adcm-troubleshoot

adcm-troubleshoot is a skill for Claude Code from arenadata/adcm-agent. It costs 122 tokens per session (2,320 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide for ADCM, a system that deploys and manages data clusters. It groups failures into bundle defects, configuration problems, intentionally hidden actions, environment issues, and network connections.

In plain words
What is it for?
Use it to diagnose rejected uploads, blocked actions, failed tasks, missing actions, empty bundles, proxy errors, TLS problems, and connection failures using ADCM status, concerns, tasks, and logs.
Why use it?
It helps identify who or what is responsible before investigating, avoiding wasted time on the wrong logs or settings.

Skill 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

Good fit Use it to diagnose rejected uploads, blocked actions, failed tasks, missing actions, empty bundles, proxy errors, TLS problems, and connection failures using ADCM status, concerns, tasks, and logs.

Compare 6 skills 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-troubleshoot

README.md
[![agentmods](https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-troubleshoot/github.svg)](https://agentmods.dev/skills/arenadata/adcm-agent/adcm-troubleshoot)
Your own site
<a href="https://agentmods.dev/skills/arenadata/adcm-agent/adcm-troubleshoot"><img src="https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-troubleshoot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for adcm-troubleshoot

Your own site · 80×15
<a href="https://agentmods.dev/skills/arenadata/adcm-agent/adcm-troubleshoot"><img src="https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-troubleshoot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,320 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00122 $0.02320
Opus 5 $0.00061 $0.01160
Sonnet 5 $0.00024 $0.00464
Haiku 4.5 $0.00012 $0.00232

Measured 10d ago against content hash edd08842e66b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

adcm-troubleshoot scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

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

address. `adcmctl.py` bypasses the environment proxy by default, so if `curl` 502s and
skills/adcm-troubleshoot/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnosing an ADCM failure

Attribute before you investigate

Almost every ADCM failure is one of five things, and each has a different owner. Deciding which one you are looking at takes a minute and saves an hour.

Class Signature Owner
Bundle defect HTTP 4xx from upload or action-run, or a job failing on its own logic you
Configuration gap a concern, or ISSUE_INTEGRITY_ERROR before anything runs the operator
Correctly masked the action is simply not in the actions list nobody — it is working
Environment a job fails reaching a package repository, a port, a disk, a peer the instance or host owner
Connectivity every path fails identically — 502, timeout, TLS your shell or the network

Start with the class, then read only the evidence that class needs.

ADCM="python3 ${CLAUDE_PLUGIN_ROOT}/scripts/adcmctl.py"
$ADCM status   --cluster <id>      # state, multi-state, services, hosts, concerns
$ADCM concerns --cluster <id>      # exactly what is blocking, per object
$ADCM tasks    --limit 10          # what ran, and how it ended
$ADCM task-logs <taskId> --failed-only --tail 200

"The action is not there" usually means it is masked, correctly

GET .../actions/ lists what can start right now. An action whose states: or masking: block excludes the object's current state and multi-state is absent from that list, and that is the bundle working as designed.

$ADCM status  --cluster <id>       # read state and multiState
$ADCM actions --cluster <id>       # what that state permits

Compare the object's state against the action's available: list in config.yaml before concluding anything is wrong. adcmctl.py run-action prints the available names when it cannot find yours, for exactly this comparison.

An action that is listed but refuses to start with startImpossibleReason set, or with ISSUE_INTEGRITY_ERROR, is the next section.

ISSUE_INTEGRITY_ERROR means "read the concerns"

Read the full file on GitHub · 177 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. 10d ago First seen · 177 lines · 122 tokens per session scan A edd08842e66b

Subscribe to this mod's changes

adcm-troubleshoot is a skill published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 122 tokens to every session and 2,320 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (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

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens