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 swan-gtm/gtm-skills --skill meta-b2b-overviewgit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/meta-b2b-overview)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/meta-b2b-overview"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/meta-b2b-overview/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/swan-gtm/gtm-skills/meta-b2b-overview"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/meta-b2b-overview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01345 |
| Opus 5.5 | $0.00018 | $0.00538 |
| Sonnet 5.5 | $0.00009 | $0.00269 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
meta-b2b-overview 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 1mo 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Ads for B2B SaaS - Overview
Why Meta works for B2B, how the algorithm works (Andromeda + Gem), and the operating model for running Meta ads for B2B SaaS with $30K+ ACV.
Why Meta for B2B SaaS
Meta gets a bad rep in B2B. People think Facebook is full of junk and you can't reach B2B buyers. That's wrong - when done right:
- ~50% lower cost per lead vs LinkedIn in many cases
- Lower cost per qualified opportunity when audience quality is validated
- B2B SaaS companies regularly drive 100+ scheduled demos/month at sub-$1,000 cost per demo, with $2-4K cost per opportunity (mid-market and enterprise).
The catch: You can't sell to everyone. B2B success on Meta depends on data quality and creative doing the targeting work - not Meta's native B2B targeting (which is weak). And you're on a discovery platform, not a search engine - people are scrolling, not shopping.
How the Algorithm Works: Andromeda + Gem
Two systems decide who sees your ads. Understanding them drives strategy.
Andromeda (Ad Processing Layer)
ML model that processes your ads - copy, images, video transcripts, carousels, targeting hints. Filters to the creative concepts it thinks will perform best.
Critical point: Andromeda needs volume. It processes "three orders of magnitude" more ads in early stages. You need many unique creative concepts, not micro-variations (blue vs green button). Think: UGC vs before/after vs meme vs problem/solution.
Post-2024 update: Andromeda is now 10,000x more powerful at finding converters. Creative quality matters more than targeting. Broad targeting + great creative can outperform hyper-segmented campaigns.
Gem (User Matching Layer)
Analyzes each user's behavior - organic interactions, ad engagement history, browsing patterns - and matches them to the creative concepts Andromeda selected. Picks the best user for each ad.
What This Means for B2B
- B2C: Broad audiences + high creative volume = fast algorithm optimization
- B2B with large TAM (SMB/mid-market): You can lean into the algorithm. Feed it creative volume, let Andromeda and Gem work.
- B2B with small TAM (enterprise, niche): The algorithm alone won't find your 500 target companies. You must supplement with explicit audience data (CRM lookalikes, third-party enrichment). The algorithm optimizes delivery within your defined audience, but can't replace audience definition.
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.
- 1mo ago First seen · 104 lines · 46 tokens per session scan A 0752823fdb00
meta-b2b-overview is a skill published in the GitHub repository swan-gtm/gtm-skills (221 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 1,345 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.
paid-ad-copy-writer
Write paid ad copy for affiliate offers across ad platforms. Triggers on: "write ad copy", "Facebook ad for affiliate", "Google Ads copy", "TikTok ad script", "Pinterest ad", "paid traffic to affiliate", "create ad campaign", "ad headlines", "ad descriptions", "scale with paid ads", "run ads for my affiliate link"…
gooseworks
GooseWorks growth coworker and router for markets, competitors, audiences, creators, campaigns, ads, photos, graphics, video, content, email, SEO, social, leads and contacts. Use for brand facts or copy too, so offers, prices, rules, audience and bestsellers reach the brand's Marketing Brain.
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
yandex-direct
Skill "yandex-direct" from VKirill/claude-lane-stack, covering version requirements, usage, use this skill when, do not use this skill when and purpose.
yandex-direct-creatives
An advertising-writing guide for Yandex.Direct, a Russian online advertising platform. It turns keyword clusters from Key Collector, a keyword research tool, into campaigns, ad groups, and ads.