claudeck: Skill for Claude Code

.claude/skills/claudeck-plugin-create/SKILL.md

claudeck-plugin-create is a skill for Claude Code from hamed-farag/claudeck. It costs 41 tokens per session (2,437 once invoked), scanned A, original, MIT.

A starter-maker for Claudeck plugins, which are add-ons for the Claudeck browser interface for Claude Code. It creates the JavaScript, CSS, and optional server-route files for a new plugin.

In plain words
What is it for?
Use it to start a built-in or personal Claudeck plugin with a kebab-case name and a short description of its purpose.
Why use it?
It removes the need to set up the plugin folders and basic files by hand. It also helps place personal plugins where they survive Claudeck updates.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code.

This is hamed-farag/claudeck's own configuration. It tells Claude Code how to work on claudeck 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 claudeck configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hamed-farag/claudeck. 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/hamed-farag/claudeck/main/.claude/skills/claudeck-plugin-create/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hamed-farag/claudeck

Made for: Claude Code.

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 claudeck-plugin-create

README.md
[![agentmods](https://agentmods.dev/badge/skills/hamed-farag/claudeck/claudeck-plugin-create/github.svg)](https://agentmods.dev/skills/hamed-farag/claudeck/claudeck-plugin-create)
Your own site
<a href="https://agentmods.dev/skills/hamed-farag/claudeck/claudeck-plugin-create"><img src="https://agentmods.dev/badge/skills/hamed-farag/claudeck/claudeck-plugin-create/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 claudeck-plugin-create

Your own site · 80×15
<a href="https://agentmods.dev/skills/hamed-farag/claudeck/claudeck-plugin-create"><img src="https://agentmods.dev/badge/skills/hamed-farag/claudeck/claudeck-plugin-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,437 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: 5 findings, 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 MCP Rug Pull · line 3
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 6
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Rogue Agent · line 24
    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.
  • medium Rogue Agent · line 109
    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.
  • medium Rogue Agent · line 158
    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 $0.00041 $0.02437
Opus 5 $0.00020 $0.01218
Sonnet 5 $0.00008 $0.00487
Haiku 4.5 $0.00004 $0.00244

Measured 9d ago against content hash 206a6635409b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claudeck-plugin-create 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 9d 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.

.claude/skills/claudeck-plugin-create/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a new Claudeck Plugin

You are scaffolding a new tab-sdk plugin called "$ARGUMENTS".

Parse the arguments: the first word is the plugin name (kebab-case), the rest is the description of what the plugin should do.

Plugin Locations

Claudeck supports two plugin directories:

Directory URL Path Use When
plugins/<name>/ (project) /plugins/<name>/ Building a built-in plugin that ships with Claudeck
~/.claudeck/plugins/<name>/ (user) /user-plugins/<name>/ Creating a personal/user-installed plugin that persists across updates

Default: Create user plugins in ~/.claudeck/plugins/<name>/ unless the user explicitly asks for a built-in plugin. User plugins are the recommended approach since they persist across npm upgrades and don't require modifying the Claudeck source code.

To resolve the user plugins directory, use ~/.claudeck/plugins/ (or $CLAUDECK_HOME/plugins/ if the env var is set).

Rules

  1. The plugin name MUST be kebab-case (e.g. my-plugin, code-metrics)
  2. All files go in the chosen plugin directory — NO other files need to be modified (no main.js, no style.css, no index.html)
  3. The plugin is auto-discovered by the server at runtime via GET /api/plugins
  4. Create at minimum: client.js and optionally client.css
  5. If the plugin needs server-side API routes, also create server.js (for user plugins, requires CLAUDECK_USER_SERVER_PLUGINS=true in ~/.claudeck/.env)
  6. If the plugin needs persistent config, also create config.json (auto-copied to ~/.claudeck/config/ on first run)

Client JS file template

Create client.js in the plugin directory following this structure:

// <Title> — Tab SDK plugin
// <Description of what the plugin does>
import { registerTab } from '/js/ui/tab-sdk.js';

registerTab({
  id: '<name>',
  title: '<Title>',
  icon: '<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">...</svg>',
  lazy: true,

  init(ctx) {
    // ── Build DOM ──
    const root = document.createElement('div');
    root.className = '<name>-tab';
    root.style.cssText = 'display:flex;flex-direction:column;flex:1;overflow:hidden;';

    // Build the UI innerHTML here...

    // ── Context API (ctx) ──
    // ctx.pluginId                      — Plugin's ID string
    // ctx.getProjectPath()              — Current project path
    // ctx.getSessionId()                — Current session ID
    // ctx.getTheme()                    — Current theme: 'dark' or 'light'
    // ctx.on('projectChanged', fn)      — Fires when user switches project (returns unsub fn)
    // ctx.on('ws:message', fn)          — Live WebSocket stream messages (returns unsub fn)
    // ctx.onState('sessionId', fn)      — Session switch (returns unsub fn)
    // ctx.off(event, fn)                — Remove an event listener
    // ctx.api                           — Full API module for fetch calls
    // ctx.storage.get(key)              — Read from plugin-scoped localStorage
    // ctx.storage.set(key, value)       — Write to plugin-scoped localStorage
    // ctx.storage.remove(key)           — Remove from plugin-scoped localStorage
    // ctx.toast(msg, opts)              — Show notification ({duration, type: 'info'|'success'|'error'})
    // ctx.showBadge(count)              — Show badge on tab button
    // ctx.clearBadge()                  — Hide badge
    // ctx.setTitle(text)                — Update tab button label
    // ctx.dispose()                     — Unsubscribe all listeners (auto-called on destroy)

    // ── Project-scoped data ──
    // If your plugin loads data scoped to a project, follow this pattern:
    //
    //   function loadData() {
    //     const project = ctx.getProjectPath();
    //     if (!project) return;
    //     fetch(`/api/plugins/<name>/?project=${encodeURIComponent(project)}`)
    //       .then(r => r.json()).then(data => { /* render */ });
    //   }
    //   ctx.on('projectChanged', loadData);  // reload on project switch
    //   loadData();                           // initial load
    //
    // IMPORTANT: ALWAYS use ctx.getProjectPath() to read the project path.
    //   NEVER use document.getElementById('project-select') directly.
    // IMPORTANT: ALWAYS use ctx.on('projectChanged', fn) to react to project changes.
    //   NEVER add your own change listener to the project select element.

    return root;  // must return an HTMLElement
  },

  // onActivate(ctx)   { /* tab became visible — ctx is passed */ },
  // onDeactivate(ctx) { /* tab was hidden — ctx is passed */ },
  // onDestroy(ctx)    { /* cleanup — ctx is passed; all subscriptions auto-disposed */ },
});

Read the full file on GitHub · 206 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. 9d ago First seen · 206 lines · 41 tokens per session scan A 206a6635409b

Subscribe to this mod's changes

claudeck-plugin-create is a skill published in the GitHub repository hamed-farag/claudeck (51 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 2,437 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens