Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/arenadata/adcm-agentnpx agentmods add skills/arenadata/adcm-agent/adcm-bundle-dslWrote 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-bundle-dsl)<a href="https://agentmods.dev/skills/arenadata/adcm-agent/adcm-bundle-dsl"><img src="https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-bundle-dsl.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 | $0.00128 | $0.02786 |
| Opus 5 | $0.00064 | $0.01393 |
| Sonnet 5 | $0.00026 | $0.00557 |
| Haiku 4.5 | $0.00013 | $0.00279 |
Grade A, and why
adcm-bundle-dsl 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 7d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring config.yaml
config.yaml is a list of prototypes. One is the top-level object (type: cluster or
type: provider), the rest are its services, and components are nested inside their
service. Everything ADCM shows and enforces comes from here.
Key inventories are in the reference files — this page is the decision rules and the traps. reference/prototype-keys.md, reference/config-params.md, reference/action-keys.md.
Declare the contract before anything else
- name: my_product
type: cluster
display_name: My Product
description: ...
version: &version 1.2.3
edition: {{ edition }}
adcm_min_version: 2.12.0 # refuse to upload to older ADCM
contract_version: "2.1" # which DSL dialect this bundle speaks
license: adcm_cluster_eula/EULA.txt
adcm_min_version and contract_version are not decoration. contract_version selects
the DSL dialect, and several keys that were normal in 1.x are rejected under 2.x —
type: job|task on an action, venv:, config_jinja: and scripts_jinja: are all
deprecated and unsupported from contract version 2.0. If a key you copied from an older
bundle is rejected, check the contract version before assuming the key is wrong.
version is what ADCM keys the bundle by. Anchor it (&version) and reference it
(*version) from every service so a bump cannot drift.
license: points at a file inside the archive. A bundle with a license cannot be used
to create a cluster until the license is accepted against the prototype — that is a
one-time API call, not a bundle defect.
states and masking are alternatives, never both
This is the single most common structural error in an action.
# Simple availability: a list of states, plus the transitions
install:
display_name: Install
states:
available: [created]
on_success: installed
on_fail: created
# Rich availability: combine state and multi_state, positively or negatively
reload:
display_name: Reload
masking:
state:
available: [installed]
multi_state:
unavailable: [external]
on_success:
state: installed
multi_state:
unset: [needs_reload]
What ships with it
3 files 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.
- 7d ago First seen · 275 lines · 128 tokens per session scan A 6d437b9c8285
adcm-bundle-dsl is a skill published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 128 tokens to every session and 2,786 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-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…
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).
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…