digitalocean-skills: Instructions file for Claude Code

CLAUDE.md

digitalocean-skills CLAUDE.md is an instructions file for Claude Code from iamnolanhu/digitalocean-skills. It costs 780 tokens per session, scanned A, original, MIT.

Repository guidance for a Claude Code extension that manages DigitalOcean cloud infrastructure, either through connected tools or direct API requests.

In plain words
What is it for?
It helps manage DigitalOcean resources such as virtual machines and firewalls, test the extension locally, and work with its skills, commands, agents, and session-start hook.
Why use it?
It explains the two operating modes and the project’s testing and file conventions, so infrastructure actions follow the intended workflow.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is iamnolanhu/digitalocean-skills's own configuration. It tells Claude Code how to work on digitalocean-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything digitalocean-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to iamnolanhu/digitalocean-skills. 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/iamnolanhu/digitalocean-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/iamnolanhu/digitalocean-skills

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.

agentmods badge for digitalocean-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/iamnolanhu/digitalocean-skills/claude-md/github.svg)](https://agentmods.dev/instructions/iamnolanhu/digitalocean-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/iamnolanhu/digitalocean-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/iamnolanhu/digitalocean-skills/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.

agentmods 80×15 button for digitalocean-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/iamnolanhu/digitalocean-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/iamnolanhu/digitalocean-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 780 This file is loaded in full into every session.
When invoked 780 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00780 $0.00780
Opus 5 $0.00390 $0.00390
Sonnet 5 $0.00156 $0.00156
Haiku 4.5 $0.00078 $0.00078

Measured 10d ago against content hash be5f73ba1a6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

digitalocean-skills CLAUDE.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 10d 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.

- **Without MCP**: Falls back to direct API calls via curl (each skill has API examples)
CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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.

What This Is

A Claude Code plugin providing DigitalOcean infrastructure management skills. The plugin works in two modes:

  • With MCP: Uses DigitalOcean MCP tools (droplet-create, firewall-list, etc.)
  • Without MCP: Falls back to direct API calls via curl (each skill has API examples)

Testing

source .env  # Load DIGITALOCEAN_API_TOKEN

Test by invoking skills/commands in conversation, or load the plugin locally:

claude plugin add ./

Architecture

.claude-plugin/plugin.json  # Plugin manifest (defines what files are skills/commands/agents/hooks)
skills/*/SKILL.md           # Workflow guides with frontmatter (name, description)
commands/*.md               # Slash commands with frontmatter (name, description, argument-hint)
agents/*.md                 # Specialized personas with frontmatter (name, description, model)
hooks/hooks.json            # Hook configuration (SessionStart runs session-start.sh)
hooks/session-start.sh      # Displays status, detects MCP mode, shows running resources

Key Patterns

Skills are opinionated playbooks that make decisions (VPC by default, defense-in-depth security). Each skill must include both MCP tool examples AND curl API fallbacks in a "Tool Reference" section.

Commands invoke skills or perform quick operations. Use /do- prefix.

Agents are multi-step personas (e.g., infrastructure-auditor runs systematic security audits).

Session-start hook detects MCP availability and shows current resource costs on session start.

Naming Conventions

  • Skill directories: kebab-caseskills/managing-ssh-keys/SKILL.md
  • Commands: /do-{action}commands/do-provision.md
  • Agents: kebab-case.mdagents/cost-optimizer.md

Quick Reference

Commands (6)

Command Description
/do-dashboard Full infrastructure view with costs
/do-costs Quick cost breakdown
/do-status Infrastructure overview
/do-provision Guided Droplet creation
/do-firewall Firewall management
/do-ssh-setup SSH key configuration

Read the full file on GitHub · 89 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. 10d ago First seen · 89 lines · 780 tokens per session scan A be5f73ba1a6e

Subscribe to this mod's changes

digitalocean-skills CLAUDE.md is an instructions file published in the GitHub repository iamnolanhu/digitalocean-skills (4 stars, last pushed 7mo ago), licensed MIT. It adds 780 tokens to every session, about $0.0039 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 2026-08-31.