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 skills/saski/arnesto/corporate-aws-clinpx skills add saski/arnesto --skill corporate-aws-cligit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/corporate-aws-cli)<a href="https://agentmods.dev/skills/saski/arnesto/corporate-aws-cli"><img src="https://agentmods.dev/badge/skills/saski/arnesto/corporate-aws-cli.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 | $0.00081 | $0.01167 |
| Opus 5 | $0.00041 | $0.00583 |
| Sonnet 5 | $0.00016 | $0.00233 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
corporate-aws-cli 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 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.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Corporate AWS CLI (federated login)
Goal
Use the correct AWS account, named profile, and region when the organization authenticates through IdP federation (SAML via tools like saml2aws, or IAM Identity Center / aws sso login). Avoid misleading CLI errors (invalid XML, empty body, wrong account) and align local commands with infrastructure-as-code (Terraform, Pulumi, Spacelift, etc.).
Use This Skill When
- Logging in with
saml2aws,aws sso login, or similar corporate flows before runningaws. aws sts get-caller-identityfails with Unable to parse response / invalid XML /b''.- After a successful login, commands still use the wrong identity or wrong region.
- You need orderable RDS engine versions or other regional APIs in the same account and region as the deployment stack.
This skill is vendor-neutral; follow your organization’s SSO and least-privilege runbooks in addition to these notes.
After federated login (saml2aws, aws sso, etc.)
- Credentials are usually stored under a named profile. The login output typically tells you to use
--profile <name>. - Pass that profile explicitly unless you intentionally use another:
aws sts get-caller-identity --profile <profile-from-login-output> awswithout--profileusesdefaultorAWS_PROFILE. Stale or emptydefaultoften produces confusing errors—not a clear “access denied”.- If you
export AWS_PROFILE=..., ensure environment variables do not override the profile chain:unset AWS_ACCESS_KEY_ID AWS_SECRET_ACCESS_KEY AWS_SESSION_TOKEN
“Invalid XML” / Empty Response (b'')
Typical causes (check in order):
- Wrong credential source — Run STS with the profile you just refreshed.
AWS_ACCESS_KEY_ID/AWS_SECRET_ACCESS_KEY/AWS_SESSION_TOKENset in the shell — unset them when using a profile.- Multiple
awsbinaries —which -a awsmay list more than one install. If behavior is odd, call the intended binary explicitly (example on Apple Silicon Homebrew):/opt/homebrew/bin/aws sts get-caller-identity --profile <profile> - Proxies / custom endpoints — Inspect
HTTPS_PROXY,HTTP_PROXY,AWS_ENDPOINT_URL,AWS_USE_FIPS_ENDPOINT,AWS_CA_BUNDLEif responses look non-AWS. - Shell job stopped with Ctrl+Z — A line like
suspended aws ...means SIGTSTP, not an AWS API error. Runjobs,fg, orkill %<n>and retry.
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 · 84 lines · 81 tokens per session scan A d9085865c050
corporate-aws-cli is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 9d ago), licensed Unlicense. It adds 81 tokens to every session and 1,167 once invoked, about $0.0004 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
eng-runbook
An engineering runbook — service overview, alerts table, dashboards links, common procedures with copy-pasteable commands, on-call rotation, and an incident-response checklist. Use when the brief mentions "runbook", "ops doc", "on-call guide", "SRE doc", or "运维手册".
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
alicloud_cli
阿里云 CLI 中文文档镜像检索与命令辅助：先走章节索引，再下钻正文页面，给出命令前必须有本地文档证据。.
terraform-cli-setup
Terraform CLI 安装与初始化技能。当用户本地未安装 Terraform 时自动完成安装，确保 terraform 命令可用并能执行 init/validate。不负责 Provider 凭证配置，凭证在实际使用时由 terraform-skill 引导。.
aiq-deploy
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
hyperpod-node-debugger
Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs replacing. Covers on-node EFA, GPU / accelerator hardware (XID, ECC, NVLink, row-remap, DCGM), Slurm node down/drained, disk and memory pressure, per-node lifecycle-script failures…