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-improvement-plangit 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-improvement-plan)<a href="https://agentmods.dev/skills/design1online/author-it/storybuilder-improvement-plan"><img src="https://agentmods.dev/badge/skills/design1online/author-it/storybuilder-improvement-plan/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-improvement-plan"><img src="https://agentmods.dev/badge/skills/design1online/author-it/storybuilder-improvement-plan.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 | $0.00838 |
| Opus 5 | $0.00000 | $0.00419 |
| Sonnet 5 | $0.00000 | $0.00168 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
storybuilder-improvement-plan 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 11d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Current Chapter Prompt the user to provide the [chapter] text or use the /storybuilder-first-draft skill if they don't have one but can provide a [story_bible] instead.
Previous Chapter Prompt the user to provide the [previous_chapter] text unless this is the first chapter.
Scene Brief Prompt the user to provide the [scene_brief] for this chapter or use the /storybuilder-scene skill to generate one if they don't have one.
Improvement Plan Given the above [chapter], I want you to critique the chapter on a line-by-line basis and find ways to improve the chapter. Give specific examples. Here are a few things to look out for: -Chapter Flow: Identify internal structure (hook, tension rise, end-of-chapter promise) -Rhythm Check: Highlight slow pacing (exposition/info-dumps). If needed, suggest scene breaks or cuts. -Show vs Tell: Highlight areas that are telling instead of showing, or not demonstrating good deep point of view for the character. Highlight exposition blocks for sensory or active-scene rewrites. -Cliches: Highlight common cliches, and over reliance on metaphors, and other signs of bad writing on the sentence level. -Adverbs: Identify any over-reliance on adverbs -Dialogue Tags: Identify dialogue tags that are not “said” or “asked”. Make suggestions for which ones should be changed to "said" or "asked". -Passive Voice: Flag instances of passive voice. -Zero Fluff: Highlight overly wordy sentences and paragraphs/areas where you could reduce fluff, as well as instances of mushy dialogue or descriptions Prose: Avoid purple sentences, keep reading level appropriate to the genre and target audience expecatations -Voice Check: Compare each major/recurring character’s dialogue and behavior against their established profile; flag off-character moments. -Voice Similarity: Flag characters that sound too similar in their voice/dialogue -Voice Remaining In Character: Flag characters that are speaking out of character ie. a soldier doesn't sound like a college professor (unless they are/were once a college professor) -Motivation Alignment: Ensure each action drives plot or character growth.", -Minor Characters: Verify new or returning townsfolk match previously defined traits or enrich them without contradiction. -Plot Holes: Things that are contradictory or don't make sense as a reader. -Open Questions: Note any unclear motives, logic gaps, or plot holes. -Repetition: Frequency of word usage, starting sentences with the same word, using the same word multiple times within a short amount of time. -Spelling Issues: Typos, missing words, incorrect tenses, noun/verb agreement, line and copy editing problems -Worldbuilding: Ideas, objects, systems, magic, etc that are not clearly explained how they work -Tension: There is a clear conflict or tension and the protagonist is actively making choices not pushed along by the plot -Internal Conflict: Must be present in the chapter -External Conflict: Should be present in the chapter, flag if missing -Ending: Did the text end where the scene brief said it should? If not, specify where the chapter should end. -Beginning: Did the text begin in a way that feels like a natural continuation from the previous_chapter_text? If not, specify how it should begin. -Reader Experience: Provide a 'Takeaway'—does the chapter leave readers eager for the next installment? Overall, your most important task is to identify these problem areas and highlight them as an issue with an explanation of why it was highlighted. The goal is to identify ways to make the writing and story content stronger. Once you’ve identified ways to do this, make a plan to improve the text. Give specific examples and recommendations on how to fix these issues. Respond to any fixes provided by the user with a new round of suggestions (if applicable).
IMPORTANT
Never change the original text. Highlight the issues, provide suggestions/examples of how they might be fixed, and leave the user to address the feedback you are providing and make a decision on how to handle it.
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.
- 11d ago First seen · 41 lines · 0 tokens per session scan A cb7b5fd7bb77
storybuilder-improvement-plan 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 838 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
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.
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…
esm
Use when working directly with the esm Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.
shap
Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global SHAP visualizations.
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.