A set of instructions for coordinating illustration work across OpenAI, fal.ai, and other image-generation services. It covers creating, editing, comparing, and preparing visual artwork.

Making campaign art, covers, comic panels, storyboards, visual variations, and image-provider comparisons.

It gives the agent a defined process for handling image requests and choosing between available image providers.

How whistlegraph/aesthetic-computer configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to whistlegraph/aesthetic-computer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/whistlegraph/aesthetic-computer/main/.claude/skills/illy/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/whistlegraph/aesthetic-computer

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/whistlegraph/aesthetic-computer/illy/github.svg)](https://agentmods.dev/skills/whistlegraph/aesthetic-computer/illy)

Your own site

<a href="https://agentmods.dev/skills/whistlegraph/aesthetic-computer/illy"><img src="https://agentmods.dev/badge/skills/whistlegraph/aesthetic-computer/illy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/whistlegraph/aesthetic-computer/illy"><img src="https://agentmods.dev/badge/skills/whistlegraph/aesthetic-computer/illy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 519 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00059	$0.00519
Opus 5.5	$0.00024	$0.00208
Sonnet 5.5	$0.00012	$0.00104
Haiku 4.5	$0.00006	$0.00052

Measured 2mo ago against content hash 648724f49df7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

illy 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 2mo 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.

.claude/skills/illy/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Illy

Use the shared illy MCP as the source of truth. The implementation, provider registry, pipelines, and full workflow live under plugins/illy/.

Workflow

Inspect the target production before generating.
- Marketing: preserve brand-brief.md, cover-prompt.txt, refs/, and gens/.
- Pop: keep illy/still prompts separate from motion prompts; the illy is the source frame for pop/lib/motion-pipeline.mjs.
Call illy_backends, illy_pipelines, and illy_contracts before choosing a paid route.
Call illy_plan before a batch or unfamiliar model. Report provider, model, references, output path, and stages.
Call illy_generate only after the requested route is clear. Existing output is cached unless force: true; rerolls archive the old take.
Inspect the output and iterate with one targeted prompt change.

Every pipeline enforces the shared physical-accuracy prompt contract. pop-panel also enforces extreme-physical-beats: a dynamic illy must be one mechanically valid temporal state with visible supports, contacts, grips, mounts, weight distribution, force direction, and physically possible camera geometry. When the built-in image tool is used, append the resolved contracts to its prompt and record their identifiers with illy_record.

Action, transformation, POV, and moving-platform motion shots use physical: "extreme", ordered normalized beats, and explicit contacts in their SHOTS entry. The shared motion pipeline rejects an incomplete extreme contract before paid generation.

Prefer an explicitly requested provider/model. Otherwise use the configured pipeline order. Never silently switch providers after a paid request fails. OpenAI is the established multi-reference route; fal.ai exposes model-shopping and specialized endpoints. Credentials resolve from the environment or the existing vault file and must never be printed.

For new adapters or custom stages, read plugins/illy/skills/illy/references/pipeline-contract.md. Keep shared presets in plugins/illy/config/; pass pipelineFile for a production-local pipeline.

Read the full file on GitHub · 36 lines

Changes

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.

2mo ago First seen · 36 lines · 59 tokens per session scan A 648724f49df7

Subscribe to this mod's changes

illy is a skill published in the GitHub repository whistlegraph/aesthetic-computer (91 stars, last pushed yesterday), licensed ISC. It adds 59 tokens to every session and 519 once invoked, about $0.0002 per session on Opus 5.5. 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.

Creative and media

illy next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
illywhistlegraph/aesthetic-computer	Skill	91	yesterday	ISC	A	59	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	2d ago	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	yesterday	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code

aesthetic-computer: Skill for Claude Code