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 design1online/author-it --skill storybuilder-scenegit clone --depth 1 https://github.com/design1online/author-itWrote 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/design1online/author-it/storybuilder-scene)<a href="https://agentmods.dev/skills/design1online/author-it/storybuilder-scene"><img src="https://agentmods.dev/badge/skills/design1online/author-it/storybuilder-scene/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/design1online/author-it/storybuilder-scene"><img src="https://agentmods.dev/badge/skills/design1online/author-it/storybuilder-scene.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 | $0.00000 | $0.00666 |
| Opus 5 | $0.00000 | $0.00333 |
| Sonnet 5 | $0.00000 | $0.00133 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
storybuilder-scene 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 10d 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.
What it actually says
Load the storybuilder-bible Prompt the user to provide the storybuilder bible or use the /storybuilder-bible skill to load the [story_bible].
Generate the scenes Prompt the user for a chapter name or chapter number [chapter] that will be used to break the outline into scenes for using the information in the [story_bible].
Given the above outline and character/worldbuilding information from the [story_bible], your task is to flesh out a “scene brief” for [chapter]. Make sure the chapter is clearly labelled with the word(s) "[chapter]". Do not name the chapter anything besides this.
This scene brief should include the following:
POV: Third person limited from the perspective of [Character Name]. Justify this choice based on emotional and narrative importance in this chapter.
Genre: [Pull this from the story_bible] Plot (Verbatim + Beats): Extract the full "[chapter]" plot summary from the outline and reproduce it verbatim in the scene brief. Then draft 20-25 scene beats to make sure you establish all of the important details of the scene. Make sure the beats focus exclusively on the plot, on what happens. Don't worry about establishing sensory details in this section.
Scene Function: Define the narrative function of this scene (e.g., Inciting Incident, Character Introduction, World Establishment, Foreshadowing Device).
Previous Chapter: Make sure the plot for this scene picks up appropriately after the end of the previous chapter text. (Disregard if this is the first chapter and there is no data for the previous chapter text).
Characters: List all characters appearing in this chapter. For each, provide: Name & Role (protagonist, antagonist, mentor, etc.) Physical Appearance: Focused on this scene — clothing, posture, visible wear, , etc. Emotional State & Goals: What they feel and want in this moment; how this affects dialogue, reactions, or inner thought. Behavioral Notes: Describe gestures, speech patterns, or tics shaped by mood or stakes.
Setting: Describe the environment using sensory-rich language. Include time of day, terrain, sounds, smells, lighting, weather, and other details relevant to the tone.
Main Source of Conflict: Explain the central dramatic tension in this chapter. Is it internal, interpersonal, societal, or environmental? Show how it escalates or shifts.
Tone & Style Notes: Guide the writing voice with specific cues: Use the “clear window” prose (simple, evocative, never ornamental). Emphasize clear magic system elements where appropriate. Ensure dialogue reflects character intention. Maintain momentum with sharp pacing and intentional foreshadowing.
Symbolism or Thematic Layer: Identify any symbols, metaphors, or archetypal moments that should emerge or be subtly introduced.
Continuity Considerations: Note any links to events from past chapters or foreshadowing for future chapters. Mention items, emotional threads, or worldbuilding that must remain consistent. Other Notes: Include worldbuilding mechanics, scene transitions, or structural devices, if any.
Important Never generate text for the user, all content must come from the user's answers or story outline/story bible content. If there isn't enough details from those to create the scene relentlessly grill the user until you can complete this scene template.
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.
- 10d ago First seen · 42 lines · 0 tokens per session scan A 8dbbdcfce719
storybuilder-scene is a skill published in the GitHub repository design1online/author-it (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 666 tokens. 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 2026-08-31.
Other skills, from other repositories
bulk-rnaseq
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and…
umap-learn
Use UMAP-learn for nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows.
esm
Use when working directly with the esm Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.
genomic-intelligence
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…