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 naveedharri/benai-skills --skill visualgit clone --depth 1 https://github.com/naveedharri/benai-skillsWrote 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/naveedharri/benai-skills/visual)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/visual"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/visual/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/naveedharri/benai-skills/visual"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/visual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, 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 Privilege Escalation · line 40 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 41 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 15 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 292 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 76 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00092 | $0.03493 |
| Opus 5 | $0.00046 | $0.01747 |
| Sonnet 5 | $0.00018 | $0.00699 |
| Haiku 4.5 | $0.00009 | $0.00349 |
Grade A, and why
visual scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infographic Generator
Create professional infographics in the BenAI brand style for LinkedIn and newsletters. Uses Gemini AI via the Nano Banana MCP server for image generation.
Connector: Nano Banana MCP (Gemini AI image generation).
Core rule: Quality is set by the thinking BEFORE the prompt. Spend 70% of effort on what to visualize, 30% on how.
UX rule: When the AI can make a good default, make it silently and let the user override. Never ask the user to confirm something the AI already decided.
Files load lazily, one phase at a time. Do NOT load reference files up front. See the Reference File Load Map at the bottom.
When This Skill Loads
- Run Phase 0 (silent config check).
- If the API key is NOT configured: jump to Phase 5-ALT (API Key Setup). Do NOT ask about content.
- If the API key IS configured: begin Phase 1.
UNDERSTAND
Phase 0: Silent Config Check
Run silently. No questions yet.
mkdir -p .infographic/images .infographic/prompts
if [ -n "$GEMINI_API_KEY" ]; then
echo "API key found in environment"
elif [ -f .env ] && grep -q "^GEMINI_API_KEY=.\+" .env; then
echo "API key found in .env file"
else
echo "API key not configured"
fi
- Key found (env var OR .env): proceed to Phase 1.
- Key NOT found: jump to Phase 5-ALT.
Then check for brand config (first found wins): ./branding.md, then .infographic/brand.md. If found, cat it and acknowledge briefly ("Found your brand context, ready to create."). branding.md is written by the /ads-creative skill (colors, fonts, voice, audience); use it for on-brand palettes, typography, and style anchors.
Phase 1: Content Intake
No reference files. No AskUserQuestion. Say:
"What content should I turn into an infographic? Paste text, share a URL, or point me to a file."
Acknowledge receipt briefly, then go to Phase 2.
Phase 2: Analysis + First Choices
>>> READ references/content-analysis.md NOW
2.1: Four-Layer Analysis
What ships with it
6 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.
- 3d ago First seen · 306 lines · 0 tokens per session scan A 498954a5dd51
visual is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 3,493 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 2026-09-05.
Other skills, from other repositories
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
media-audio-gen
An audio-generation skill for turning text into speech, cloning a voice from a sample, dubbing videos into other languages, and creating sound effects.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.
media-higgsfield-identity
A Higgsfield workflow for keeping a person, character, product, or other visual reference consistent across generated images. It chooses between a trained identity model and a one-image reference method.
media-notebooklm-slide-prompt
A prompt builder that turns lecture, class, or seminar notes into instructions for NotebookLM Studio to create slides. It also creates image prompts for each slide using Nano Banana, Google's image-generation model.
media-gpt-image-2-prompt
A prompt builder for GPT-image-2, an OpenAI image-generation model. It turns a short request into six sections covering the subject, action, scene, composition, lighting, style, and text limits.