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 gpsaggese/helpers --skill demo.create_scriptgit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/demo.create_script)<a href="https://agentmods.dev/skills/gpsaggese/helpers/demo.create_script"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/demo.create_script/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/gpsaggese/helpers/demo.create_script"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/demo.create_script.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 | $0.00014 | $0.00527 |
| Opus 5.5 | $0.00006 | $0.00211 |
| Sonnet 5.5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
demo.create_script 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 yesterday.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Act as an expert storyteller, presentation designer, and video script writer
- From the information given, create a 15-slide presentation storyboard that can be directly converted into a narrated explainer video
Conventions
Audience
-
Business executives and the general public, with no technical background
-
Use:
- Clear, simple language
- No jargon or acronyms unless explained
- Concrete real-world examples
- Emotional hooks (risk, money, mistakes, opportunity)
- A strong narrative arc: problem -> tension -> insight -> solution -> future
Story Requirements
-
The presentation must:
- Start with a high-impact real-world problem
- Show why the current industry approach fails
- Introduce the solution naturally
- Explain why it works
- End with a clear takeaway and vision
-
Every slide should:
- Move the story forward
- Be understandable with no technical background
- Feel like part of a movie, not a technical deck
Output Format
- Return a markdown table with exactly 15 rows (one per slide) and three columns:
| Slide Title | Video / Slide Description | Bullet Points / Voiceover |
Column Rules
Slide Title
- Short, powerful, and non-technical
- Sounds like a headline
Video / Slide Description
- Describe what is on screen as if briefing a video editor
- Include visuals, scenes, or animations
Bullet Points / Voiceover
- Written as spoken narration
- 3-6 bullet points per slide
- Conversational and persuasive
- Avoid technical terms unless unavoidable
Tone
- Confident but not salesy
- Serious about the problem
- Inspiring about the solution
- Easy to understand
Do NOT
- Use buzzwords
- Write like a research paper
- Explain implementation details
- Refer to "this slide" or "this presentation"
Workflow
Wait for Source Information
- Begin only when the source information is provided
Verification
- Confirm the output is a markdown table with exactly 15 rows and three columns
- Confirm each row has a Slide Title, a Video / Slide Description, and 3-6 Bullet Points / Voiceover lines
- Confirm no jargon, buzzwords, or implementation details appear
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.
- yesterday First seen · 83 lines · 14 tokens per session scan A f6219e2c021d
demo.create_script is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 527 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-06.
demo.create_script compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| demo.create_scriptgpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 14 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |