What is no-crd CLAUDE.md?

Repository guidance for working on nogoo9, a platform that lets AI agents start, route, and manage temporary Kubernetes workloads without custom resource definitions. It lists the project’s purpose, commands, and supported runtimes.

Use it when changing nogoo9’s MCP server—the service that lets AI agents control workloads through the Model Context Protocol—or when checking and deploying the project.

It gives a coding agent the project context and the commands needed to install dependencies, check types, lint, test, build, run, and deploy the code.

How nogoo9/no-crd configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nogoo9/no-crd. 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/nogoo9/no-crd/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nogoo9/no-crd

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nogoo9/no-crd/claude-md/github.svg)](https://agentmods.dev/instructions/nogoo9/no-crd/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nogoo9/no-crd/claude-md"><img src="https://agentmods.dev/badge/instructions/nogoo9/no-crd/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nogoo9/no-crd/claude-md"><img src="https://agentmods.dev/badge/instructions/nogoo9/no-crd/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,690 This file is loaded in full into every session.

When invoked 1,690 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01690	$0.01690
Opus 5.5	$0.00676	$0.00676
Sonnet 5.5	$0.00338	$0.00338
Haiku 4.5	$0.00169	$0.00169

Measured 2mo ago against content hash 54122fe1c32a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

no-crd CLAUDE.md 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 2mo 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.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Purpose

nogoo9 is a platform providing agent-driven, on-demand pod orchestration for Kubernetes (k8s/k3s) without Custom Resource Definitions. It enables AI agents and APIs to dynamically spin up, route to, and manage ephemeral workloads — similar to JupyterHub or cloud IDE services, but agnostic to actual use cases.

The platform is delivered as:

MCP Server — exposes pod lifecycle tools to AI agents via the Model Context Protocol.

Commands

# Install dependencies
bun install

# Type check
bun run typecheck

# Lint import boundaries & path aliases (scripts/check-imports.ts)
bun run lint

# Format / auto-fix with Biome
bun run format

# Run dev server on specific runtimes (from source)
bun run dev:bun
bun run dev:deno
bun run dev:node

# Run MCP server on specific runtimes (from built bundle)
bun run run:bun
bun run run:deno
bun run run:node

# Run all unit tests
bun run test
moon run mcp:test

# Build package via Moon (Node target)
moon run mcp:build

# Deploy MCP to local k3d cluster
moon run mcp:deploy
moon run mcp:deploy-wsl

Toolchain & Coding Conventions

Proto pins Bun (1.3.11), Node (22.14.0), Deno (2.3.3), and Moon (2.1.3) via .prototools. Run proto use to install pinned versions.
Linting/formatting uses Biome (biome.json), not ESLint/Prettier.
Path Alias Invariant: Never use relative parent paths (../) in src/ modules. Always use the project path alias (~/) (e.g. import { foo } from "~/server/helpers.js").

Architecture

Project layout

src/            — MCP server exposing pod lifecycle tools (cross-runtime)
src/server/     — Fastify HTTP server, SSE manager, OIDC singleflight & proxies
src/mcp/        — MCP tool implementations & schema definitions
src/polyfill.ts — Polyfill file for global environment compatibility
deno.json       — Deno import mappings for Node modules
infra/k3d/      — Local k3d cluster setup + k8s manifests
scripts/        — Documentation sync and lifecycle test scripts

Read the full file on GitHub · 134 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.

2mo ago First seen · 134 lines · 1,690 tokens per session scan A 54122fe1c32a

Subscribe to this mod's changes

no-crd CLAUDE.md is an instructions file published in the GitHub repository nogoo9/no-crd (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,690 tokens to every session, about $0.0068 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 2026-08-31.

no-crd CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
no-crd CLAUDE.mdnogoo9/no-crd	Instructions file	2	2mo ago	Apache-2.0	A	1,690	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

no-crd: Instructions file for Claude Code