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 alecs5am/ralphy --skill storyboard-cheatcodegit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/alecs5am/ralphy/storyboard-cheatcode)<a href="https://agentmods.dev/skills/alecs5am/ralphy/storyboard-cheatcode"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/storyboard-cheatcode/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/alecs5am/ralphy/storyboard-cheatcode"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/storyboard-cheatcode.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 | $0.00086 | $0.01850 |
| Opus 5.5 | $0.00034 | $0.00740 |
| Sonnet 5.5 | $0.00017 | $0.00370 |
| Haiku 4.5 | $0.00009 | $0.00185 |
Grade A, and why
storyboard-cheatcode 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 1mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storyboard Cheatcode
name: storyboard-cheatcode description: Turn a one-line concept into a multi-panel previs storyboard image, then optionally a cheap-preview video and a hero video render. Uses the Higgsfield MCP server (image and video tools). Asks the user before every render and never assumes budget tolerance. Use when the user asks to build a storyboard, plan AI video shots, generate a previs sheet, or wants an AI video from a concept. storyboard-cheatcode A previs-first AI-video pipeline. You generate a multi-panel storyboard image, then offer escalating render tiers — cheap preview first, hero render only on confirmation. All generation runs through the Higgsfield MCP server.
Operating principle — always ask, never guess Every step begins by asking the user. Do not pre-fill creative choices, do not infer budget tolerance, do not chain steps without explicit confirmation.
Renders cost real credits (~7 per storyboard image, ~50–70 per 12s 720p Seedance clip). The user is the creative director; you are the operator. Iterating cheaply on the storyboard image before any video render is the single biggest cost saver. Prerequisite The user must have the Higgsfield MCP connector added to Claude. If the Higgsfield tools (e.g. higgsfield_generate_image, higgsfield_generate_video) are not available in this session, stop and tell the user:
Add the Higgsfield connector first: Settings → Connectors → Add custom MCP → URL: https://mcp.higgsfield.ai/mcp. Sign in with your Higgsfield account when prompted.
Then re-run the skill.
Step 1 — Collect inputs (one batched ask) Ask the user for all of these in a single message. Do not ask one at a time. Mark each clearly:
- CONCEPT — one sentence describing the scene or sequence
- ASPECT RATIO — 16:9 (default), 9:16, or 1:1
- NUMBER OF PANELS — 4, 6 (default), or 9
- PANEL ART STYLE — photoreal cinematic (default), manga, noir ink, hand-drawn storyboard, Pixar warmth, or your own
- FACE / CHARACTER REFERENCE — image URL or uploaded image (or "none")
- PRODUCT / OBJECT REFERENCE — image URL or uploaded image (or "none")
- HARD NEGATIVES — anything that must NOT appear (e.g. "no weapons", "no on-screen text") When their answers come back, echo a one-line plan summary and ask explicitly: "Ready to generate the storyboard sheet?" Do not proceed without a yes.
Step 2 — Generate the storyboard sheet Build a single prompt that:
Names the grid explicitly: "A {N}-panel storyboard previs sheet, laid out as a {rows}×{cols} grid on a black background with thin white panel borders. Each panel labeled in clean white sans-serif text in the bottom-left corner ('SHOT 1' through 'SHOT {N}') with a short scene title." Describes each panel in 1–2 sentences. Always include the camera angle per panel (wide establishing / medium / close-up / low hero angle / over-shoulder / etc). Lists negatives under a HARD RULES: block, spelled out explicitly. Ends with: "ONE single image — the entire {N}-panel sheet in one composition, {aspect}. Each panel {style}." Call the Higgsfield MCP image tool. Use gpt_image_2 as the model (best for grids, text, detail). Pass any provided reference images.
higgsfield_generate_image( model = "gpt_image_2", prompt = "", aspect_ratio = "", resolution = "2k", quality = "high", reference_images = [, ] ) The MCP returns a job_id. Immediately call higgsfield_wait_for_job(job_id) and wait for the result URL.
Show the resulting image to the user. Then ask:
- Regenerate with feedback (tell me what to change)
- Generate an end-frame anchor (lock the final shot of the video)
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.
- 1mo ago First seen · 119 lines · 86 tokens per session scan A 91ed2b9598e3
storyboard-cheatcode is a skill published in the GitHub repository alecs5am/ralphy (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,850 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
geo-database
Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.