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 acquia/acquia-skills --skill trial-managementgit clone --depth 1 https://github.com/acquia/acquia-skillsWrote 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/acquia/acquia-skills/trial-management)<a href="https://agentmods.dev/skills/acquia/acquia-skills/trial-management"><img src="https://agentmods.dev/badge/skills/acquia/acquia-skills/trial-management/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/acquia/acquia-skills/trial-management"><img src="https://agentmods.dev/badge/skills/acquia/acquia-skills/trial-management.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 | $0.00039 | $0.03616 |
| Opus 5.5 | $0.00016 | $0.01446 |
| Sonnet 5.5 | $0.00008 | $0.00723 |
| Haiku 4.5 | $0.00004 | $0.00362 |
Grade A, and why
trial-management 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 7d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trial Site Management
Use when:
- Creating a new trial Drupal site on Acquia Cloud
- Checking whether a trial is still provisioning, has finished, or has failed
- Getting the live site URL or admin sign-in link for a completed trial
- Retrying a trial that failed to provision
- Picking a Drupal template or AWS region before creating a trial
Note: The Trials API is a lightweight, pre-MEO provisioning surface in the v2 Cloud API (acli api:*), not MEO (acli api:v3:*). A user can have only one active trial at a time.
The Trial Lifecycle
api:trials:create ──▶ pending ──▶ in-progress ──▶ completed
│
└────────▶ failed ──▶ api:trials:retry ──▶ in-progress
status is always one of: pending, in-progress, completed, failed. Poll with api:account:find-trial — never assume completion, always check status before trusting _links.
| Status | What's available |
|---|---|
pending / in-progress |
percent_complete (0-100 integer) only. No site link yet. |
completed |
_links.site (live public URL) and _links.admin (one-time sign-in link) both appear. |
failed |
_links.retry appears. Call api:trials:retry, not api:trials:create again. |
Stuck trial: if status is pending with site_name: null, the trial is stuck server-side and cannot be resumed or retried (api:trials:retry is for failed trials only). Do not call api:trials:create again. Report the trial's id to the user and direct them to Acquia Support to clear the record.
Check Your Trial (and get the live site URL)
acli api:account:find-trial
This looks up your own trial account — no ID argument needed. This is the command to poll after creating a trial, and the command to use whenever an agent or user asks "where's my site?" / "is my trial ready?".
Example response once provisioning finishes:
{
"id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"site_name": "mytrialsite",
"status": "completed",
"percent_complete": 100,
"region": "us-east-1",
"_links": {
"site": { "href": "https://ppd2005c06prod.prod.acquia-sites.com" },
"admin": { "href": "https://ppd2005c06prod.prod.acquia-sites.com/user/login?token=abc123def456" }
}
}
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.
- 7d ago Changed · +29 lines bae13d962768
- 8d ago First seen · 224 lines · 39 tokens per session scan A a6f4539daa64
trial-management is a skill published in the GitHub repository acquia/acquia-skills (10 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 3,616 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-30.
trial-management compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trial-managementacquia/acquia-skills | Skill | 10 | yesterday | MIT | A | 39 | Claude Code, Codex |
| agent-platform-tuninggoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 64 | Claude Code, Codex |
| application-integration-authoringgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 103 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| application-design-center-design-deploygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 94 | Claude Code, Codex |
| gke-alert-configurationgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 120 | Claude Code, Codex |
| google-cloud-storage-basicsgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 213 | Claude Code, Codex |