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 skills add arenadata/adcm-agent --skill adcm-action-authoringgit 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/skills/arenadata/adcm-agent/adcm-action-authoring)<a href="https://agentmods.dev/skills/arenadata/adcm-agent/adcm-action-authoring"><img src="https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-action-authoring/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.
<a href="https://agentmods.dev/skills/arenadata/adcm-agent/adcm-action-authoring"><img src="https://agentmods.dev/badge/skills/arenadata/adcm-agent/adcm-action-authoring.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00162 | $0.02532 |
| Opus 5 | $0.00081 | $0.01266 |
| Sonnet 5 | $0.00032 | $0.00506 |
| Haiku 4.5 | $0.00016 | $0.00253 |
Grade A, and why
adcm-action-authoring 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 8d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing the Ansible an ADCM action runs
An action's script: is an ordinary Ansible playbook, executed by ADCM against an
inventory it generates for that one run. Everything unusual about writing one comes
from that inventory and from the handful of modules ADCM injects.
The inventory is generated per run, and it is the whole context
You do not write an inventory and you cannot assume one. ADCM builds it from the cluster's current mapping, configuration and imports at the moment the action starts. Top-level variables (reference/job-inventory.md):
| Variable | Holds |
|---|---|
cluster |
the cluster's config, state, multi_state, name, id, imports |
services |
every added service by name — .config, .state, and its components |
job |
this run — .config (what the operator supplied), .id, .action, .params |
<service>.before_upgrade |
the pre-upgrade snapshot, during an upgrade only |
adcm_hostid |
the ADCM id of the host the task is running on |
Two rules follow, and both are the difference between a playbook that works once and one that works.
Guard every optional lookup. A service that is not added is simply absent from
services, and an unset config field is none, not missing. services.foo.config.bar
explodes on a cluster that never added foo.
when:
- services.monitoring is defined
- services.monitoring.state != 'created'
job.config is the action's own configuration, cluster.config and
services.<name>.config are the object's. They are different things and confusing them
produces a task that reads a value nobody set.
Group names come from the mapping, not from you
ADCM generates these groups; the names are exact:
| Group | Contains |
|---|---|
CLUSTER |
every host in the cluster, excluding hosts in maintenance mode |
<service> |
hosts running any component of that service |
<service>.<component> |
hosts running that component |
<service>.<component>.add |
hosts the pending hc_acl change will add it to |
<service>.<component>.remove |
hosts it will be removed from |
target |
the host a host_action: true action was launched against |
PROVIDER, HOST |
hostprovider actions: all its hosts / the acting host |
CLUSTER.maintenance_mode, <service>.maintenance_mode, <service>.<component>.maintenance_mode |
the hosts excluded from the groups above |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 221 lines · 162 tokens per session scan A 2addc012a312
adcm-action-authoring is a skill published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 162 tokens to every session and 2,532 once invoked, about $0.0008 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…