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 agentmods add skills/jdpalumbo2/workbench/jp-frontend-designnpx skills add jdpalumbo2/workbench --skill jp-frontend-designgit clone --depth 1 https://github.com/jdpalumbo2/workbenchWrote 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/jdpalumbo2/workbench/jp-frontend-design)<a href="https://agentmods.dev/skills/jdpalumbo2/workbench/jp-frontend-design"><img src="https://agentmods.dev/badge/skills/jdpalumbo2/workbench/jp-frontend-design.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.01019 |
| Opus 5 | $0.00031 | $0.00509 |
| Sonnet 5 | $0.00012 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
jp-frontend-design 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 5d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JP Frontend Design
Overview
Unconstrained generation regresses to the statistical mean of every UI ever made — templated, forgettable, instantly recognizable as AI output. Constraints get set BEFORE code. Design is a sequence of deliberate, subject-grounded choices, and this skill is the sequence.
Companions (load if available): a craft-level design skill (e.g. Anthropic's
frontend-design) alongside this one; a dataviz skill before any chart. This skill
governs the ORDER of work.
The sequence (do these in order — no component code before step 2 exists)
- Brief. Propose 3 distinct visual directions: each gets a name, 3 mood words, a typography pairing, a color story, and one thing it deliberately avoids. Slop-test each: would a generic version of this prompt produce the same direction? If yes, replace it. The user picks or remixes. Working autonomously? Pick the direction most grounded in the subject's own world and say so — never the safest.
- Tokens file. One
tokens.css/ theme config before any component: semantic color names, type scale, spacing scale, radii, shadows. Every component consumes only tokens. This file is where taste lives — tweaks happen here, not in components, and a hand-edit to 30 lines of variables restyles the whole app. - References (when given). Screenshots get analyzed first — "what creates the hierarchy, density, spacing rhythm, type character" — then the findings go into the tokens. Analyze-then-build, never clone.
- One hero screen to full polish. Not a scaffold of every page. One screen, finished, embodying the brief's signature element.
- Screenshot critique loop — minimum 2 rounds. Render it, screenshot at desktop AND mobile widths (browser MCP / Playwright / DevTools), then critique both images as a senior product designer: 10 specific problems across hierarchy, spacing, typography, color; fix; re-shoot. Quality floor each round: responsive at mobile width, visible keyboard focus, prefers-reduced-motion respected. Models critique rendered output far better than they design blind — the loop is where quality actually happens.
- Scale out. Only after the hero passes: "extend this system" to remaining screens. Coherence comes from the tokens + finished exemplar.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 79 lines · 62 tokens per session scan A ac3a95cb08f4
jp-frontend-design is a skill published in the GitHub repository jdpalumbo2/workbench (1 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 1,019 once invoked, about $0.0003 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
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…