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 facebook-ads-audience-targeting-analysisgit 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/facebook-ads-audience-targeting-analysis)<a href="https://agentmods.dev/skills/coupler-io/skills/facebook-ads-audience-targeting-analysis"><img src="https://agentmods.dev/badge/skills/coupler-io/skills/facebook-ads-audience-targeting-analysis/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/facebook-ads-audience-targeting-analysis"><img src="https://agentmods.dev/badge/skills/coupler-io/skills/facebook-ads-audience-targeting-analysis.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 | $0.00106 | $0.02438 |
| Opus 5.5 | $0.00042 | $0.00975 |
| Sonnet 5.5 | $0.00021 | $0.00488 |
| Haiku 4.5 | $0.00011 | $0.00244 |
Grade A, and why
facebook-ads-audience-targeting-analysis 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 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.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Facebook Ads Audience Targeting Analysis
Shows which Meta audiences bring results and which ones are paying to reach the same people twice. Facebook Ads Audience Targeting Analysis is a Coupler.io AI agent skill that works with live data from Facebook Ads (Meta Ads).
Tells you which audiences earn their spend, and which ones you are paying twice to reach.
Meta will not tell you which audience a result came from. There is no audience column in the reporting layer — targeting is a setting, not a dimension — so the only record of what an ad set was aimed at is the name somebody typed when they built it. That means an honest audience analysis has to start by admitting what it is reading, and most audience reporting quietly does not.
What you get back
- Cost per result by audience group, built from the ad set naming convention, with the convention stated so you can see what was assumed.
- Prospecting against retargeting, with the caveat that retargeting is measured on demand someone else created — it always looks cheaper and rarely is.
- Age and gender performance with bid-adjustment candidates, and a minimum-volume floor so you are not acting on eleven conversions.
- Audience ageing — cost per result by how long the ad set has been running against the same people, at constant creative, which is what separates a tired audience from a tired ad.
- New against existing customers where Advantage+ shopping is running and the segment split exists.
- A coverage statement. What could and could not be read from this data.
Read-only. It never changes targeting, a bid or an audience.
How to run this
Three calls to a spoken answer: find the dataset → schema and coverage verdict spoken out loud → one combined query. Two calls when the dataset is known.
Overriding rules: never spend a call proving the connection works; speak at the coverage read; missing data is a line in the write-up, not a gate; don't narrate steps.
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 · 189 lines · 106 tokens per session scan A b1b946e916d8
facebook-ads-audience-targeting-analysis is a skill published in the GitHub repository coupler-io/skills (41 stars, last pushed 4d ago), licensed MIT. It adds 106 tokens to every session and 2,438 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-15.
facebook-ads-audience-targeting-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| facebook-ads-audience-targeting-analysiscoupler-io/skills | Skill | 41 | 4d ago | MIT | A | 106 | 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 |