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.
/plugin marketplace add arenadata/adcm-agent/plugin install adcmWrote 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/skills/arenadata/adcm-agent/adcm-cluster-deploy)<a href="https://agentmods.dev/skills/arenadata/adcm-agent/adcm-cluster-deploy"><img src="https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-cluster-deploy.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 5.1 | $0.00124 | $0.02200 |
| Opus 5 | $0.00062 | $0.01100 |
| Sonnet 5 | $0.00025 | $0.00440 |
| Haiku 4.5 | $0.00012 | $0.00220 |
Grade A, and why
adcm-cluster-deploy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploying a test cluster
Establish the instance and the hosts before touching anything
There is no default instance and no default host list. Both come from the resolved settings (adcm-connection) or from the user:
ADCM_SCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts"
ADCM="python3 $ADCM_SCRIPTS/adcmctl.py"
$ADCM whoami # which instance, as whom
$ADCM hosts --free # what is actually available to deploy on
If deploy.hosts is set in the config file, those are the hosts you may use. If it is
not, ask which hosts to use — or pass --count N and let the tool take free ones, and
say in your report which it took. Never assume a host name, and never take a host that
belongs to another cluster: add-hosts refuses, and that refusal is correct.
Registering hosts and hostproviders is out of scope. If there is no free capacity, that is a message for the instance owner, not a problem to work around.
The sequence
Every step prints what it did and records ids in <repo>/.adcm/state.json, so later steps
need no arguments.
# 0. the bundle: whatever was last uploaded, or upload the last build now
$ADCM bundles --mine
$ADCM upload # uses last_build from state
# 1. prototype and licence
$ADCM prototype --type cluster # note the id and the licence status
$ADCM accept-license <prototypeId> # only when status is "unaccepted"
# 2. cluster — name defaults to <deploy.cluster_prefix or $USER>-MMDD-HHMM
$ADCM create-cluster --prototype-id <id>
# 3. services — all of the bundle's, or a subset
$ADCM add-services --cluster <clusterId>
$ADCM add-services --cluster <clusterId> --names svc_a,svc_b
# 4. hosts
$ADCM add-hosts --cluster <clusterId> --names <host,host> # or --count 2
# 5. mapping — satisfies each component's minimum across the attached hosts
$ADCM map --cluster <clusterId> # add --optional for [0,n] components
$ADCM show-mapping --cluster <clusterId>
# 6. configuration — see below
$ADCM concerns --cluster <clusterId>
# 7. install, and watch it
$ADCM run-action --cluster <clusterId> --name install --wait
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.
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.
- 5d ago First seen · 193 lines · 124 tokens per session scan A b81827c4bcc3
adcm-cluster-deploy is a skill published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 124 tokens to every session and 2,200 once invoked, about $0.0006 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.
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…
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).
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…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
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".
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…