penguin-harness: Skill for Claude Code

.agents/skills/penguin-harness-frontend/SKILL.md

penguin-harness-frontend is a skill for Claude Code, Codex from Prism-Shadow/penguin-harness. It costs 91 tokens per session (10,961 once invoked), scanned A, original, Apache-2.0.

A set of frontend rules for PenguinHarness's Web App, which is the browser-based part of the product. It covers interface styling, status colours, icons, spacing, layouts, form fields, popups, and user-facing text.

In plain words
What is it for?
Use it when adding or restyling web-app screens, choosing colours or icons, arranging rows and forms, writing interface copy, or building popups.
Why use it?
It keeps new interface work consistent with decisions already used across the app and avoids introducing conflicting styling patterns or meanings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Prism-Shadow/penguin-harness's own configuration. It tells Claude Code and Codex how to work on penguin-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything penguin-harness configures →

About the project

PenguinHarness is a local-first platform in which multiple AI agents create, evaluate, optimize, and deploy agent applications. It is for people building AI software who want agents to generate applications and improve their own behavior through skills.

Prism-Shadow/penguin-harness · 2,975 stars · on GitHub · penguin.ooo

Reuse

Borrowing it

Nothing to install: this file belongs to Prism-Shadow/penguin-harness. 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/Prism-Shadow/penguin-harness/main/.agents/skills/penguin-harness-frontend/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Prism-Shadow/penguin-harness

Made for: Claude Code, Codex.

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.

agentmods badge for penguin-harness-frontend

README.md
[![agentmods](https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-harness-frontend/github.svg)](https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-harness-frontend)
Your own site
<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-harness-frontend"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-harness-frontend/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.

agentmods 80×15 button for penguin-harness-frontend

Your own site · 80×15
<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-harness-frontend"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-harness-frontend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,961 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 111
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.10961
Opus 5.5 $0.00036 $0.04384
Sonnet 5.5 $0.00018 $0.02192
Haiku 4.5 $0.00009 $0.01096

Measured today against content hash 8ec8641bcb56, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

penguin-harness-frontend 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 today.

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.

.agents/skills/penguin-harness-frontend/SKILL.md · 601 lines

How it starts

The opening of the file, as written. The whole thing — 601 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend conventions

packages/web is React 19 + Vite + Tailwind CSS 4, with no cn/clsx, no tailwind-merge, and no variants library. Classes are composed with template literals, and a component's variants are a Record<Key, string> next to it (button.tsx's variantClass, input.tsx's sizeClass). Match that shape; do not introduce a styling dependency.

This file records the decisions that already exist so they are not re-litigated per PR. Read penguin-harness-dev for the repo-wide contract (verification chain, changelog, two-repo layout).

Start in the shared UI package

Before adding or changing a control on any frontend, inspect packages/ui/src/index.ts, packages/ui/src/site.ts and the relevant component under packages/ui/src/components/. Reuse its component, hook or class helper. When it lacks the behavior needed by the app, extend that shared component and update its callers. A reusable interaction or visual rule belongs in packages/ui; each host supplies domain data, routing, translated labels, preference persistence and actions. Do not copy a shared control into a feature or patch its defaults in packages/web/src/styles.css.

Extract a common component or hook when the same interaction appears in multiple places. Keep the abstraction at the concrete behavior being shared; a one-off business rule stays with its feature. During review, check for duplicated markup, page-local overrides and call sites that bypass the shared component. Verify the shared change in the gallery and in a representative host surface.

Landing, docs and gallery chrome

Use @prismshadow/penguin-ui/site for the shared SiteHeader, SiteNavLinks, SiteLanguageMenu, SiteThemeToggle, SiteGitHubLink and site icons, and for what the sites' pages share: SiteFooter, SiteCodeCard, SiteCopyButton, SitePill, SiteMarkdown (article prose with SiteCodeBlock and SiteCodeTabs; the docs pass SITE_DOC_REMARK_PLUGINS and every site passes highlightSiteCode), SiteToc with useActiveTocEntry, SiteSidebarNav, SiteSearchDialog, SiteExternalLink, the preference providers (SiteThemeProvider, SiteLocaleProvider, the shared penguin-site.* keys) and useRouteScroll. Import @prismshadow/penguin-ui/site.css for their scoped appearance and shared cursors; a site's Tailwind entry also imports site-page.css (the dark variant, the brand scale, the neutral dark ramp, body defaults). This entry is independent of the app renderer and full theme; public sites do not need the app's bundled fonts just to render a page, nor the theme icon sets: a site control draws line icons (site-icons, CheckLineIcon) and builds menu rows with MenuRow, never GlyphIcon, MenuItem or a mark drawn in every set, any of which carries the sets into the landing and docs bundles. Their wrappers only adapt routes, labels, content and preferences. Do not restore copied navbar markup, language-menu event handlers, theme cycles, footers, copy buttons or Markdown typography in a site package.

Read the full file on GitHub · 601 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.

  1. today Changed · +4 lines 8ec8641bcb56
  2. yesterday Changed · +10 lines dc70cf138a64
  3. 2d ago Changed · +3 lines f93db6c84f46
  4. 8d ago Changed · +5 lines d1e251b19ad8
  5. 9d ago Changed · +7 lines e624552d791c
  6. 10d ago Changed · +17 lines 69c2aa3d4954
  7. 11d ago Changed · +56 lines · +91 tokens per session 83f93abce491
  8. 13d ago Changed · +1 lines 4c33c30c329d
  9. 14d ago Changed · +130 lines · -156 tokens per session e82b6e605bca
  10. 22d ago First seen · 368 lines · 156 tokens per session scan A 57e6fb395cf9

Subscribe to this mod's changes

penguin-harness-frontend is a skill published in the GitHub repository Prism-Shadow/penguin-harness (2,975 stars, last pushed today), licensed Apache-2.0. It adds 91 tokens to every session and 10,961 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

ui-craft

Design, build, redesign, or modify browser-visible web interfaces with product-quality composition, visual systems, interaction states, responsive behavior, accessibility, and browser visual QA. Use for HTML, CSS, JavaScript, React, Vue, or Svelte pages and components, landing pages, dashboards, admin tools, settings…

MemTensor/memmy-agent · 86 tokens

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json…

antgroup/agentic-ai-landscape · 94 tokens

dashboard

Update the agent's Control Center. Use when the user says "update my Control Center", "update my dashboard", "redesign my home", or "/dashboard".

openonion/connectonion · 35 tokens

tailwind-design-system

Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.

calesthio/OpenMontage · 42 tokens

anti-slop-frontend

A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…

BlackBeltTechnology/pi-agent-dashboard · 147 tokens

accessibility-a11y

Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.

BlackBeltTechnology/pi-agent-dashboard · 44 tokens