no-crd GEMINI.md

no-crd GEMINI.md is an instructions file for Gemini CLI from nogoo9/no-crd. It costs 1,970 tokens per session, scanned A, original, Apache-2.0.

Repository-specific instructions for working on no-crd, a platform that lets AI agents create and manage temporary Kubernetes pods without custom cluster definitions. It covers the project structure, architecture, tools, and coding conventions.

In plain words
What is it for?
Use it when developing or reviewing no-crd, especially its Model Context Protocol server, Kubernetes pod lifecycle operations, cross-runtime TypeScript code, local clusters, and project commands.
Why use it?
It gives a coding agent the project context and working rules it needs before changing the repository, reducing confusion about how the pod-management system is organised.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Gemini CLI.

Install

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.

agentmods
npx agentmods add instructions/nogoo9/no-crd/gemini-md
Clone the repo
git clone --depth 1 https://github.com/nogoo9/no-crd

Made for: Gemini CLI.

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 no-crd GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nogoo9/no-crd/gemini-md.svg)](https://agentmods.dev/instructions/nogoo9/no-crd/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/nogoo9/no-crd/gemini-md"><img src="https://agentmods.dev/badge/instructions/nogoo9/no-crd/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,970 This file is loaded in full into every session.
When invoked 1,970 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01970 $0.01970
Opus 5 $0.00985 $0.00985
Sonnet 5 $0.00394 $0.00394
Haiku 4.5 $0.00197 $0.00197

Measured 5d ago against content hash e27dd274627b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

no-crd GEMINI.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 5d 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.

GEMINI.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini CLI Mandate: nogoo9 / no-crd

This repository is a platform for agent-driven, on-demand pod orchestration in Kubernetes (k8s/k3s) without Custom Resource Definitions. It provides dynamic pod lifecycle management similar to JupyterHub or cloud IDE services, but agnostic to actual use cases.

Project Overview

  • Purpose: Let AI agents (and APIs) dynamically spin up, route to, and manage ephemeral pods on Kubernetes — without requiring CRDs or cluster-level operators.
  • Architecture:
    • MCP Server (src/): Model Context Protocol server exposing pod lifecycle tools — spawn, stop, list, templates — to AI agents.
  • Technology Stack: Bun, Deno, Node.js, TypeScript, Moon (task runner), Biome (linting/formatting), Docker, k3d (local k8s), Kubernetes client-node.

Architecture Map

graph TD
    Agent["AI Agent / Client"] --> MCP["MCP Server: src/"]
    MCP --> K8s["Kubernetes API"]
    K8s --> Pod["Spawned Pod"]

Repository Structure

nogoo9/
├── src/                 # MCP server for pod lifecycle tools (cross-runtime)
│   ├── server/          # Fastify HTTP server, SSE manager, OIDC singleflight & proxies
│   ├── mcp/             # MCP tool implementations & schema definitions
│   └── polyfill.ts      # Global environment polyfills for Deno/Node compatibility
├── infra/
│   └── k3d/             # Local k3d cluster setup + manifests
├── .agents/             # AI agent rules & workflows
├── .moon/               # Moon workspace + toolchain config
├── .github/             # CI workflows
├── deno.json            # Deno import maps for Node module compatibility
└── package.json         # Package configuration & conditional exports

Development Conventions

  • Toolchain: Supports Bun, Deno, and Node.js runtimes. Pinned via .prototools and .moon/toolchain.yml.
  • 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").
  • Linting & Formatting: Strictly adhere to Biome and import checks. Run bun run format (Biome lint + auto-fix) and bun run lint (scripts/check-imports.ts). Do NOT use ESLint or Prettier.
  • Testing (Mandatory):
    • TDD: Write unit tests before implementing features or fixes.
    • Unit Tests: Located in src/**/*.test.ts.
    • Run all tests: bun run test or moon run mcp:test.
  • Error Handling: Use clear descriptive messages. MCP tools must return structured error responses.

Read the full file on GitHub · 116 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. 5d ago First seen · 116 lines · 1,970 tokens per session scan A e27dd274627b

Subscribe to this mod's changes

no-crd GEMINI.md is an instructions file published in the GitHub repository nogoo9/no-crd (2 stars, last pushed 24d ago), licensed Apache-2.0. It adds 1,970 tokens to every session, about $0.0098 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 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens