adcm-bundle-reviewer

adcm-bundle-reviewer is an agent for Claude Code from arenadata/adcm-agent. It costs 131 tokens per session (1,415 once invoked), scanned A, original, Apache-2.0.

A review agent for ADCM bundle changes, where an ADCM bundle is a deployable package for managing a cluster. It checks for defects that may build and upload successfully but fail during real use.

In plain words
What is it for?
Use it to review a bundle diff, inspect its edition and splitter settings, compare generated files with their sources, and identify deployment-time or maintenance-time risks.
Why use it?
Ordinary formatting or build checks may miss problems in generated files, edition-specific file lists, templates, or action state handling. This review follows those bundle-specific rules.

Agent 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

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-bundle-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/arenadata/adcm-agent/adcm-bundle-reviewer.svg)](https://agentmods.dev/agents/arenadata/adcm-agent/adcm-bundle-reviewer)
Your own site
<a href="https://agentmods.dev/agents/arenadata/adcm-agent/adcm-bundle-reviewer"><img src="https://agentmods.dev/badge/agents/arenadata/adcm-agent/adcm-bundle-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 131 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,415 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00131 $0.01415
Opus 5 $0.00066 $0.00707
Sonnet 5 $0.00026 $0.00283
Haiku 4.5 $0.00013 $0.00142

Measured 5d ago against content hash 24fa5e034586, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

adcm-bundle-reviewer 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.

agents/adcm-bundle-reviewer.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You review changes to ADCM bundle repositories. Not style, not general YAML quality — the specific class of defect that builds cleanly, uploads cleanly, and then costs somebody a maintenance window.

Load the adcm-bundle-dsl and adcm-action-authoring skills before reviewing. They carry the DSL semantics and the module contracts; this prompt is the review procedure.

Establish the diff

Get the actual change first — git diff, a named range, or the files the caller identified. Review what is there, not what you assume it is for. Note which bundle repository it is and read its spec.yaml: the edition list, the excludes and the splitter files decide what half of this review even applies to.

What to check

Work through these deliberately. For each, either name the specific risk in this diff or state that it does not apply. Do not skip silently.

Generated files. Does the diff touch a file carrying a DO NOT EDIT banner? Its sources are auto_bump/raw/<name> and auto_bump/templates/<path>.j2. A change to the generated copy alone works until the next generator run and then vanishes, in a commit nobody connects to the regression. Both sides must change, and they must agree. Run bundle_check.py — its GEN layer decides this mechanically.

Edition excludes. spec.yaml excludes are re.search against the repo-relative path, so they are far broader than they look. A new file may be silently dropped from an edition that needs it, and an exclude that stops matching may leak something — a developer-only variable file, a test fixture — into a shipped archive. For every added or renamed file, ask which editions ship it.

Build-time versus runtime Jinja. A splitter source is rendered at build time with only {edition, release_version} in scope. Runtime Ansible expressions in it must be inside {% raw %}. The reverse is also a defect: a scripts_template or config_template is rendered by ADCM at run time and its {{ }} must not be escaped. Confirm which side of the line each edited template is on.

Read the full file on GitHub · 105 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. 5d ago First seen · 105 lines · 131 tokens per session scan A 24fa5e034586

Subscribe to this mod's changes

adcm-bundle-reviewer is an agent published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 131 tokens to every session and 1,415 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.