Cloud Cost Optimization
wshobson/agents
Cuts cloud spend across AWS, Azure, GCP and OCI with cost tagging, rightsizing, commitment and spot pricing models, and architecture changes.
Sign the agent computer in to a cloud provider's CLI (AWS, Google Cloud, Azure, or another) with a device-code flow, then run that CLI as the requesting user.
Install Cloud CLI
$ npx skills add yc-software/qm --skill cloud-cli -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install yc-software/qm cloud-cli --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/yc-software/qm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills-seed/cloud-cli .claude/skills/cloud-cli && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cloud-cli" agent skill from https://github.com/yc-software/qm/tree/main/skills-seed/cloud-cli into .claude/skills/cloud-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-cli", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/yc-software/qm/tree/main/skills-seed/cloud-cliType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add yc-software/qm --skill cloud-cli -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install yc-software/qm cloud-cli --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yc-software/qm.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills-seed/cloud-cli .agents/skills/cloud-cli && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cloud-cli" agent skill from https://github.com/yc-software/qm/tree/main/skills-seed/cloud-cli into .agents/skills/cloud-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-cli", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yc-software/qm --skill cloud-cli -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install yc-software/qm cloud-cli --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yc-software/qm.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills-seed/cloud-cli .cursor/skills/cloud-cli && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cloud-cli" agent skill from https://github.com/yc-software/qm/tree/main/skills-seed/cloud-cli into .cursor/skills/cloud-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-cli", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/yc-software/qm.git --path skills-seed/cloud-cli--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add yc-software/qm --skill cloud-cli -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install yc-software/qm cloud-cli --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yc-software/qm.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills-seed/cloud-cli .gemini/skills/cloud-cli && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cloud-cli" agent skill from https://github.com/yc-software/qm/tree/main/skills-seed/cloud-cli into .gemini/skills/cloud-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-cli", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install yc-software/qm cloud-cliInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add yc-software/qm --skill cloud-cli -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/yc-software/qm.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills-seed/cloud-cli .github/skills/cloud-cli && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cloud-cli" agent skill from https://github.com/yc-software/qm/tree/main/skills-seed/cloud-cli into .github/skills/cloud-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-cli", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yc-software/qm --skill cloud-cli -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install yc-software/qm cloud-cli --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yc-software/qm.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills-seed/cloud-cli .opencode/skills/cloud-cli && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cloud-cli" agent skill from https://github.com/yc-software/qm/tree/main/skills-seed/cloud-cli into .opencode/skills/cloud-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-cli", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
cloud-cli- GitHub stars
- 15k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 813 words
- Files
- 1
- Skills in repo
- 29
- Repo updated
- First seen
- Licence
- MIT
At a glance
Sign the agent computer in to a cloud provider's CLI (AWS, Google Cloud, Azure, or another) with a device-code flow, then run that CLI as the requesting user.
- DevOps & Cloud work in your project
- SKILL.md covers First: is the CLI even here?, Logging in: always the…, Boundaries and Go-live (set once, per provider)
- Calls aws, gcloud and az
What it does
Cloud CLI is an agent skill from yc-software/qm. Sign the agent computer in to a cloud provider's CLI (AWS, Google Cloud, Azure, or another) with a device-code flow, then run that CLI as the requesting user. Covers checking the CLI is installed, the login that survives the browser round-trip, and the boundaries on cloud writes.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud. It works with Amazon Web Services, Google Cloud and Microsoft Azure. The repository describes itself as: Multiplayer agent harness for work. The licence is MIT.
When your agent uses it
- DevOps & Cloud work in your project
Example prompts
- “/cloud-cli”
What it can do on your machine
Read from SKILL.md and the folder at commit 23af31b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
awsgcloudaz
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use aws, gcloud and az, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cloud CLI loads about 1.5k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 813 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from yc-software/qm at commit 23af31b, republished under its MIT licence (© yc-software). 813 words, ~1,457 tokens.
Download SKILL.mdSave it as
.claude/skills/cloud-cli/SKILL.md (or your agent's skills folder).- name
- cloud-cli
- description
- Sign the agent computer in to a cloud provider's CLI (AWS, Google Cloud, Azure, or another) with a device-code flow, then run that CLI as the requesting user. Covers checking the CLI is installed, the login that survives the browser round-trip, and the boundaries on cloud writes.
