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 agentmods add skills/themattberman/meta-ads-kit/ad-uploadnpx skills add TheMattBerman/meta-ads-kit --skill ad-uploadgit clone --depth 1 https://github.com/TheMattBerman/meta-ads-kitWrote 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/themattberman/meta-ads-kit/ad-upload)<a href="https://agentmods.dev/skills/themattberman/meta-ads-kit/ad-upload"><img src="https://agentmods.dev/badge/skills/themattberman/meta-ads-kit/ad-upload.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.04877 |
| Opus 5 | $0.00026 | $0.02439 |
| Sonnet 5 | $0.00010 | $0.00975 |
| Haiku 4.5 | $0.00005 | $0.00488 |
Grade A, and why
ad-upload scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s \ How it starts
The opening of the file, as written. The whole thing — 647 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Upload
Take the copy and images from ad-copy-generator, validate them locally, generate a dry-run payload, and only then prepare an official Ads CLI-backed upload/create flow. No copy-paste into Ads Manager. No live change without approval.
This skill handles the guarded chain: validate → dry-run artifact → creative/ad command preview → approved PAUSED create.
Read workspace/brand/ per the _vibe-system protocol if available.
Brand Memory Integration
Reads: stack.md, assets.md, learnings.md (all optional)
| File | What it provides |
|---|---|
workspace/brand/stack.md |
Stored ad account ID, default ad set IDs, target CPA |
workspace/brand/assets.md |
Index of existing creatives and their IDs |
workspace/brand/learnings.md |
Past upload patterns, what's worked |
Writes:
| File | What it contains |
|---|---|
workspace/brand/assets.md |
Appends uploaded creative IDs and ad IDs |
workspace/campaigns/{name}/ads/{creative}.upload.json |
Full API response — creative ID, ad ID, status |
Setup
Official Ads CLI auth
# System user token + ad account for official Ads CLI
export ACCESS_TOKEN="your_system_user_token"
export AD_ACCOUNT_ID="act_123456789"
# Verify CLI/auth posture
./scripts/meta-kit.sh doctor
meta ads adaccount list
Use direct Graph API only as a fallback for fields/features not yet exposed by official Ads CLI.
Store in workspace/brand/stack.md so you don't set these every time:
ad_account: act_123456789
default_adset_id: 23847293847
The Upload Chain
Every ad goes through four steps:
1. Validate copy + image
|
2. Write dry-run artifact with exact command/payload preview
|
3. Create/upload creative via official CLI where supported
|
4. Create PAUSED ad only after explicit approval
Step 1: Validate Before Uploading
Run validation before touching the API. Catch errors locally.
Copy Validation
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.
- 5d ago First seen · 647 lines · 51 tokens per session scan A ec159b972ad0
ad-upload is a skill published in the GitHub repository TheMattBerman/meta-ads-kit (311 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 4,877 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
infographic-template-updater
Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.