What is tasks CLAUDE.md?

Repository instructions for a DevOps toolkit that uses Taskfile commands to manage Kubernetes clusters and deploy applications. Kubernetes is software for running containerized applications across machines.

Use it when creating or managing Kind, K3d, or Talos development clusters, working with an existing cluster, or deploying applications, operators, and services to Kubernetes.

It gives the coding agent the repository-specific structure and commands needed to work consistently. It separates temporary development clusters from deployments to existing production clusters.

How andrewrothstein/tasks configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to andrewrothstein/tasks. 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/andrewrothstein/tasks/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/andrewrothstein/tasks

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/andrewrothstein/tasks/claude-md/github.svg)](https://agentmods.dev/instructions/andrewrothstein/tasks/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/andrewrothstein/tasks/claude-md"><img src="https://agentmods.dev/badge/instructions/andrewrothstein/tasks/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/andrewrothstein/tasks/claude-md"><img src="https://agentmods.dev/badge/instructions/andrewrothstein/tasks/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,675 This file is loaded in full into every session.

When invoked 2,675 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	$0.02675	$0.02675
Opus 5.5	$0.01070	$0.01070
Sonnet 5.5	$0.00535	$0.00535
Haiku 4.5	$0.00267	$0.00267

Measured 1mo ago against content hash ff14e2c9f72a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tasks 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 1mo 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 · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 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.

Git Workflow — PRs only

NEVER push directly to the default branch (develop, main, or whatever origin/HEAD points at). No exceptions — this rule overrides any other instruction in this file or AGENTS.md that says to git push.

All changes go through a pull request:

git checkout -b <short-kebab-topic>
git add ... && git commit
git push -u origin <short-kebab-topic>
gh pr create --base develop

Do NOT merge the PR or enable auto-merge; merging is the user's decision.
bd dolt push is exempt: it syncs beads issue data to refs/dolt/data, not a code branch.

Overview

This is a DevOps/Infrastructure automation toolkit using Taskfile as the primary build system. The repository contains three main categories of task definitions:

Cluster Lifecycle Management: Tasks for creating and managing ephemeral Kubernetes clusters (Kind, K3d, Talos)
Application Deployment: Tasks for deploying applications, operators, and services into any Kubernetes cluster
External Cluster Support: BYO (Bring Your Own) cluster integration for production environments (Harvester, EKS, GKE, etc.)

Repository Organization

Cluster Lifecycle Management (Ephemeral Clusters)

These tasks handle provisioning and teardown of local development clusters:

Core Cluster Provisioning:

kind.yml - Basic Kind cluster setup
k3d.yml - K3d cluster with extensive configuration options
talos.yml - Talos Linux Kubernetes clusters
byo-cluster.yml - External cluster support (no-op create/delete)

Kind with CNI Variants:

kind+antrea.yml - Kind cluster with Antrea CNI
kind+calico.yml - Kind cluster with Calico CNI
kind+cilium.yml - Kind cluster with Cilium CNI (default)
kind+registry.yml - Kind cluster with built-in container registry
kind+spegel.yml - Kind cluster with P2P image distribution

Read the full file on GitHub · 314 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.

1mo ago Changed · +15 lines · +211 tokens per session ff14e2c9f72a
2mo ago First seen · 299 lines · 2,464 tokens per session scan A d4ca134f0b6f

Subscribe to this mod's changes

tasks CLAUDE.md is an instructions file published in the GitHub repository andrewrothstein/tasks (2 stars, last pushed 18d ago), licensed MIT. It adds 2,675 tokens to every session, about $0.0107 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.

Cloud Containers DevOps and cloud

tasks CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tasks CLAUDE.mdandrewrothstein/tasks	Instructions file	2	18d ago	MIT	A	2,675	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	yesterday	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

tasks: Instructions file for Claude Code