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-academicgit 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-academic)<a href="https://agentmods.dev/skills/epicsagas/velith/book-academic"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-academic/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-academic"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-academic.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 | $0.00055 | $0.01102 |
| Opus 5 | $0.00028 | $0.00551 |
| Sonnet 5 | $0.00011 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
book-academic 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 3d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic
The reader is a peer or an examiner. They will check the citations, and they will notice when the literature review summarizes instead of argues. Academic AI text fails by being fluent about things it has not read.
Structure by discipline
- Sciences: IMRAD (Introduction → Methods → Results → Discussion), plus Abstract, References, Appendices.
- Social sciences: Introduction → Literature review → Theoretical framework → Methods → Findings → Discussion → Conclusion.
- Humanities: Thesis → evidence chapters (each an argument, not a topic) → synthesis → conclusion.
- Thesis/dissertation: as above with committee and program requirements from
PRD.mdoverriding defaults (chapter count, word limits, citation style, formatting). - Monograph: like humanities but with a stronger narrative spine and less methodological apparatus.
Literature review
Organize by theme and argument, never chronologically and never author-by-author. Establish the field → identify the gap → position this work. For each source: claim, method, limitation, relevance to this work. Build a synthesis matrix (themes × sources) in sources/INDEX.md before drafting. The review argues that the gap exists; it does not list what people have said.
Argument
Toulmin: claim → evidence → warrant → backing → qualifier → rebuttal. Every chapter thesis supports the central thesis, and the chapter's opening states its claim, position, and scope. Paragraph: topic sentence (claim) → evidence and analysis → link. Hedging is calibrated, not stacked: "may suggest" is fine; "it could perhaps be argued that it may" is not.
Citation integrity
- Every citation refers to a real work the author has (or the fact-checker has verified exists) with the correct authors, year, title, venue, and page range. A fabricated or misattributed citation is a Critical defect; the fact-checker removes it.
- Drafts cite inline with source IDs (
[S12, p. 45]); copy edit converts to the house style (APA 7, MLA 9, Chicago 17, IEEE, or the program's own). - Direct quotes ≤ 40 words inline, longer as block quotes, always with page numbers.
- Paraphrase must change structure, not only vocabulary.
- Citation density: heavy in the review, light in methods and results, moderate in discussion.
- Self-citation disclosed; retracted works not cited; preprints marked.
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.
- 3d ago Changed · +36 lines · +29 tokens per session 4f583661eced
- 8d ago First seen · 31 lines · 26 tokens per session scan A 3d2ba7402a9b
book-academic is a skill published in the GitHub repository epicsagas/Velith (33 stars, last pushed 3d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,102 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.
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.
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.