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-screenplaygit 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-screenplay)<a href="https://agentmods.dev/skills/epicsagas/velith/book-screenplay"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-screenplay.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01060 |
| Opus 5 | $0.00027 | $0.00530 |
| Sonnet 5 | $0.00011 | $0.00212 |
| Haiku 4.5 | $0.00005 | $0.00106 |
Grade A, and why
book-screenplay 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenplay
A screenplay is a document for collaborators, read by people who read hundreds. It must be fast, visual, and impossible to put down on page 10. Novelistic interiority does not exist here; everything the audience learns, they see or hear.
Structure
- Three acts by page: feature 90-120 pages; Act 1 to ~25, Act 2 to ~85, Act 3 to end. One page ≈ one minute.
- Eight sequences (two per act in 1 and 3, four in 2), each 12-15 pages with its own mini-arc: status quo → disruption → strategy → complication → crisis → decision → new status quo. Sequences prevent the second-act sag.
- Beat placement: inciting incident by page 10-12; first-act turn ~25; midpoint ~55 (a reversal, not an event); low point ~75; third-act turn ~85.
- TV: cold open, act breaks at commercial points (4-5 acts for network, 3 for streaming), A/B/C stories per episode, season arc bible with per-episode outlines. Pilot must establish the engine (what generates episodes forever).
- Web series: 8-15 pages per episode, hook in the first 30 seconds, cliffhanger every episode.
- Short: 5-30 pages, one turn, no subplot.
Scene
- Slug line:
INT./EXT. LOCATION - DAY/NIGHT. Location names consistent across the script (bible). - Every scene: someone wants something, something is in the way, the scene ends with the situation changed. Outcome: yes-but, no-and, no-but.
- Enter late, leave early. Cut the arrival, the greeting, the goodbye.
- Action lines: present tense, only what can be seen or heard, 3-4 lines max per paragraph, white space is pacing. No "we see." No camera directions unless writer-director.
- Character introduction: NAME in caps at first appearance, age, one telling detail. Not a paragraph of backstory.
Dialogue
- Subtext over statement. Characters talk around the thing.
- Distinct voice per character: rhythm, vocabulary, what they never say. Cover the names; the reader should still know who is speaking.
- Monologues ≤ 5 lines unless the script earns a set piece.
- Parentheticals rarely; the actor decides.
- V.O. and O.S. sparingly and consistently.
- Korean: 존댓말/반말 relationships fixed per pair in the bible; a shift is a story event. 지문 in 현재형.
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 · +53 lines · +24 tokens per session 18ff17666ae5
- 8d ago First seen · 25 lines · 30 tokens per session scan A 24978605d3ba
book-screenplay is a skill published in the GitHub repository epicsagas/Velith (33 stars, last pushed 2d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,060 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.
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.