Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/arenadata/adcm-agent/adcm-connectgit clone --depth 1 https://github.com/arenadata/adcm-agentWrote 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-connect)<a href="https://agentmods.dev/commands/arenadata/adcm-agent/adcm-connect"><img src="https://agentmods.dev/badge/commands/arenadata/adcm-agent/adcm-connect.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 | $0.00012 | $0.00595 |
| Opus 5 | $0.00006 | $0.00298 |
| Sonnet 5 | $0.00002 | $0.00119 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade B, and why
adcm-connect scanned grade B 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`chmod 600` whichever file you create. How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get this session talking to an ADCM instance. Target: $ARGUMENTS
Load the adcm-connection skill — it owns the resolution chain, the credential rules and the failure table. This command drives it.
Find out what is already set before changing anything
ADCM_SCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts"
python3 "$ADCM_SCRIPTS/adcmctl.py" config-show
That works even when nothing is configured, and it prints the provenance of every field —
so you can see whether a value came from the environment, the repository's .adcm.yaml or
the user config. Read it before proposing an edit.
Then prove it:
python3 "$ADCM_SCRIPTS/adcmctl.py" whoami
Success prints the instance URL, the account and the ADCM version. Stop here if it works.
If something is missing
Ask the user for it. Never guess a URL from a git remote, a playbook, an old skill file or an earlier conversation, and never try an account they did not give you.
What you need: the base URL including scheme and port, the account name, and how the
password is obtained — ideally a password_command: naming their password manager, so
nothing sits at rest.
Write it to ~/.config/adcm-agent/config.yaml for something they use from several
repositories, or <repo>/.adcm.yaml for a per-repository default. If you write the
per-repository file, add .adcm.yaml and .adcm/ to that repository's .gitignore in
the same change — the tooling refuses to read a plaintext credential out of a file git
would commit, and that refusal is the point.
chmod 600 whichever file you create.
If it fails
Use the failure table in the skill. The three that get misdiagnosed:
- HTTP 502 on every path — an inherited proxy, not the instance. Fix
no_proxyandNO_PROXYin the shell. CERTIFICATE_VERIFY_FAILED— an internal CA. Setca_bundle:, which keeps verification on.--insecureis for one-off triage, never for a stored profile.AUTH FAILED— ask the user. Do not try a second account.
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.
- 4d ago First seen · 62 lines · 12 tokens per session scan B 6e72783445e7
adcm-connect is a command published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 12 tokens to every session and 595 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
deploy
Build, test, deploy with staged rollout.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
cf-scaffold-project
Scaffold a Cloudflare project — Worker, Pages, or Worker+D1+R2 starter — with Wrangler config, Terraform skeleton, and GitHub Actions deploy using scoped API tokens.
scan
Scan AWS account for cost optimization.
finops-feedback
Step 5 (Feedback Loop & Celebration) — measure realized against projected savings, compute a labelled Cloud Entropy proxy, close the opportunity, and emit at least one new idea or policy update so the loop actually closes. Applies the double-loop gate. Mutates on the closure path.
run-panguweather
Guide the user through running PanguWeather end-to-end on an AMD cluster.