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 S3YED/appie-kit --skill ad-creative-new-backgroundsgit clone --depth 1 https://github.com/S3YED/appie-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/s3yed/appie-kit/ad-creative-new-backgrounds)<a href="https://agentmods.dev/skills/s3yed/appie-kit/ad-creative-new-backgrounds"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/ad-creative-new-backgrounds/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/s3yed/appie-kit/ad-creative-new-backgrounds"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/ad-creative-new-backgrounds.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 | $0.00093 | $0.00784 |
| Opus 5 | $0.00046 | $0.00392 |
| Sonnet 5 | $0.00019 | $0.00157 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
ad-creative-new-backgrounds 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 8d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Creative — Same Text, New Background (Prompt 3)
Part of the ad-creative-variations family. Full context: ../ad-creative-variations/SKILL.md.
When to use
- The brief from
ad-creative-analyze-winnerrecommended "USE PROMPT 3" or "USE BOTH" and the text angle was STRONG. - Never use this if the text angle was WEAK — that would copy a weak text 5 times. Run
ad-creative-fix-weak-angleinstead and route toad-creative-new-anglesonly. - Never route fresh hooks (from
ad-creative-generate-hooks) into this skill — the text here must stay 100% identical to the original.
Prerequisites
- The full brief from
ad-creative-analyze-winner, verbatim, with a STRONG text angle score. - The winning ad image again.
- The target market/language (must match the brief — the text isn't changing, but rules should still be stated explicitly).
Procedure
Based on this winning ad brief:
[PASTE HERE: full output from Prompt 1]
I will upload the winning ad as a reference image.
Keep the EXACT same text and layout as the winning ad:
* Same headline text, same font style, same position
* Keep ALL layout and text elements exactly as listed in the brief
under TEXT ELEMENTS and FORMAT
* Do NOT add layout elements that are not in the brief, and do NOT
remove elements that are in the brief
Create 5 Higgsfield (Nano Banana 2) prompts that ONLY change
the background image/scene behind the exact same text.
Each prompt must describe:
* The main subject: if the brief says there is a person, describe age,
gender, expression and pose. If the brief says there is no person,
describe the product/scene/object instead. Follow the MAIN SUBJECT
section of the brief.
* The setting/background
* The lighting and mood
* How it differs from the original while staying relevant
to the same target audience
Rules for each prompt:
* Keep all text elements 100% identical to the winning ad
* All text in [LANGUAGE/MARKET]
* Only include brand name, logo and product if they were present
in the original winning ad
* Stay relevant to the same target audience from the brief
* Each of the 5 images must feel distinctly different from each
other and from the original
* Use winning ad as reference for text placement and style
* Clean ad creative only
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.
- 8d ago First seen · 72 lines · 93 tokens per session scan A f99037f16518
ad-creative-new-backgrounds is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 16d ago), licensed MIT. It adds 93 tokens to every session and 784 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 2026-09-03.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
aws-patterns
Lambda best practices, S3 event patterns, SQS/SNS fanout, and DynamoDB access patterns for serverless AWS architectures.
review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…
agents-md-protocol
Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.
investment-memo-generator
Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.
python-memory-safe-scripts
Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloctrim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU…