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-outline)<a href="https://agentmods.dev/skills/epicsagas/velith/book-outline"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-outline/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-outline"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-outline.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 | $0.00038 | $0.01213 |
| Opus 5 | $0.00019 | $0.00607 |
| Sonnet 5 | $0.00008 | $0.00243 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
book-outline 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 2: Outlining
Goal: an outline detailed enough that each chapter can be drafted in full context without inventing structure, and a bible that keeps twenty chapters telling one story or making one argument.
Read PRD.md, STYLE.md, ideation.md, sources/INDEX.md, the genre skill, and ${CLAUDE_PLUGIN_ROOT}/skills/loom/quality-bar.md.
Process
- Invoke
book-architectwith the project directory. It producesoutline.md(draft) andbible.md(initial), then validates its own structure and writes the score and issues intooutline.md's## Validationsection. - Review the validation. If the score is below 8/10 or any Critical issue remains, have book-architect revise once. If still below, surface the issues to the author instead of iterating blindly.
- Author checkpoint. Present: the structural shape (one paragraph), the chapter list with one-line purposes, the pacing map, the top three risks the architect flagged, and the bible summary. Ask for approval or changes. Required stop.
- On approval, add
## Approvaltooutline.mdwith the date and any author notes. The router treats an outline without this section as unapproved.
What a chapter spec must contain
The chapter-writer will draft from this spec plus the full manuscript so far. Anything missing here gets invented inconsistently. Per chapter:
- Title (working) and slug
- Purpose — what this chapter changes for the reader. If two chapters have the same purpose, one is redundant.
- Entry state — where the reader (and, for fiction, the protagonist) is at the start: what they know, want, fear, believe
- Exit state — same, at the end. The delta is the chapter.
- Pull — the question or tension that carries the reader through this chapter
- Content — for fiction: 2-5 scene seeds (situation, turn, what is at stake); for nonfiction: the claims made, evidence used (source IDs), the example or story that anchors it; for technical: concepts, the code artifact built, the failure shown
- Sets up / pays off — references to other chapters by number
- Must not — repetitions to avoid, things the reader must not learn yet, tonal limits
- Length target and difficulty (nonfiction/technical)
- Sources — IDs from
sources/INDEX.md
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 · +43 lines · +10 tokens per session 6cd8d314b918
- 9d ago First seen · 31 lines · 28 tokens per session scan A fddadefe5136
book-outline is a skill published in the GitHub repository epicsagas/Velith (34 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,213 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.
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.