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 frontier-ai-next/mgarlbot --skill aws_opsgit clone --depth 1 https://github.com/frontier-ai-next/mgarlbotWrote 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/frontier-ai-next/mgarlbot/aws_ops)<a href="https://agentmods.dev/skills/frontier-ai-next/mgarlbot/aws_ops"><img src="https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/aws_ops.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 | $0.00020 | $0.00788 |
| Opus 5 | $0.00010 | $0.00394 |
| Sonnet 5 | $0.00004 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
aws_ops 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS EC2 (aws_api tool)
Креды в настройках бота: AWS_PROFILE или AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY, плюс AWS_REGION.
Не передавай ключи в аргументах и не выводи их в ответ.
Когда использовать
- «покажи EC2 / инстансы в AWS»
- «подними t3.micro в eu-central-1»
- «останови / запусти инстанс i-…»
- «какие VPC / subnets / security groups»
Безопасность (обязательно)
- Не вызывай
terminate_instanceбез явного запроса пользователя на удаление. - Для
terminate_instanceнуженparams.confirm: true. - По умолчанию предпочитай
t3.micro/t3.small; не запускай дорогие типы без запроса. - Перед
run_instance:list_vpcs→list_subnets→list_security_groups→list_amis(Ubuntu/Amazon Linux). - После
run_instance— краткий отчёт: InstanceId, IP, тип, регион.
Типовые вызовы
Инстансы:
{"action": "list_instances", "params": {"region": "eu-central-1"}}
{"action": "get_instance", "params": {"instance_id": "i-0123456789abcdef0", "region": "eu-central-1"}}
Запуск (минимальный):
{
"action": "run_instance",
"params": {
"region": "eu-central-1",
"ami_id": "ami-xxxxxxxx",
"instance_type": "t3.micro",
"name": "mgarlbot-test",
"key_name": "my-key",
"subnet_id": "subnet-xxx",
"security_group_ids": ["sg-xxx"]
}
}
Stop / start:
{"action": "stop_instance", "params": {"instance_id": "i-xxx", "region": "eu-central-1"}}
{"action": "start_instance", "params": {"instance_id": "i-xxx", "region": "eu-central-1"}}
Terminate (только по явной просьбе):
{"action": "terminate_instance", "params": {"instance_id": "i-xxx", "region": "eu-central-1", "confirm": true}}
Сеть и образы:
{"action": "list_vpcs", "params": {"region": "eu-central-1"}}
{"action": "list_subnets", "params": {"region": "eu-central-1", "vpc_id": "vpc-xxx"}}
{"action": "list_security_groups", "params": {"region": "eu-central-1"}}
{"action": "list_amis", "params": {"region": "eu-central-1", "owners": ["amazon"], "name_filter": "ubuntu-noble", "max_results": 10}}
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 · 76 lines · 20 tokens per session scan A 307f89b20c8d
aws_ops is a skill published in the GitHub repository frontier-ai-next/mgarlbot (17 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 788 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 2026-08-30.
Other skills, from other repositories
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
network-rca
Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience computejob on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.
givemeanode-agent-compute
Operate GiveMeANode GPU nodes, batch jobs, storage, and rollout sandboxes through its connected MCP server with bounded spend, durable recovery, and explicit approval for paid or destructive actions.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.