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/fmind/dotfiles/google-cloud-operationsnpx skills add fmind/dotfiles --skill google-cloud-operationsgit clone --depth 1 https://github.com/fmind/dotfilesWhat 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 | $0.00034 | $0.00708 |
| Opus 5 | $0.00017 | $0.00354 |
| Sonnet 5 | $0.00007 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
google-cloud-operations 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 2d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operate Google Cloud
Use gcloud for bounded account, project, IAM, API, billing, logging, and audit operations. Use cloud-run for application deployment, terraform-stack for provisioned infrastructure, and incident-response for a live outage.
Workflow
-
Resolve identity and scope: Inspect the active named configuration, account, project, and quota or billing project. Do not activate another configuration or change defaults merely to make a command work.
gcloud config configurations list --format=json gcloud config configurations describe <configuration> --format=json gcloud config get auth/impersonate_service_account --configuration <configuration> gcloud config get auth/access_token_file --configuration <configuration> gcloud projects describe <project-id> --format=json -
Resolve the effective principal: Check
CLOUDSDK_AUTH_IMPERSONATE_SERVICE_ACCOUNT,CLOUDSDK_AUTH_ACCESS_TOKEN_FILE, and invocation flags as well as the named configuration. Impersonation and access-token-file overrides replace the selected account; before consequential calls, pin the intended impersonation chain explicitly or prove that neither override is active. -
Pin every consequential call: Pass
--configuration,--account,--project, and--billing-projectwhen applicable so terminal defaults cannot redirect the operation. Pass--impersonate-service-accountwhen the approved effective principal is an impersonation chain. Prefer a named configuration per environment. -
Start read-only: Describe the resource, current IAM policy, enabled services, billing linkage, relevant logs, quotas, and dependencies. Bound list and log queries by project, resource, and time window.
-
Plan the mutation: State the exact resource, before and after state, permissions, cost or quota impact, dependent services, rollback, and verification command. Enabling APIs, changing IAM or billing, deleting resources, and production operations require explicit authority.
-
Use short-lived identity: Prefer user OAuth, Workload Identity Federation, or explicit service-account impersonation over downloaded keys. Never print access tokens, credential files, or debug HTTP headers.
-
Apply minimally: Change only the named resource.
--quietsuppresses prompts; it does not make an operation safe or authorize it. -
Verify independently: Re-read the resource and its audit or operation status, then confirm behavior at the intended boundary. Separate local configuration, accepted API request, completed operation, and user-visible outcome.
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.
- 2d ago First seen · 41 lines · 34 tokens per session scan A baaa324c3722
google-cloud-operations is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 708 once invoked, about $0.0002 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
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
aiq-research
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
obsidian-bases
Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.
telegram
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…
chezmoi-expert
Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform…