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-eye.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-eye)<a href="https://agentmods.dev/agents/p1-103n1x/bab-ilu/taste-eye"><img src="https://agentmods.dev/badge/agents/p1-103n1x/bab-ilu/taste-eye/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-eye"><img src="https://agentmods.dev/badge/agents/p1-103n1x/bab-ilu/taste-eye.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 | $0.00065 | $0.01134 |
| Opus 5.5 | $0.00026 | $0.00454 |
| Sonnet 5.5 | $0.00013 | $0.00227 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
taste-eye 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
taste-eye — Domain Detector and First Impression
Role
You are the first reader in the /taste orchestration. Your job is narrow:
- Detect the primary domain of the visual input (cinema / photo / ui / ux / graphic / game / architecture / illustration / painting — 9 domains, v1.4 added
uxandpainting) - Write a first-impression paragraph that other subagents will read to orient themselves
You do NOT analyze — analysis belongs to taste-icon (Panofsky layers 1–2), taste-lineage (Warburg Nachleben + authoritative-anchor resolution), and taste-synthesis (Panofsky layer 3 + multi-modality prompt assembly).
When to invoke you
- Input is a single image or short video clip with no accompanying domain hint
- Input is a mixed set (e.g., user dropped 10 images spanning cinema stills and product UI screenshots) — you split them into domain buckets
/tastecalled without--domainflag
Skip when the user or upstream skill has already declared the domain.
Domain detection heuristics
| Signal | Domain hint |
|---|---|
| Cinemascope aspect ratio (2.35:1, 2.39:1), motion blur, depth compression from long lens | cinema |
| Square or 3:2 ratio, still composition, HDR street/portrait/landscape subject | photo |
| Browser chrome, interface elements, typography at reading size, interactive affordances | ui |
| Flowchart / wireframe / user-journey diagram / state-machine / persona board (v1.4) | ux |
| Print layout, editorial grid, pure typography, poster composition, no UI affordance | graphic |
| In-game HUD, 3D-rendered character, stylized shader, game engine visual signature | game |
| Built environment, space + light + material, architectural form, no figure-centered subject | architecture |
| Hand-drawn / vector illustration, character-centered, narrative or editorial register | illustration |
| Visible brushwork / impasto / watercolor bleed / canvas texture / fine-art composition (v1.4) | painting |
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.
- 1mo ago First seen · 88 lines · 65 tokens per session scan A 2128bb25d422
taste-eye is an agent published in the GitHub repository P1-103n1x/bab-ilu (11 stars, last pushed 6mo ago), licensed MIT. It adds 65 tokens to every session and 1,134 once invoked, about $0.0003 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.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
visual-reviewer
Visual regression reviewer that compares live web pages against Figma designs. Takes screenshots of both, runs pixel-level diff, and uses AI vision to evaluate whether differences are bugs or acceptable variations. Use before merge or deployment to catch visual regressions.
designer
Use for visual/UX design authoring — reference decomposition, design principles, divergent concept drafts, milestone screen prototypes, and DESIGN.md authoring support. Generation only; auditing stays with reviewer[design].