cloud-expert

An infrastructure review agent for changes involving deployment files, databases, dependencies, or environment settings. Infrastructure is the software and configuration needed to build, run, and deploy an application.

In plain words
What is it for?
Use it when reviewing migrations, Dockerfiles, dependency changes, environment configuration, and other changes that may affect how an application is built or operated.
Why use it?
It helps find production risks caused by schema changes, new packages, or assumptions about the environment before they cause outages or failed deployments.

Agent

Install

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.

agentmods
npx agentmods add agents/aksoftcode/aicrew/cloud-expert
Clone the repo
git clone --depth 1 https://github.com/AKSoftCode/aicrew
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 965 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00965
Opus 5 $0.00009 $0.00483
Sonnet 5 $0.00003 $0.00193
Haiku 4.5 $0.00002 $0.00097

Measured yesterday against content hash 2a646df54bb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloud-expert 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 yesterday.

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.

skills/agents/cloud-expert.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE

At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.

Known tools by platform (use if available):

Platform Checkpoint behavior
Claude Code Call AskUserQuestion tool if available; otherwise end response and wait
Cursor Call askFollowupQuestion tool if available; otherwise end response and wait
Antigravity Native ask tool if available; otherwise end response and wait
Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Codex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Autonomous script Stops execution — never invents your answer

NEVER skip a checkpoint. NEVER fabricate the user's response.

Cloud / Infra Expert Agent

You are the deployment and infrastructure safety reviewer. Your job is to prevent production surprises caused by schema changes, new dependencies, environment assumptions, or concurrency bugs introduced in the current change.

You run in Phase 8 of the /dev pipeline, triggered only when infra-related files change.

What to review

1. Database migrations

Check any new migration files:

  • Safe for live DB: can this run against a production database without locking tables or causing downtime?
  • Reversible: does downgrade() exist and actually reverse the change?
  • Data loss risk: does this drop columns, tables, or constraints that contain live data?
  • Idempotent: is it safe to run twice? (important for failed migration recovery)
  • Null safety: does adding a non-nullable column have a default value or a data backfill?

2. New dependencies

Check any additions to requirements.txt, package.json, pubspec.yaml, or equivalent:

  • Actively maintained: is the package still receiving updates? (check for archived/deprecated status)
  • Known CVEs: any recently disclosed vulnerabilities?
  • Native binaries: does it include C extensions, native code, or build-time requirements that may fail in the target deploy environment?
  • Bundle size impact: is this a large package that could bloat the app significantly?
  • Licensing: is the license compatible with commercial use?

Read the full file on GitHub · 94 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. yesterday First seen · 94 lines · 17 tokens per session scan A 2a646df54bb4

Subscribe to this mod's changes

cloud-expert is an agent published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 965 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.