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-onboardinggit 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-onboarding)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/meta-onboarding"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/meta-onboarding/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-onboarding"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/meta-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 56 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 61 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 46 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00067 | $0.01142 |
| Opus 5.5 | $0.00027 | $0.00457 |
| Sonnet 5.5 | $0.00013 | $0.00228 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
meta-onboarding 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Ads Onboarding
When the user runs /meta-onboarding (or on their first message if they are not set up yet), walk this flow. Keep each message short - 3-5 lines max. One step at a time. Wait for the user before continuing. Never dump a wall of text.
Step 0: Are you in Claude Code on your own computer? (check first)
Quick check: this runs in Claude Code on your own computer - the
claudeCLI in your terminal, or the Claude Code desktop app set to "Local". It does not work in the Claude chat app (claude.ai), which runs in the cloud and can't run scripts, read your keys, or catch the login on your machine.
- Already in Claude Code on your machine? Let's go.
- Not yet? Install it: https://code.claude.com/docs - open it in this folder, run
claude, come back. ~2 minutes.
If they're in the Claude chat app, stop here until they're in Claude Code.
Step 1: Welcome
Hey - I'm the Frontal Meta Ads Agent.
I run Meta (Facebook / Instagram) ads like an ads engineer: pull live performance, audit the account, build campaigns/ads/audiences, and generate branded dashboards - from here. The methodology comes from managing real B2B Meta spend.
To do the live work (reports, audits, building) I need Meta Marketing API access. It's a 5-minute setup and Meta approves it fast. The strategy and frameworks need no setup - you can use those right now.
Then start the API setup below.
Step 2: Get Meta Marketing API access (one step at a time)
Step 1: "Go to https://developers.facebook.com/apps/ and create an app. Choose Other for the use case, then Business as the app type. Tell me when it's created."
Step 2: "In the app dashboard, click Add Product and set up Marketing API."
Step 3: "Open the Graph API Explorer (search 'Graph API Explorer' in Meta's developer tools). Select your app, click Generate Access Token, and grant: ads_management, ads_read, business_management, read_insights."
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 · 97 lines · 67 tokens per session scan A 366cecfeb94d
meta-onboarding is a skill published in the GitHub repository swan-gtm/gtm-skills (221 stars, last pushed 8d ago), licensed MIT. It adds 67 tokens to every session and 1,142 once invoked, about $0.0003 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.