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/skills/taste/SKILL.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/skills/p1-103n1x/bab-ilu/taste)<a href="https://agentmods.dev/skills/p1-103n1x/bab-ilu/taste"><img src="https://agentmods.dev/badge/skills/p1-103n1x/bab-ilu/taste/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/p1-103n1x/bab-ilu/taste"><img src="https://agentmods.dev/badge/skills/p1-103n1x/bab-ilu/taste.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 | $0.00089 | $0.02578 |
| Opus 5 | $0.00044 | $0.01289 |
| Sonnet 5 | $0.00018 | $0.00516 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
taste 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 12d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/taste — Lens-aware taste and vault diagnostics
Lens awareness (v2.1)
/taste dispatches on the active lens's analysis_contract.taste field.
That field is a list of report types the lens commits to produce. The
same command name serves three very different deliverables because
"what counts as taste" is a lens-level judgment, not a Bab-ilu-level one.
Runtime wiring (shared by every mode):
- Read the active lens at
.agent/lenses/active/lens.yamlviatools/lens_loader.load_lens(lens_id)— or honor--lens <id>when the user explicitly overrides. - Inject the lens's
prompts.mdviatools.lens_context.active_lens_preamble()at the top of every LLM-facing call. The preamble carries the lens's judgment rules, tone hints, and traps. Commands that skip this step will produce lens-shaped output with lens-neutral voice — a silent quality bug. - Resolve tier labels from
lens.entity_model(tier_0,tier_1_atom,tier_1_cluster) and anchor rules fromlens.anchors.authority_fields. Every downstream stage reads these, never hardcodes "work"/"motif".
Dispatch table
| Lens | analysis_contract.taste contents |
Behavior |
|---|---|---|
aesthetic-warburg |
aesthetic_density_by_domain, motif_frequency_top20, panel_emergence_heatmap |
Creative mode (legacy v2.0): walk the Panofsky pipeline on the visual input, write an Aesthetic MD + optional Warburg panel. See the body of this skill below. |
engineering-alexander |
(lens-defined list) | Diagnostic mode: report coverage of incident × pattern bipartite graph — which incidents lack patterns, which patterns have too few incidents, which pattern-languages are emergent. No write to vault. |
general-zettelkasten |
(lens-defined list) | Diagnostic mode: report Bloom-level distribution of notes, under-linked notes, concept-cluster gaps. No write to vault. |
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.
- 12d ago First seen · 209 lines · 89 tokens per session scan A 0c1c863b83f3
taste is a skill published in the GitHub repository P1-103n1x/bab-ilu (11 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 2,578 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.