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 epicsagas/Velith --skill book-fictiongit clone --depth 1 https://github.com/epicsagas/VelithWrote 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/epicsagas/velith/book-fiction)<a href="https://agentmods.dev/skills/epicsagas/velith/book-fiction"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-fiction/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/epicsagas/velith/book-fiction"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-fiction.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 | $0.00057 | $0.01866 |
| Opus 5 | $0.00028 | $0.00933 |
| Sonnet 5 | $0.00011 | $0.00373 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
book-fiction 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 4d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fiction
The reader of a novel is not looking for a well-structured story. They are looking for the experience of being inside someone else's consequential life. Structure is how you keep them there. This file is craft, not a template.
Structure: choose, do not apply
Pick the shape that fits the premise and say why in outline.md. Options:
- Three-act (setup 25% / confrontation 50% / resolution 25%). Midpoint reversal. Works for almost everything; risk is a flat second act.
- Save the Cat 15-beat (Opening Image → Theme Stated → Setup → Catalyst 10% → Debate → Break into Two 20% → B Story → Fun and Games → Midpoint 50% → Bad Guys Close In → All Is Lost 75% → Dark Night → Break into Three 80% → Finale → Final Image). Best for commercial genre fiction. Risk: fifteen equal-sized chapters that feel engineered.
- Hero's Journey (12 stages). Best for quest and coming-of-age. Risk: mentor and threshold scenes that feel obligatory.
- Story Grid / five commandments per scene (inciting incident, progressive complication, crisis, climax, resolution) applied at scene, sequence, act, and global level. Best for making every unit turn.
- Snowflake for planning: one sentence → paragraph → character summaries → expand. A planning method, not a book shape.
- Bespoke: braided timelines, epistolary, nested frames, reverse chronology. Only when the premise demands it and the author agrees.
Whatever the shape: the inciting incident is inside the first 10-12% or the reader leaves; the midpoint changes what the protagonist wants or believes, not just what happens; the ending is caused by a choice the protagonist could only make after everything that came before.
Subplots carry theme or contrast. Each needs its own small arc and must converge with the main line by the third act or be cut.
POV plan in the outline: whose head, what distance, which chapters. Do not change the plan mid-draft without updating the bible.
Scene design
A scene is a unit where something changes. If nothing changes, it is not a scene; cut it or merge 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.
- 4d ago Changed · +82 lines · +26 tokens per session 6094ce1e0597
- 10d ago First seen · 21 lines · 31 tokens per session scan A 484a64d6b3f1
book-fiction is a skill published in the GitHub repository epicsagas/Velith (34 stars, last pushed 4d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,866 once invoked, about $0.0003 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
ai-native-software-dev
Use when the user asks to build, change, modernize, or reconstruct non-trivial software with an AI-native workflow, including greenfield development, work in an existing codebase, or authorized reference-based product reconstruction; also use when lifecycle planning, architecture, implementation, testing, review…
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
short-drama
A production workflow for making multi-episode AI short dramas, covering story planning, character consistency, scripts, generated video shots, voices, sound, subtitles, and final assembly.
paper-explainer
A research-content workflow that turns an arXiv paper or a local PDF into an explanation for a video or written article. arXiv is a public online archive of research papers.
open-ontologies
AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
multi-voice-dubbing
A script-to-audio workflow that gives different characters different voices and emotions, then combines their lines into one audio track with subtitles naming each speaker.