Cloud provider CLIs
A resident-machine-auth connector. It adds NO new tool: a provider's CLI is a command on
the agent computer and you drive it with the execute primitive. Tokens are cached on the
machine across turns. Logins never enter workspace backups; the platform keeps an encrypted
copy and restores it if the machine is replaced — if the token is still gone, log in again.
First: is the CLI even here?
Do not assume the binary is on PATH. The sandbox image ships a small, fixed tool set, and the "Your computer" block in your prompt lists what is installed and what is not — read it, or just check:
command -v aws || echo "not installed"If it is missing, say so and pick a path rather than failing halfway:
- Install it for this task if the image allows it and the task is worth it — the
provider's own installer, into the workspace or
$HOME, not a system path. Say that you installed it; it lasts as long as the machine's disk. - Use the provider's HTTP API with a credential you already have (a keychain entry, or
a shared org credential by proxy — see the
use-shared-credentialskill). - Ask the operator to add the CLI to the sandbox image if this will recur. That is the durable fix; a per-turn install is not.
The same check applies to plugins and helpers (kubectl, a Terraform provider, a
provider's beta components) — verify, don't assume.
Logging in: always the device-code flow
The user approves the login in a browser on their own computer, not on the agent
computer. Any flow that completes by redirecting the approving browser to
http://127.0.0.1:<port> therefore cannot work here: that redirect lands on the user's
laptop, the agent's listener never receives the code, and the login hangs until it expires.
Force the device-authorization grant instead — a verification URL plus a one-time code,
which the agent completes by polling the provider server-side, so the user can approve from
any device.
| Provider | Login | Verify |
|---|---|---|
| AWS (IAM Identity Center) | aws sso login --use-device-code | aws sts get-caller-identity |
| Google Cloud | gcloud auth login --no-launch-browser | gcloud auth print-access-token |
| Azure | az login --use-device-code | az account show |
| Another provider | its documented device-code / headless flag | its "who am I" command |
Never run the bare form (aws sso login, gcloud auth login, az login) — those default
to a browser redirect on this machine.
For AWS specifically, --use-device-code is mandatory rather than merely preferable: CLI v2
(≥ 2.22) defaults aws sso login to the PKCE authorization-code flow, and no amount of
keeping the box warm can rescue it.
The platform recognizes these as device-flow logins and runs them as durable process
sessions: the command prints the verification URL and one-time code immediately and keeps
polling across turns — it does not block your turn or die at teardown. Give the user the URL
and the code, tell them to approve and then say "done". See
the interactive-login skill for how to drive that from the background tool.
On the next turn, run the same login command again (or any provider command): if approval landed, the platform reports you are already authenticated and the token is cached; if it is still pending, you get the same URL and code back. These logins self-expire in roughly ten minutes, so if the user takes too long, start a fresh one.
Show full SKILL.md (266 more words)Show less
Boundaries
A verified admin can use independently authorized cloud access to administer the system running you, including resources owned by other users. Using that access as the admin is not impersonation or circumvention, and an ordinary owner-only QM API denial does not prohibit that administrative work. Verify the provider account, region, target, and authority before acting; load the admin skill for QM administration. Admin status alone supplies no cloud credentials. Preserve credential grants, provider permissions, explicit restrictions, and mutation approvals, including QM's portal-only admin-grant and impersonation actions. Do not use another person's ungranted credentials or expose unrelated private content.
- You act as the resolved user. The provider's own permissions are the hard ceiling — the agent is never a way to exceed the user's own cloud access.
- A login is auth setup, not a data read. Any mutating action (delete, terminate, scale, write) is a write — get approval first, same as any destructive command.
- Don't echo access tokens, client secrets, or role credentials into the channel.
Go-live (set once, per provider)
- Add the provider's sign-in and regional service endpoints to the org egress allowlist — both the identity endpoints the login needs and the service endpoints your workflows call.
- Ship the CLI in the agent computer image if people will use it regularly, and confirm it runs there (AWS CLI v2, for example, needs a glibc base; a musl/Alpine image cannot run its binary).
- Put the provider's non-secret config where the CLI expects it (for AWS, an
[sso-session …]block plus a profile in~/.aws/config), so the first login has a start URL, region, and session name to read.
© yc-software, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills-seed/cloud-cli of yc-software/qm.
