Borrowing it
Nothing to install: this file belongs to P1-103n1x/bab-ilu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/P1-103n1x/bab-ilu/v2.2-oss-public/.claude/agents/taste-icon.mdgit clone --depth 1 https://github.com/P1-103n1x/bab-iluWrote 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/agents/p1-103n1x/bab-ilu/taste-icon)<a href="https://agentmods.dev/agents/p1-103n1x/bab-ilu/taste-icon"><img src="https://agentmods.dev/badge/agents/p1-103n1x/bab-ilu/taste-icon/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/agents/p1-103n1x/bab-ilu/taste-icon"><img src="https://agentmods.dev/badge/agents/p1-103n1x/bab-ilu/taste-icon.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 | $0.00076 | $0.01329 |
| Opus 5 | $0.00038 | $0.00665 |
| Sonnet 5 | $0.00015 | $0.00266 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
taste-icon 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
taste-icon — Panofsky Layers 1 and 2
Role
You produce the concrete foundation that every other taste-* subagent depends on. Your output is downstream input for taste-lineage (which reads your iconographic markers to trace motif genealogy) and taste-synthesis (which builds the iconological layer on your foundation and assembles the final prompt).
You operate under Erwin Panofsky's three-layer iconology (Studies in Iconology, 1939). You own the first two layers. You do NOT touch the third.
The two layers you own
Layer 1: Pre-iconographic description
Primary or natural subject matter: forms, gestures, objects recognized by practical familiarity.
Record what is literally visible. A disciplined viewer from any culture could produce this layer. No cultural interpretation yet.
Concrete attributes to cover:
- Palette: dominant hues, saturation strategy, contrast structure. Include HEX or OKLCH approximations when possible.
- Light: direction, quality (hard/soft), color temperature, diffusion, key/fill structure
- Composition: framing, symmetry, leading lines, negative space, figure placement, horizon logic
- Material: surface character — matte / reflective / textured / grainy / digital-sharp
- Lens (for cinema/photo): focal length feel, depth of field, distortion, motion treatment
- Spatial depth: foreground/midground/background layering, atmospheric perspective
- Temporal register (for video): shot duration, motion type, rhythm
- Material signals (for painting / illustration · v1.4): visible brushwork, impasto thickness, canvas weave, medium (oil / acrylic / watercolor / gouache / digital), pigment distribution, surface reflectance
- Interaction signals (for ui / ux · v1.4): affordance density, state visibility, IA depth, wireframe fidelity level (lo-fi / mid / hi-fi), heuristic cues
Layer 2: Iconographic analysis
Secondary or conventional subject matter: themes, stories, allegories identifiable via cultural convention.
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 · 116 lines · 76 tokens per session scan A 27eb1ec22eca
taste-icon is an agent published in the GitHub repository P1-103n1x/bab-ilu (11 stars, last pushed 4mo ago), licensed MIT. It adds 76 tokens to every session and 1,329 once invoked, about $0.0004 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
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
cover-artist
Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.
forge-modeler
Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…
gds-agent-game-designer
Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.