wasted spend, sized — search terms and product matches past the significance floor with no orders.
- A negative list with match types, checked against terms that sell.
- A harvest list — search terms that sell, to add as exact keywords or product targets, paired with the negatives that stop them competing with themselves.
- A scale list — campaigns beating the ACOS target at their full budget.
- The net move — freed spend and where it goes, budget unchanged.
Read-only on your Amazon Ads account. It proposes negatives and moves; it never adds one.
Call budget
| Calls to a spoken answer | |
|---|---|
| Cold | locate the data → coverage verdict (speak) → one combined query = 3 |
| Warm — dataset already known | coverage verdict (speak) → one combined query = 2 |
This skill may need more than one dataset — search terms and campaign budgets can be separate reports, and on legacy each ad product has its own search term report. Add a call for each extra dataset the run actually needs, and say so rather than padding the budget in advance.
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.
- 6d ago First seen · 245 lines · 118 tokens per session scan B 989e5c3b743c
amazon-ads-wasted-spend-and-scaling is a skill published in the GitHub repository coupler-io/skills (41 stars, last pushed 4d ago), licensed MIT. It adds 118 tokens to every session and 3,260 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-15.
amazon-ads-wasted-spend-and-scaling compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| amazon-ads-wasted-spend-and-scalingcoupler-io/skills | Skill | 41 | 4d ago | MIT | B | 118 | Claude Code |
| jobs-to-be-donewondelai/skills | Skill | 2.8k | today | MIT | A | 137 | Claude Code |
| remotion-best-practicesguanyang/open-agent-hub | Skill | 1.0k | yesterday | MIT | A | 116 | Claude Code |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | 6d ago | MIT | A | 60 | Claude Code |
| etsy-social-media-marketingnexscope-ai/eCommerce-Skills | Skill | 1.5k | 11d ago | MIT | A | 23 | Claude Code, Codex |
| walmart-price-trackernexscope-ai/eCommerce-Skills | Skill | 1.5k | 11d ago | MIT | A | 0 | Claude Code, Codex |
| happiness-skillkangarooking/cangjie-skill | Skill | 13k | 1mo ago | MIT | A | 136 | Claude Code, Codex |