adcm-overview

adcm-overview is a skill for Claude Code from arenadata/adcm-agent. It costs 133 tokens per session (2,413 once invoked), scanned A, original, Apache-2.0.

An orientation guide to ADCM bundle repositories, where a bundle is a validated package describing a data cluster and its services, components, and hosts. It explains how these objects, actions, states, tasks, licenses, imports, and upgrades fit together.

In plain words
What is it for?
Use it when working on bundle files such as config.yaml and spec.yaml, defining cluster services, preparing deployments, or understanding ADCM states and actions.
Why use it?
It helps distinguish a rejected bundle definition from a deployment failure. ADCM checks the bundle's contract before running actions, so understanding its object model makes errors easier to interpret.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the adcm plugin — 8 skills, 7 commands, 3 agents shipped together

Good fit Use it when working on bundle files such as config.yaml and spec.yaml…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add arenadata/adcm-agent
Claude Code
/plugin install adcm

Made for: Claude Code.

Or install adcm, the plugin that ships this one along with the rest of its 8 skills, 7 commands, 3 agents.

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 adcm-overview

README.md
[![agentmods](https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-overview.svg)](https://agentmods.dev/skills/arenadata/adcm-agent/adcm-overview)
Your own site
<a href="https://agentmods.dev/skills/arenadata/adcm-agent/adcm-overview"><img src="https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-overview.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,413 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00133 $0.02413
Opus 5 $0.00067 $0.01207
Sonnet 5 $0.00027 $0.00483
Haiku 4.5 $0.00013 $0.00241

Measured 6d ago against content hash 532f597865fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

adcm-overview 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 6d 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.

skills/adcm-overview/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working in an ADCM bundle repository

A bundle is a contract ADCM validates, not a directory of playbooks

ADCM reads one config.yaml per bundle and turns it into prototypes — typed declarations of a cluster, its services, their components, and optionally a hostprovider and its hosts. Everything the UI and the API expose is derived from those prototypes: which configuration fields exist, which actions may run, which states they move the object through, and how many hosts each component needs.

That has one consequence worth internalising before anything else: most of what looks like a broken deploy is a rejected contract. ADCM validates the whole definition at upload time and refuses to run an action whose preconditions are not met. Its error text is the test result, not an obstacle.

Object What it is Created by
Bundle the uploaded .tgz — prototypes plus their Ansible payload uploading an archive
Prototype one typed declaration inside the bundle (type: cluster|service|component|provider|host|adcm) the bundle
Cluster an instance of a cluster prototype you, from a prototype id
Service an instance of a service prototype, added to a cluster add-services
Component a part of a service that runs on hosts implied by the service
Host a machine ADCM can reach, owned by a hostprovider the instance owner
Hostcomponent map which component runs on which host — ADCM calls this the mapping map
Task / Job one action run / one script inside it running an action
Concern a blocking issue ADCM raises against an object ADCM, continuously

State and multi-state are different things and both gate actions. A state is single valued (created, installed, running, and whatever the bundle invents). Multi-state is a set of flags set and cleared independently. An action's states: / masking: block can require either, so an action missing from the API listing is usually correctly hidden, not missing from the bundle.

Read the full file on GitHub · 163 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. 6d ago First seen · 163 lines · 133 tokens per session scan A 532f597865fb

Subscribe to this mod's changes

adcm-overview is a skill published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 133 tokens to every session and 2,413 once invoked, about $0.0007 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 skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens