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/commands/arenadata/adcm-agent/adcm-triage)<a href="https://agentmods.dev/commands/arenadata/adcm-agent/adcm-triage"><img src="https://agentmods.dev/badge/commands/arenadata/adcm-agent/adcm-triage.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 | $0.00017 | $0.00609 |
| Opus 5 | $0.00009 | $0.00304 |
| Sonnet 5 | $0.00003 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
adcm-triage 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work out what failed and whose problem it is. Subject: $ARGUMENTS
Load the adcm-troubleshoot skill. For a deep investigation, delegate to the adcm-failure-triager agent.
Classify before investigating
Every ADCM failure is one of five classes, and each needs different evidence:
| Class | Signature |
|---|---|
| Bundle defect | HTTP 4xx from upload or action-run; a job failing on its own logic or an undefined variable |
| Configuration gap | a concern; ISSUE_INTEGRITY_ERROR before any script runs |
| Correctly masked | the action is absent from the actions list — nothing is broken |
| Environment | UNREACHABLE, a package repository error, a disk or port problem |
| Connectivity | every path fails identically — blanket 502, timeout, TLS |
Name the class and the evidence for it. If two are plausible, say what would distinguish them.
Gather what that class needs
ADCM="python3 ${CLAUDE_PLUGIN_ROOT}/scripts/adcmctl.py"
$ADCM status --cluster <id>
$ADCM concerns --cluster <id>
$ADCM tasks --limit 10
$ADCM task-logs <taskId> --failed-only --tail 200
Read the first failing job, not the last. A half-completed action leaves the cluster inconsistent, so later jobs fail for unrelated reasons.
Quote log lines verbatim. The literal string is what maps to a source line.
Map a bundle error back to the source
ADCM names the rendered path. Open .adcm/staging/<edition>/<path> at the reported line,
then find it in the .j2 source — and in auto_bump/raw/ if that file is generated.
Refute your own conclusion before reporting it
- Is the action masked rather than missing? Compare
stateandmultiStateagainst the action'savailable:list. - Does it fail on every host (bundle) or exactly one (that host)?
- Does
whoamialso fail? Then the cluster is not the subject. - Was the bundle built with
--skip-pymod? AnImportErroron a vendored module is a build flag, not a code defect.
Report
Attribution first, then the evidence verbatim, the mechanism, the source file and line where it is a bundle defect, and the next step for whoever owns it. List what you ruled out.
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 · 63 lines · 17 tokens per session scan A e122cdc09f7f
adcm-triage is a command published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 17 tokens to every session and 609 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
step-research
Always research before proposing a fix. The Untether bug you're chasing is often a known upstream engine quirk, a previously-fixed regression, or a documented config gotcha.
iterate-feature
Iterate on the feature "$ARGUMENTS" to fix issues and address feedback.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
fix
Universal debugging and fix application with semantic code analysis.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.