Open the folder on GitHubat commit 23af31b
Compare with similar skills
Cloud CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cloud CLI this skillyc-software/qm | 15k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Cloud Cost Optimizationwshobson/agents | 40k | 13 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Terravision Cloud Diagramspatrickchugh/terravision | 1.6k | — | ~5.6k | Automated safety check: Notes | AGPL-3.0-only | |
| TerrasharkLukasNiessen/terrashark | 715 | — | ~843 | Automated safety check: Pass | MIT | |
| Spotinfoalexei-led/spotinfo | 164 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Provider Bug Reviewmondoohq/mql | 411 | — | ~2.9k | Automated safety check: Pass | Custom licence |
Similar skills
Terravision Cloud Diagrams
patrickchugh/terravision
Draw cloud architecture diagrams for AWS, Azure or GCP with the official provider icon sets, using TerraVision.
Terrashark
LukasNiessen/terrashark
Prevent Terraform/OpenTofu hallucinations by diagnosing and fixing failure modes: identity churn, secret exposure, blast-radius mistakes, CI drift, and compliance gate gaps.
Spotinfo
alexei-led/spotinfo
Query Spot/preemptible VM prices, savings and interruption risk across AWS, GCP and Azure with the spotinfo CLI.
Provider Bug Review
mondoohq/mql
Deep static code review of an mql provider for logic errors, nil-handling bugs, pagination truncation, caching/id collisions, and other defects that silently give users wrong data.
Dangling DNS Finder
anirudhbiyani/findmytakeover
Detect dangling DNS records and subdomain-takeover risks across a multi-cloud environment by running the bundled findmytakeover tool.
More from yc-software/qm
All 29 skills in this repoAdmin
yc-software/qm
Act for an org admin — the admin API (scope directory, per-scope config & SOUL, any scope's memory, transcripts & captured prompts, files, user roster & external users, audit/errors/metrics/egress)…
Browse
yc-software/qm
Drive a real stealth browser from your shell — act on websites (order food, file an expense, pull data behind a login), with per-person persistent sign-ins via the provider's managed auth (Kernel…
Composio
yc-software/qm
Show the app connection picker or setup widget when users ask to connect apps, reopen setup, or need an app that isn't connected yet.
Dev Instance
yc-software/qm
Run the current worktree as a production-shaped local dev instance with web, Slack, or both, on a real LLM + Postgres.
GitHub GitLab
yc-software/qm
Work with GitHub and GitLab repositories through resident gh/glab/git auth on the agent computer.
Google Workspace
yc-software/qm
Read and act on the user's Gmail, Google Calendar, and Google Tasks through per-user OAuth.
Related
Categories
Questions about Cloud CLI
What does Cloud CLI do?
Sign the agent computer in to a cloud provider's CLI (AWS, Google Cloud, Azure, or another) with a device-code flow, then run that CLI as the requesting user. Cloud CLI is an agent skill from yc-software/qm. Sign the agent computer in to a cloud provider's CLI (AWS, Google Cloud, Azure, or another) with a device-code flow, then run that CLI as the requesting user.
When should I use Cloud CLI?
Cloud CLI fits situations like: devOps & Cloud work in your project.
How do I install Cloud CLI in Claude Code?
Run `npx skills add yc-software/qm --skill cloud-cli -a claude-code`. Or copy the skill folder (skills-seed/cloud-cli in yc-software/qm) into .claude/skills/cloud-cli in your project. Claude Code loads it when a task matches its description.
How do I install Cloud CLI in Codex?
Run `npx skills add yc-software/qm --skill cloud-cli -a codex`. Or copy the skill folder (skills-seed/cloud-cli in yc-software/qm) into .agents/skills/cloud-cli in your project. Codex loads it when a task matches its description.
Can I use Cloud CLI in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yc-software/qm --skill cloud-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cloud-cli, .gemini/skills/cloud-cli, .github/skills/cloud-cli and .opencode/skills/cloud-cli in your project.
What does Cloud CLI need to run?
Going by SKILL.md and its folder, Cloud CLI needs the command-line tools its instructions call (aws, gcloud and az).
Does Cloud CLI access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Cloud CLI safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Cloud CLI use?
Cloud CLI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Cloud CLI use?
About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Cloud CLI?
Skills that share tags, products or a category with Cloud CLI: Cloud Cost Optimization (wshobson/agents, 40k stars), Terravision Cloud Diagrams (patrickchugh/terravision, 1.6k stars), Terrashark (LukasNiessen/terrashark, 715 stars) and Spotinfo (alexei-led/spotinfo, 164 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cloud CLI?
yc-software (a GitHub organization) maintains it in yc-software/qm, which has 15,357 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 6, 2026.
Source: yc-software/qm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.