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.
npx agentmods add instructions/alexellis/arkade/agents-mdgit clone --depth 1 https://github.com/alexellis/arkadeWrote 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/instructions/alexellis/arkade/agents-md)<a href="https://agentmods.dev/instructions/alexellis/arkade/agents-md"><img src="https://agentmods.dev/badge/instructions/alexellis/arkade/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03832 | $0.03832 |
| Opus 5 | $0.01916 | $0.01916 |
| Sonnet 5 | $0.00766 | $0.00766 |
| Haiku 4.5 | $0.00383 | $0.00383 |
Grade A, and why
arkade AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Run a `curl -i -X HEAD https://github.com/OWNER/REPO/releases/latest` (adds `/latest` to go directly to the latest release) - change OWNER and REPO accordingly. The `location` header in the response will show the actu How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Guide for AI Agents Contributing new downloads/apps/CLIs to Arkade
This document provides guidance for AI agents working on arkade, specifically for reviewing and adding new CLI tools to the arkade get command.
For system-level packages (usually Linux-only), see the arkade system install - usually for tools like Node.js, Go, Prometheus. Sometimes uses Go templates for tool definitions, often just uses its own code in the command.
For binaries distributed via OCI images, see arkade oci install.
Types of Arkade Commands
Arkade provides several types of installers:
-
arkade get- CLI tools usually to be placed at/usr/local/bin/or$HOME/.arkade/bin/. These are standalone binaries that can be downloaded and executed directly. -
arkade system install- Linux-only system-level tools like Node.js, Go, Prometheus. These require additional installation steps or system configuration. -
arkade oci install- Fetches binaries out of OCI images. Ideal for projects that use private repositories like slicer/actuated/k3sup-pro. -
arkade install- Kubernetes Helm charts or manifests for add-ons like OpenFaaS CE, Istio, PostgreSQL. These deploy software to Kubernetes clusters.
This guide focuses on arkade get - adding CLI tools that provide static binaries for download.
1. How to Add a New CLI (Tool) to Arkade
What Can Be Added
Only tools with static binaries can be added to arkade. The tool must provide pre-compiled binaries for download.
Cannot be added:
- Python-based tools (e.g.,
aws-cli,azure-cli) - require Python runtime - Node.js-based tools without static binaries - require Node.js runtime
- Tools that require installation scripts or package managers
- Tools that need runtime dependencies beyond the binary itself
Prerequisites
- Fork and create a branch:
git checkout -b add-TOOL_NAME
Step 1: Check GitHub Releases
CRITICAL: Before writing code, check the latest stable release on GitHub to see what OS/architecture combinations are available.
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.
- 3d ago First seen · 303 lines · 3,832 tokens per session scan A 2df3cdcbd3c1
arkade AGENTS.md is an instructions file published in the GitHub repository alexellis/arkade (4,611 stars, last pushed 5d ago), licensed MIT. It adds 3,832 tokens to every session, about $0.0192 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
terraform-hcloud-kube-hetzner AGENTS.md
AGENTS.md instructions for mysticaltech/terraform-hcloud-kube-hetzner, a project described as: Optimized and Maintenance-free Kubernetes on Hetzner Cloud in one command!
nacos AGENTS.md
AGENTS.md instructions for alibaba/nacos, covering agents.md, ai contribution guidelines, repository overview, core architecture and build & test commands.
k8e AGENTS.md
Instructions for xiaods/k8e, covering agents.md, project overview, architecture (big picture), key architectural flows and building.
Kubeli CLAUDE.md
Instructions for atilladeniz/Kubeli, covering kubeli - kubernetes management desktop app, project overview, quick start, development (tauri + vite) and web only development.
kubara AGENTS.md
Instructions for kubara-io/kubara, covering ai agent context, scope, product intent (stable), truth hierarchy and reference map.
Kubeli AGENTS.md
Instructions for atilladeniz/Kubeli: For project-specific conventions, commands, architecture, and workflow, consult CLAUDE.md first.