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 krusemediallc/cursor-ad-agent --skill human-ad-copygit clone --depth 1 https://github.com/krusemediallc/cursor-ad-agentWrote 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/krusemediallc/cursor-ad-agent/human-ad-copy)<a href="https://agentmods.dev/skills/krusemediallc/cursor-ad-agent/human-ad-copy"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/human-ad-copy/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/krusemediallc/cursor-ad-agent/human-ad-copy"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/human-ad-copy.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 | $0.00084 | $0.01613 |
| Opus 5 | $0.00042 | $0.00807 |
| Sonnet 5 | $0.00017 | $0.00323 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
human-ad-copy 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 10d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human ad copy
Write copy that earns attention through a real observation, useful detail, or checkable claim. Do not try to "beat" AI detectors. Authorship detectors are unreliable, and no wording pattern proves who or what wrote a passage. This skill is an editorial system for removing generic patterns that readers often associate with low-effort generated copy.
Hard requirement (operator mandate): never use em dashes (—) in ad copy.
This applies to every body, title, description, hook, and draft, with no
exceptions. Rewrite with a period, comma, colon, or a split sentence. The
validator treats any em dash as a HARD failure that blocks handoff.
Required inputs
Before drafting, identify:
- Offer: product, price or terms, mechanism, and destination.
- Audience: situation, awareness level, pain, desired outcome, and objections.
- Creative: what the image or video already communicates.
- Voice: supplied brand guidance or representative approved copy.
- Receipts: verified numbers, dates, names, features, demos, quotes, results, constraints, and failures.
- Action: the one thing the reader should do.
Ask only for missing facts that materially change the copy. If a draft can
proceed with placeholders, use explicit brackets such as [verified result].
Never turn an assumption into a claim.
Workflow
1. Build a claim ledger
List each material claim and its source before writing. A receipt can be a measured result, product specification, named source, customer quote, screenshot, demo, policy, price, or dated event.
- Keep verified claims.
- Mark claims that still need evidence.
- Cut claims that cannot be checked.
- Preserve testimonials verbatim apart from approved typo fixes. Never invent a customer, quote, statistic, deadline, scarcity condition, or endorsement.
Specificity is not decoration. A precise unsupported number is still false.
2. Choose genuinely different angles
Read the 15 direct-response frameworks, then match frameworks to the available receipts and the creative. One framework is enough for one ad. A variant set should test different bets, not synonyms.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 192 lines · 84 tokens per session scan A 04acf0abfb16
human-ad-copy is a skill published in the GitHub repository krusemediallc/cursor-ad-agent (10 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,613 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
RunAPI Media Generator
A workflow for creating images, videos, music, and audio through RunAPI, a service that provides access to media-generation models. It checks the chosen model and request before submitting the job.
RunAPI Model Explorer
A RunAPI catalogue assistant that lists available AI models, explains their required inputs, and provides current pricing information.
imaginode
Generate AI images and videos through the Imaginode MCP server (imaginode.ai). Use when the user asks to create, generate or illustrate an image, picture, visual, thumbnail, or a short video clip, and the Imaginode MCP tools (generateimage, generatevideo, listmodels, getgenerationstatus) are available.
uni1-image-ad
Use when the user wants to generate a Meta/Facebook image ad with Luma uni-1 and attach it to an existing Meta ad set. Triggers on phrases like "uni-1 ad", "make a Luma ad creative", "new image ad in ", "uni-1 image ad for Meta", "generate uni-1 ad creative", "upload uni-1 image as Meta ad". Anchors on uni-1 + Meta…
image-ad-clone
Use when the user wants to reverse-engineer an existing image ad into a reusable, parameterizable prompt template that can be reused with any brand and any product. Triggers on phrases like "clone this ad as a template", "reverse engineer this ad", "turn this ad into a prompt", "extract a template from this image"…
distribea-media
Generate or place on-brand media (images, video, music, voice) with Distribea. Use whenever a project needs imagery or audio — a hero/illustration/avatar, a page full of placeholders, a video clip, background music, or a voice-over — instead of shipping stock photos, placeholders, CSS-gradient-only sections, or raw…