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-nonfictiongit 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-nonfiction)<a href="https://agentmods.dev/skills/epicsagas/velith/book-nonfiction"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-nonfiction/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-nonfiction"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-nonfiction.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 | $0.00050 | $0.01515 |
| Opus 5 | $0.00025 | $0.00758 |
| Sonnet 5 | $0.00010 | $0.00303 |
| Haiku 4.5 | $0.00005 | $0.00152 |
Grade A, and why
book-nonfiction 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 7d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nonfiction
The reader of nonfiction wants one of three things: to understand something they did not, to be able to do something they could not, or to have lived through something they never will. Decide which this book delivers (or which mix) in PRD.md, and let that decide the structure. A how-to book with the structure of a memoir fails both.
Structure options
- Problem → Principles → Practice → Advanced — the default for practical nonfiction. Reader arrives with a pain, leaves with a method.
- Narrative spine with argument chapters — a story runs through the book (a case, a person, a year) and argument chapters hang off it. Best for big-idea books.
- Question-driven — each chapter is a question the previous chapter raised. Best for explanatory nonfiction.
- Chronological — history, memoir, biography. Risk: "and then" pacing; fix by organizing around turning points, not dates.
- Thematic essays — a collection unified by voice and subject. Each essay stands alone; the order builds.
- Framework — one model, one chapter per component. Risk: framework inflation; only if the framework is genuinely the book's contribution.
Whatever the shape: the introduction earns the reader's next hour by naming the pain and the promise; chapter 1 delivers something usable; the middle escalates from simple to hard, not from topic to topic; the ending returns to the promise and shows it kept.
Argument
Every chapter has one claim the reader could disagree with. If they cannot disagree, it is not a claim, it is a topic.
- Claim → evidence → warrant → objection → answer. The objection is the strongest one a smart skeptic would raise, not a straw one.
- Confidence signaling. Mark what is settled, what is contested, and what is the author's speculation. Uniform confidence is a tell and a liability.
- One recurring example carried across chapters beats a new example every paragraph. The reader builds a mental model of it.
- Abstraction ladder. Every abstract paragraph is followed by a concrete one. Never two abstractions in a row.
- Cut the preview and the recap. Chapter titles and transitions do that work.
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.
- 7d ago Changed · +70 lines · +24 tokens per session dbc8be01274c
- 12d ago First seen · 19 lines · 26 tokens per session scan A 2e0f1e15337e
book-nonfiction is a skill published in the GitHub repository epicsagas/Velith (35 stars, last pushed 7d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,515 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.
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.
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.
skill-competitor-analysis
A research process for studying how competing social-media accounts choose topics, format posts, publish, and engage with followers. It turns publicly available competitor activity into a content-strategy report.