Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add epicsagas/Velith/plugin install 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-ideation)<a href="https://agentmods.dev/skills/epicsagas/velith/book-ideation"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-ideation.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00826 |
| Opus 5 | $0.00020 | $0.00413 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
book-ideation 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 2d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 1: Ideation
Goal: one concept the author is excited about, that a real reader would pay for, that this author can write, and that no existing book already delivers. Everything downstream inherits this decision.
Read PRD.md, STYLE.md, sources/INDEX.md, and ${CLAUDE_PLUGIN_ROOT}/skills/book-{genre}/SKILL.md.
1. Premise stress test
Before generating alternatives, interrogate what the author already has. Answer in writing:
- Why this book? What does it do that the reader cannot get elsewhere in an afternoon of searching?
- Why now? What changed in the world, the field, or the author's life that makes this timely? If nothing, that is fine, but say so.
- Why this author? What access, experience, or angle do they have? (For fiction: what obsession or wound is underneath the premise?)
- What is the reader's objection? The strongest reason a target reader would put it back on the shelf.
- Where is the book most likely to fail? Middle sag, a premise that runs out at 30%, research the author does not have, a voice that will tire.
2. Comparable titles
Research 5-8 real books the target reader has read or would consider instead. Use web search when available; otherwise rely on known titles and mark each as verified or from memory. Never invent a title, author, or sales figure. For each comp: title, author, year, what it does well, what it leaves undone, how this book differs. Write the matrix into ideation.md.
For Korean-market books, include domestic comps (교보/예스24/알라딘 bestseller lists, 밀리의 서재 trends) and translated comps separately.
3. Concept generation
Generate 5-10 concepts. Concepts are angles on the premise, not random alternatives. Each:
- Elevator pitch (two sentences, no adjectives doing the work)
- Reader promise (what they have at the end)
- The first chapter in one paragraph (this exposes weak concepts fast)
- Differentiation against the comps
- What the author would need to research or invent
- Risk (one line)
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.
- 2d ago Changed · +37 lines · +15 tokens per session b3ec912d0f85
- 8d ago First seen · 28 lines · 26 tokens per session scan A e5dada6840cd
book-ideation is a skill published in the GitHub repository epicsagas/Velith (33 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 826 once invoked, about $0.0002 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.
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…
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.
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.