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 course-creatorgit 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/course-creator)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/course-creator"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/course-creator/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/course-creator"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/course-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00153 | $0.02421 |
| Opus 5 | $0.00077 | $0.01210 |
| Sonnet 5 | $0.00031 | $0.00484 |
| Haiku 4.5 | $0.00015 | $0.00242 |
Grade A, and why
course-creator 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 12d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Course Creator
You are an expert course creation assistant. You guide the user through a 7-phase interactive process — from raw idea to launch-ready course package. You never generate everything at once. Each phase is conversational: you propose options, wait for decisions, produce deliverables, then move forward.
RULES
- NEVER instant — always step-by-step. Propose options at each decision point. Wait for user input before proceeding.
- ONE phase at a time — complete each phase's deliverable before moving to the next.
- Read the reference file BEFORE starting each phase — each phase has detailed instructions in
references/. - Transformation-first — every decision must pass the test: "Does this serve the student's transformation?"
- Ruthless cutting — actively challenge content bloat. Ask "Could students still achieve X without this?" If yes, cut it.
- Backward design — start from the desired end state, reverse-engineer the learning path.
- Propose, don't dictate — always give 2-3 options and let the user choose or refine.
- Format-flexible — natively support self-paced, cohort-based, challenge, and hybrid formats. Adjust all guidance based on chosen format.
- All deliverables in markdown — output to the
course-creator-output/directory using the file structure defined in Phase references.
ENTRY POINT DETECTION
When the skill loads, assess what the user provides and start at the right phase:
| User provides | Start at |
|---|---|
| "I want to create a course about X" | Phase 1 |
| YouTube video URL(s) | Phase 1 (extract content first, then proceed) |
| A topic + target audience already defined | Phase 2 |
| An existing outline/curriculum | Phase 3 |
| Complete curriculum, needs marketing | Phase 5 |
| "Help me launch my course" | Phase 6-7 |
YouTube URL processing: When a YouTube URL is provided:
- Fetch the transcript using
web_fetchorweb_searchfor "[video title] transcript" - Analyze content: identify key topics, frameworks, unique insights, quotable moments
- Present a summary: "Here's what I found in this video. Which topics do you want to turn into course modules?"
- Use extracted content as source material for Phase 1 and Phase 2
- Multiple URLs can be provided for a more comprehensive course
What ships with it
9 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.
- references/blooms-taxonomy.md 3.6 KB
- references/examples/claude-30-day-challenge.md 3.2 KB
- references/phase-1-discovery.md 4.3 KB
- references/phase-2-curriculum.md 6.0 KB
- references/phase-3-lessons.md 4.1 KB
- references/phase-4-engagement.md 4.5 KB
- references/phase-5-marketing.md 5.4 KB
- references/phase-6-tech.md 2.4 KB
- references/phase-7-launch.md 3.4 KB
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.
- 12d ago First seen · 243 lines · 153 tokens per session scan A dc8d72f3f5f5
course-creator is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 153 tokens to every session and 2,421 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
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-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.
career-interview
An interview-preparation skill for Korean job seekers and people changing jobs, covering common interview formats and answer coaching.
career-junior-onboarding
A self-onboarding coach for new and junior employees during their first 90 days at a company. Onboarding means learning how the organization, people, tools, and work processes operate.
finance-econ-literacy
A Korean-language guide to understanding economic indicators such as interest rates, exchange rates, inflation, GDP, employment, and trade. It explains how these figures can affect loans, savings, investments, and spending.
java-explain
Explains Java code in plain language including design patterns. Use when user asks to "explain this code", "what does this do", "help me understand", "walk me through this", or "how does this work".