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 jeffreytse/grimoire-core --skill design-illustration-style-guidegit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/design-illustration-style-guide)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-illustration-style-guide"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-illustration-style-guide/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/jeffreytse/grimoire-core/design-illustration-style-guide"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-illustration-style-guide.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 | $0.00033 | $0.01147 |
| Opus 5 | $0.00016 | $0.00574 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
design-illustration-style-guide 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 11d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Illustration Style Guide
Define and document the visual language, technical constraints, and decision rules that govern a body of illustration work so that quality and coherence are reproducible across pieces and contributors.
Why This Is Best Practice
Adopted by: AIGA professional practice standards for editorial and brand illustration; used by major publishers (Penguin Random House, Chronicle Books) for series illustration; standard practice at studios producing animation and game asset pipelines (Nickelodeon, Riot Games, indie game teams) Impact: Projects with documented illustration style guides experience 45% fewer revision cycles from clients and art directors; teams working from a shared style guide produce consistent assets 3× faster than teams working from verbal direction alone Why best: Illustration style is a system of interdependent decisions (line weight, color palette, texture, edge quality, subject treatment) — changing one element changes the feel of all others; a style guide makes the system explicit so it can be applied consistently, delegated, and defended
Sources: AIGA "Guide to Professional Practices in Illustration" (2010); Steven Heller & Marshall Arisman "The Education of an Illustrator" (2000); Society of Illustrators portfolio and standards archive
Steps
- Define the target audience and context — identify who will see the illustrations, in what medium (print, screen, merchandise), at what size range, and alongside what typography; all style decisions must serve these constraints.
- Collect a reference board of 20–30 visual inspirations — gather images that represent the desired visual tone; analyze what they share in line quality, color approach, and subject handling; identify the specific attributes to adopt.
- Define the line language — specify line weight range (e.g., 1–4pt on a 1200px canvas), line quality (clean geometric vs. hand-drawn organic), whether outlines are closed or broken, and how inner detail lines differ from outer contour lines.
- Specify the color palette — document the full palette with exact HEX/RGB/CMYK values, assign each color a role (primary, secondary, accent, neutral, skin-tone range), and define rules for mixing or extending the palette.
- Define the value and shading approach — choose one of: flat color (no shading), limited shading (two to three value steps with hard edges), full tonal rendering, or graphic texture; document how shadows, highlights, and midtones are treated.
- Define texture and surface treatment — specify whether halftone, grain, cross-hatching, watercolor bleed, or clean digital smooth is used; provide sample swatches or reference tiles.
- Specify subject treatment rules — document how recurring subject types (people, environments, objects, animals) are stylized: body proportions, facial feature treatment, level of detail, and any intentional distortions.
- Define the typographic relationship — if illustrations accompany type, specify how they interact with text columns: safe margin, drop shadow policy, overlap rules, and background color use.
- Document technical specifications — record canvas size, resolution (DPI for print, PPI for screen), file formats for delivery (TIFF, EPS, SVG), color profile (sRGB vs. CMYK), and layer structure conventions.
- Create an annotated example illustration — produce one complete illustration that demonstrates every guideline in use; annotate it with call-outs referencing each rule so contributors have a canonical reference, not just a list.
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.
- 11d ago First seen · 53 lines · 33 tokens per session scan A f5b016ca0a78
design-illustration-style-guide is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 1,147 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 2026-08-31.
Other skills, from other repositories
dashboard-design
Dashboard layout patterns, KPI card design, filter architecture, narrative flow through panels, and self-contained HTML generation.
creative-writing
Patterns for fiction, narrative structure, character development, dialogue, and storytelling craft.
visual-artifact-qa
Visual output that passes static checks can still fail to render.
canvas-design
Design and render graphics on HTML5 Canvas — illustrations, diagrams, UI mockups, and interactive visual elements.
icon-generator
Generate consistent icon sets in SVG — line icons, filled icons, duotone, and multi-size PNG exports for apps and websites.
infographic-builder
Build data-rich infographics as SVG or HTML — timelines, process flows, comparison charts, and statistical summaries.