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.
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/plugins/nodnarbnitram/claude-code-extensions/cce-typescript)<a href="https://agentmods.dev/plugins/nodnarbnitram/claude-code-extensions/cce-typescript"><img src="https://agentmods.dev/badge/plugins/nodnarbnitram/claude-code-extensions/cce-typescript/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/plugins/nodnarbnitram/claude-code-extensions/cce-typescript"><img src="https://agentmods.dev/badge/plugins/nodnarbnitram/claude-code-extensions/cce-typescript.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cce-typescript 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 6d 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.
This is a copy
84% identical to cce-anthropic — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "cce-typescript",
"version": "1.0.0",
"description": "TypeScript and frontend tooling including Braintrust testing and fumadocs documentation",
"author": {
"name": "Claude Code Extensions Contributors",
"url": "https://github.com/nodnarbnitram/claude-code-extensions"
},
"homepage": "https://github.com/nodnarbnitram/claude-code-extensions",
"repository": "https://github.com/nodnarbnitram/claude-code-extensions",
"license": "MIT",
"keywords": [
"typescript",
"frontend",
"braintrust",
"testing",
"documentation"
]
}
What it installs
The manifest is a name and a version. 2 agents travel with it, and installing the plugin installs all of them — 124 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 6d ago First seen · 20 lines scan A 61857390f4be
cce-typescript is a plugin published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 84% identical to cce-anthropic, differing in 13 lines, and is treated as a copy.
Other plugins, from other repositories
excessibility
LiveView introspection and accessibility testing skills for Phoenix. Use htmlsnapshot() to capture state at any point, axe-core for WCAG compliance, timeline analysis for debugging.
fuse-react
Expert React 19 with hooks, TanStack Router, Zustand, React Hook Form, Testing Library, shadcn/ui, and SOLID principles.
podium-mcp
Mobile + canvas automation MCP — 51 tools for AI agents: iOS (simulator + real) & Android control, native UI automation, Maestro E2E flows, React Native/Metro debugging, WebView DOM + network, and a no-vision canvas/WebGL brain (Pixi/Konva/Fabric/Phaser/Three/Babylon) that drives game UIs like DOM — 5x fewer tokens th.
dev-infrastructure-skills
Framework-specific development best practices for React, Next.js, Supabase/Postgres, TDD, and Playwright E2E testing. Fills the engineering knowledge gaps that workflow orchestrators need to produce better code.
testable-nextjs-skill
Claude Code Skill for writing testable Next.js applications. Provides guidance for testing App Router, RSC, Server Actions, Route Handlers, and middleware with minimal test deltas and stability tactics.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.