dorkos: Skill for Claude Code

.claude/skills/maintaining-dev-playground/SKILL.md

maintaining-dev-playground is a skill for Claude Code from dork-labs/dorkos. It costs 95 tokens per session (3,885 once invoked), scanned A, original, MIT.

A development guide for keeping DorkOS's component gallery aligned with its application UI. The gallery shows components in isolation so developers and designers can inspect them separately.

In plain words
What is it for?
Use it when editing UI components or the development gallery to decide whether a showcase should be added or updated.
Why use it?
It prevents the gallery from becoming outdated or missing newly changed components, which can hide visual regressions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dork-labs/dorkos's own configuration. It tells Claude Code how to work on dorkos 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 dorkos configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { PlaygroundSection } from '../PlaygroundSection';.

Part of the flow plugin — 31 skills, 39 commands, 5 agents, 4 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to dork-labs/dorkos. 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/dork-labs/dorkos/main/.claude/skills/maintaining-dev-playground/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 31 skills, 39 commands, 5 agents, 4 hooks.

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 maintaining-dev-playground

README.md
[![agentmods](https://agentmods.dev/badge/skills/dork-labs/dorkos/maintaining-dev-playground.svg)](https://agentmods.dev/skills/dork-labs/dorkos/maintaining-dev-playground)
Your own site
<a href="https://agentmods.dev/skills/dork-labs/dorkos/maintaining-dev-playground"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/maintaining-dev-playground.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,885 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.
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 $0.00095 $0.03885
Opus 5 $0.00048 $0.01943
Sonnet 5 $0.00019 $0.00777
Haiku 4.5 $0.00010 $0.00388

Measured today against content hash c95382c7a173, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

maintaining-dev-playground 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.

.claude/skills/maintaining-dev-playground/SKILL.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maintaining the Dev Playground

The Dev Playground (apps/client/src/dev/, accessible at /dev in development) is a living gallery of every visual component in DorkOS. It exists so that designers and developers can review components in isolation, catch regressions visually, and verify that the design system is coherent.

The playground is only useful if it stays in sync with the actual application. Stale or missing showcases erode trust and let regressions slip through. This skill exists to prevent that drift.

When This Skill Applies

Assess playground impact whenever you edit files in:

  • apps/client/src/layers/widgets/**/ui/** — widget UI components
  • apps/client/src/layers/features/**/ui/** — feature UI components
  • apps/client/src/layers/entities/**/ui/** — entity UI components
  • apps/client/src/layers/shared/ui/** — shared UI primitives
  • apps/client/src/dev/** — direct playground edits

After editing a UI component, ask yourself three questions:

  1. Is this component a good playground candidate? (See candidacy criteria below)
  2. Is it already in the playground? Check the section registries in dev/sections/.
  3. If it's already there, is the showcase still accurate? Does it reflect the current props, states, and visual appearance?

Candidacy Criteria

A component belongs in the playground if it meets any of these:

  • Visual and reusable — renders UI that appears in more than one place, or could
  • Has multiple meaningful states — loading, empty, error, active, disabled, etc.
  • Part of the design system — buttons, inputs, cards, badges, overlays
  • A composed widget or panel — TasksPanel, MessagingConnections, TunnelDialog, etc.
  • Complex enough to regress — more than trivial markup; has conditional rendering, animations, or data-dependent layout

A component does NOT belong if it's:

  • Pure logic (hooks, utilities, stores) with no visual output
  • A one-line wrapper that adds a className
  • A layout container with no meaningful visual states
  • A page-level route component (the playground itself IS the page-level view)

Read the full file on GitHub · 269 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 c95382c7a173
  2. 3d ago First seen · 265 lines · 95 tokens per session scan A 52ed76721f00

Subscribe to this mod's changes

maintaining-dev-playground is a skill published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 3,885 once invoked, about $0.0005 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 2026-09-03.