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/adkit/ads-mcp/studionpx skills add adkit/ads-mcp --skill studiogit clone --depth 1 https://github.com/adkit/ads-mcpWhat 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 | $0.00091 | $0.00716 |
| Opus 5 | $0.00046 | $0.00358 |
| Sonnet 5 | $0.00018 | $0.00143 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
studio 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 2d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Studio — AI Creative Generation
Requires AdKit to be connected — run /ads:setup first if needed.
1. Generate images
Use adkit_studio with entity: "ads" and action: "generate". Omit id to auto-create an ad, or pass an ad ID to add variants.
adkit_studio entity: "ads" action: "generate" params: { mode: "create", aspectRatio: "1:1", instructions: "Minimal SaaS hero image, dark background" }
Generate params
| Param | Description |
|---|---|
mode |
create, clone, resize, edit (default: create) |
aspectRatio |
1:1, 16:9, 9:16 (required) |
instructions |
Generation prompt |
audience |
Target audience context |
quantity |
1-10 (default: 1) |
model |
AI model (auto-detected from project config) |
quality |
Model-specific quality setting |
colors |
Hex color array, e.g. ["#FF5733"] |
references |
Array for clone/edit/resize (see below) |
title |
Used when auto-creating ad |
Clone from library
Clone a proven competitor ad discovered via adkit_library:
adkit_studio entity: "ads" action: "generate" params: { mode: "clone", aspectRatio: "1:1", references: [{ type: "library-ad", id: "<adId>" }] }
Reference types
| Type | Use case |
|---|---|
library-ad |
Clone/edit from a library ad by ID |
media |
Reference a previously generated studio media item |
temporary_upload |
User's own file (get uploadId via action: "request_upload_url" first) |
Clone, edit, and resize each require exactly one reference.
2. Create a brief (optional)
adkit_studio entity: "ads" action: "create" params: { title: "Spring Sale Ad", specs: { format: "image", targetAudience: "SaaS founders" }, content: { headline: "20% Off", copy: "Start your free trial today" } }
3. Upload user files
Call entity: "media" action: "request_upload_url" with filename and contentType, PUT file bytes to the returned URL, then pass { type: "temporary_upload", id: "<uploadId>" } in generate references.
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.
- 2d ago First seen · 69 lines · 91 tokens per session scan A 9225c43b9dd5
studio is a skill published in the GitHub repository adkit/ads-mcp (12 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 716 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
hypd-overview
What the HYPD plugin can do — platforms, analyses and slash commands. Use when the user asks what HYPD is, what it can do, or which command fits their task.
hypd-tools
How HYPD's tools work and the invariants to respect when calling them. Load before the first HYPD tool call in a session.
hypd-getting-started
Connect HYPD and your ad accounts. Use when HYPD is not connected yet, a HYPD tool returns an authentication error, or the user asks how to set up or start using HYPD.
dcf-model
Build discounted cash flow valuation workbooks in Excel.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).