adcm-teardown

adcm-teardown is a command for Claude Code from arenadata/adcm-agent. It costs 14 tokens per session (360 once invoked), scanned A, original, Apache-2.0.

A cleanup command for ADCM test deployments. ADCM is a system for managing clusters and deployment bundles, which are packages used to create them.

In plain words
What is it for?
Use it to list resources owned by the current repository, confirm the targets, then delete its clusters and bundles from the configured ADCM instance.
Why use it?
It helps prevent accidental deletion of resources created by someone else and follows the required order for removing dependent resources.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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 to list resources owned by the current repository, confirm the targets, then delete its clusters and bundles from the configured ADCM instance.

Compare 6 commands 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-teardown

README.md
[![agentmods](https://agentmods.dev/badge/commands/arenadata/adcm-agent/adcm-teardown.svg)](https://agentmods.dev/commands/arenadata/adcm-agent/adcm-teardown)
Your own site
<a href="https://agentmods.dev/commands/arenadata/adcm-agent/adcm-teardown"><img src="https://agentmods.dev/badge/commands/arenadata/adcm-agent/adcm-teardown.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 360 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 $0.00014 $0.00360
Opus 5 $0.00007 $0.00180
Sonnet 5 $0.00003 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 7d ago against content hash 5c07e93e6d33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

adcm-teardown 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.

commands/adcm-teardown.md · 45 lines

What it actually says

Clean up after test deploys. Target: $ARGUMENTS

Show what is yours first, and confirm

ADCM="python3 ${CLAUDE_PLUGIN_ROOT}/scripts/adcmctl.py"
$ADCM owned          # clusters and bundles this checkout created on this instance
$ADCM clusters       # everything on the instance, for context

owned reads the ownership records in <repo>/.adcm/state.json. Anything not in that list belongs to somebody else.

Deletion is destructive and not reversible. List what you are about to remove and get confirmation before removing it, even when the user asked for a teardown — they may not know a cluster on that list is still in use.

Then remove, cluster before bundle

$ADCM delete-cluster <clusterId>
$ADCM delete-bundle  <bundleId>

Order matters: ADCM refuses to delete a bundle a cluster is using.

Both commands refuse anything this checkout did not create. If one refuses, that is the guard working — do not reach for --force. Use it only when the object's owner has explicitly said yes, and say in your report that you did.

Hosts

Deleting a cluster releases its hosts back to the free pool. Do not delete hosts or hostproviders; they belong to the instance owner.

Report

What you removed, by id and name; what you deliberately left and why; and anything the guard refused, so the user can take it up with the owner.

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. 7d ago First seen · 45 lines · 14 tokens per session scan A 5c07e93e6d33

Subscribe to this mod's changes

adcm-teardown is a command published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 14 tokens to every session and 360 once invoked, about $0.0001 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.