adcm-connection

adcm-connection is a skill for Claude Code, Codex from arenadata/adcm-agent. It costs 125 tokens per session (2,187 once invoked), scanned B, original, Apache-2.0.

A guide to connecting ADCM tooling to an Arenadata Cluster Manager instance, a system for managing data clusters. It explains where the server address, credentials, profiles, and security settings come from.

In plain words
What is it for?
Use it when configuring adcmctl.py with command-line options, environment variables, repository settings, named profiles, passwords, API tokens, proxies, or TLS verification.
Why use it?
It prevents commands from silently connecting to the wrong cluster or using unsafe default credentials. Missing settings produce an explicit error instead of a guessed connection.

Skill for Claude CodeCodex

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

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 skills/arenadata/adcm-agent/adcm-connection
Any agent
npx skills add arenadata/adcm-agent --skill adcm-connection
Clone the repo
git clone --depth 1 https://github.com/arenadata/adcm-agent

Made for: Claude Code, Codex.

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-connection

README.md
[![agentmods](https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-connection.svg)](https://agentmods.dev/skills/arenadata/adcm-agent/adcm-connection)
Your own site
<a href="https://agentmods.dev/skills/arenadata/adcm-agent/adcm-connection"><img src="https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-connection.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00125 $0.02187
Opus 5 $0.00063 $0.01094
Sonnet 5 $0.00025 $0.00437
Haiku 4.5 $0.00013 $0.00219

Measured 5d ago against content hash 51d8209e5038, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

adcm-connection scanned grade B with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

The file is also checked for group/other read permission and warns; `chmod 600` it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

exactly this reason — if you see 502 from `curl` but not from `adcmctl.py`, that is the
skills/adcm-connection/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Connecting to an ADCM instance

There is no default instance, and that is the feature

adcmctl.py has no built-in URL, no built-in account, and no built-in host list. A tool that quietly falls back to a fixed address ends up talking to a stand that was decommissioned two quarters ago, and a tool that falls back to admin/admin teaches everyone to leave admin/admin in place.

So when a setting is missing you get an error naming the setting and the three places it can come from, and nothing is attempted:

NOT CONFIGURED: the ADCM base URL is not configured.
Set it in one of (highest precedence first):
  export ADCM_URL=https://adcm.example.internal:8443
  <repo>/.adcm.yaml            ->  url: ...      (add .adcm.yaml to .gitignore)
  ~/.config/adcm-agent/config.yaml  ->  url: ...

Ask the user which instance to use. Do not guess one from a git remote, a hostname in a playbook, an old skill file, or an earlier conversation.

Resolution order

Every field resolves independently, first match wins:

# Source Use it for
1 CLI flag — --url, --user, --profile, --insecure, --use-proxy a one-off override
2 Environment — ADCM_URL, ADCM_USER, ADCM_PASSWORD, ADCM_TOKEN, ADCM_PROFILE, ADCM_VERIFY_SSL, ADCM_CA_BUNDLE, ADCM_USE_PROXY secrets, CI
3 <repo>/.adcm.yaml (or .yml / .json) this repository's usual instance
4 ~/.config/adcm-agent/config.yaml your instances, shared across repositories

ADCM_PASS is accepted as an alias for ADCM_PASSWORD. Ask config-show rather than reasoning about precedence — it prints the resolved value and its provenance:

python3 "$ADCM_SCRIPTS/adcmctl.py" config-show    # works even when nothing is set
python3 "$ADCM_SCRIPTS/adcmctl.py" whoami         # proves URL + credentials + route

The config file, with profiles

One file describes every instance you use. Full key list in reference/config-file.md.

Read the full file on GitHub · 179 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 179 lines · 125 tokens per session scan B 51d8209e5038

Subscribe to this mod's changes

adcm-connection is a skill published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 125 tokens to every session and 2,187 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). 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

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

cloud-architect

Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…

Jeffallan/claude-skills · 71 tokens