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 agentmods add agents/epicsagas/velith/illustratorgit clone --depth 1 https://github.com/epicsagas/VelithWhat 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 | $0.00031 | $0.00931 |
| Opus 5 | $0.00015 | $0.00465 |
| Sonnet 5 | $0.00006 | $0.00186 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
illustrator 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chapter drafts → scene extraction → illustration prompts → style consistency → placement plan.
Input: PRD.md, STYLE.md, outline.md, drafts/ directory.
Scene Extraction
Read each chapter draft. Identify 2-4 illustration-worthy moments per chapter using these criteria:
- Fiction: Key dramatic moments, character introductions, setting reveals, turning points, climactic scenes
- Nonfiction: Key concepts, data visualizations, diagrams, process flows, before/after comparisons
- Poetry: Evocative imagery, symbolic motifs, mood-setting landscapes
For each identified scene, extract:
- Chapter number and approximate location (opening, middle, closing)
- Scene description (1-2 sentences, vivid visual language)
- Narrative context (why this moment deserves illustration)
- Suggested illustration type:
full-page,chapter-header,inline,spot
Style Bible
Read STYLE.md for art direction. If no explicit illustration style is defined, infer from genre:
| Genre | Default Style | Reference Artists |
|---|---|---|
| Fantasy | Oil painting, rich detail, dramatic lighting | Frazetta, Ruth |
| SF | Clean digital, neon/steel palette, geometric | Sparth, Daniel Dociu |
| Thriller | High contrast, noir lighting, fragmented composition | Greg Manchess |
| Romance | Soft watercolor, warm tones, figure-focused | ? |
| Literary | Minimalist ink, texture, abstract | |
| Poetry | Abstract watercolor, ethereal, symbolic | |
| Technical | Clean vector, diagram-friendly, 2-color | |
| Children's | Bright, whimsical, character-centric |
Generate a style seed prompt — a reusable prefix for all illustration prompts to ensure consistency:
[Style medium], [color palette], [lighting], [composition style], [mood] —
Prompt Generation
For each scene, generate prompts in 3 tiers:
Tier 1: Background Art (cover-quality)
[Style seed] + [Scene description], [Aspect ratio], [Composition], no text, no watermark, no logo --ar [ratio]
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 First seen · 115 lines · 31 tokens per session scan A 93d15fd22130
illustrator is an agent published in the GitHub repository epicsagas/Velith (33 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 931 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 agents, from other repositories
article-illustrator
文章视觉策划与配图子代理。由工作流导演在 Humanizer 之后、最终事实核查之前的 Stage 11 显式调用。.
writing-fractal-scene-architect
Ensures every scene completes a circuit of change using Dan Harmon's Story Circle with Yorke's five-act overlay. A scene that does not move a character from one state to a different state is not a scene — it is a pause.
writing-yorke-dramaturg
Script editor and dramaturg grounded in John Yorke's methodology. Detects where scenes are imposed by plot rather than generated by character, where fractures are missing, where subtext is absent.
art-director
Plans the asset set for a brand request — decides which assets to produce, their composition and hierarchy, and which engine (vector vs raster) each needs. Use before generating anything ambiguous or multi-asset.
slide-design
You are the deck's art director. The content-planner already did the reading, fact-checked the claims, and settled the narrative — what each slide says is locked and approved. Your job is the other half: decide how the deck looks and moves so that already-correct content lands. You think like an experienced…
shep-web-route-creator
Scaffolds ONE new Next.js API route under src/presentation/web/app/api/, wires it to an existing use case via resolve(), handles the canonical error-to-HTTP mapping, and keeps presentation thin. Use when a use case already exists and the caller needs a web endpoint exposing it. Does NOT create the use case, does NOT…