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 MoizIbnYousaf/marketing-cli --skill image-gengit clone --depth 1 https://github.com/MoizIbnYousaf/marketing-cliWrote 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/moizibnyousaf/marketing-cli/image-gen)<a href="https://agentmods.dev/skills/moizibnyousaf/marketing-cli/image-gen"><img src="https://agentmods.dev/badge/skills/moizibnyousaf/marketing-cli/image-gen.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 System Prompt Leakage · line 134 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00167 | $0.02765 |
| Opus 5 | $0.00084 | $0.01383 |
| Sonnet 5 | $0.00033 | $0.00553 |
| Haiku 4.5 | $0.00017 | $0.00277 |
Grade A, and why
image-gen 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/image-gen — On-Brand Image Generation
Describe what you need. Get an image that looks like your brand made it.
This skill reads your visual brand identity from brand/creative-kit.md, crafts a narrative prompt that bakes in your style constraints, and generates the image via Gemini API. No brand style defined yet? It still works — just at a lower enhancement level. Run /visual-style first for the best results.
On Activation
-
Check
GEMINI_API_KEYenvironment variable.- If missing: "Image generation requires a Gemini API key. Set GEMINI_API_KEY in your environment. Get one at ai.google.dev."
- Do not proceed without it.
-
Read brand files in priority order:
brand/creative-kit.md— look for## Visual Brand Stylesectionbrand/voice-profile.md— personality informs image tonebrand/positioning.md— angles inform visual metaphorsbrand/landscape.md— Claims Blacklist (don't generate imagery that visually implies blacklisted claims)
-
Determine enhancement level:
| Level | Context available | Image quality |
|---|---|---|
| L0 | No brand files | Good generic images — uses discovery questions + prompt craft |
| L1 | voice-profile.md | Personality-aligned — playful brand gets warm/bright images |
| L2 | + creative-kit.md colors/typography | Color-constrained — palette woven into prompts |
| L3 | + Visual Brand Style section | Fully on-brand — style anchors, lighting, mood, composition all applied |
Phase 1: Discovery
Use AskUserQuestion. Ask one at a time. Skip questions the user already answered in their request.
Question 1: Purpose "What's this image for?"
- Blog header / article illustration
- Social media post (which platform?)
- Product shot / marketing asset
- Hero image / landing page
- Presentation / slide deck
- Something else (describe it)
This determines aspect ratio:
| Use case | Default ratio | Resolution |
|---|---|---|
| Blog header | 16:9 | 2K |
| Social square | 1:1 | 2K |
| Social story | 9:16 | 2K |
| Hero / banner | 21:9 | 2K |
| Product shot | 4:3 | 4K |
| Thumbnail | 16:9 | 1K |
What ships with it
2 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.
- 8d ago First seen · 278 lines · 167 tokens per session scan A db6ab14ef701
image-gen is a skill published in the GitHub repository MoizIbnYousaf/marketing-cli (31 stars, last pushed 22d ago), licensed MIT. It adds 167 tokens to every session and 2,765 once invoked, about $0.0008 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
ads-generate
Generate paid-ad image assets from a validated creative brief and brand profile using an explicitly configured image provider. Triggers on: generate ads, generate ad images, create ad creatives, create ad images, make ad images, generate visuals, make campaign visuals, generate images from campaign brief.
ads-create
Create source-grounded paid-ad campaign concepts, messaging, copy, creative briefs, and production plans from a validated brand profile, campaign objective, platform requirements, and optional audit evidence. Triggers on: campaign brief, campaign concepts, create a campaign, ad concepts, ad copy, ad messaging…
ads-creative
Audit paid-ad copy, images, video, hooks, concepts, format coverage, platform-native fit, message match, creative fatigue, accessibility, and policy across supported platforms. Use for creative audit, ad creative, creative fatigue, creative diversity, ad copy review, video review, image review, or production…
ads-photoshoot
Generate rights-cleared paid-ad product photography variants from an authorized source image and validated brand profile. Triggers on: product photo, product photography, virtual photoshoot, photoshoot, enhance product image, studio shot, lifestyle shot, lifestyle product image, floating product image, ingredient shot.
instagram-marketing
Plan, draft, audit, and publish content for Instagram. Use when the user wants to write a caption with a first-125-char hook, plan a slide-by-slide carousel, reverse-engineer the hook from a viral Reel or carousel, size hashtags the 2026 way, remove AI tells from a caption, or plan a week of Reels and carousels.…
tt-humanizer
Remove the AI-script tells viewers hear in a TikTok spoken script and caption: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity, written-not-spoken phrasing, "hey guys" filler; caps em dashes. Includes --mode audit pre-film check (hook, completion design, caption fit)…