google/skills is a collection of Agent Skills that guide AI agents in using Google products and technologies, including Google Cloud services. Developers and agents use these reusable workflows for tasks such as cloud authentication, data analysis, application deployment, and AI platform management. The catalogue entries are skills, plugins, and an MCP integration from this collection.
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 google/skills --skill workload-manager-basicsgit clone --depth 1 https://github.com/google/skillsWrote 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/google/skills/workload-manager-basics)<a href="https://agentmods.dev/skills/google/skills/workload-manager-basics"><img src="https://agentmods.dev/badge/skills/google/skills/workload-manager-basics.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00117 | $0.01484 |
| Opus 5 | $0.00059 | $0.00742 |
| Sonnet 5 | $0.00023 | $0.00297 |
| Haiku 4.5 | $0.00012 | $0.00148 |
Grade A, and why
workload-manager-basics 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workload Manager Basics
Workload Manager validates enterprise workloads against Google Cloud best practices and recommendations. The public client libraries are centered on evaluations: define a resource scope, choose built-in or custom rules, run an evaluation, then inspect results and scanned resources.
Use This Flow
flowchart LR
Rules["List rules"] --> Eval["Create or update evaluation"]
Resources["Project, folder, or org scope"] --> Eval
Eval --> Run["Run evaluation"]
Run --> Results["Inspect evaluation results"]
Results --> Remediate["Remediate findings"]
Results --> Export["Optional BigQuery export"]
Core API Constraints
To ensure compatibility, security, and successful integration:
- Public Surface Only: You MUST strictly interact with Workload Manager
using the official public
google-cloud-workloadmanagerclient library or the public REST API (workloadmanager.googleapis.com/v1). - No Internal or Undocumented APIs: Do NOT attempt to use internal RPC protocols, private service backends, or undocumented discovery mechanisms. They are not supported for public integrations and will fail.
- No Service-Specific CLI: There is no public
gcloud workload-managerCLI command group. Usegcloudonly for authentication, IAM role assignment, and fetching raw REST tokens. - Sandbox Execution Robustness (Auth/Mock Fallbacks): When gcloud authentication or Workload Manager API calls fail in sandboxed or restricted environments (e.g., due to Context Aware Access token blocks, missing API enablement, or mock resources returning 404/403), immediately fall back to presenting example code and static findings from your references instead of entering retry loops. Present the correct client library code structure or REST API payload example, clearly explain the auth or resource limitation, and list typical rules or mock findings statically to satisfy the request.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/client-library-usage.md 12 KB
- references/core-concepts.md 3.9 KB
- references/general-best-practices.md 5.0 KB
- references/iam-security.md 5.1 KB
- references/public-cli-status.md 2.0 KB
- references/public-mcp-status.md 935 B
- references/rest-usage.md 7.0 KB
- references/setup-prerequisites.md 3.0 KB
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 · 160 lines · 117 tokens per session scan A 81312f7c506d
workload-manager-basics is a skill published in the GitHub repository google/skills (19,604 stars, last pushed today), licensed Apache-2.0. It adds 117 tokens to every session and 1,484 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
scheduled-jobs
Covers cron and scheduled work done right — idempotency, preventing overlapping runs, monitoring for missed and failed runs, alerting on silence, and getting time zones and DST transitions correct. Use this whenever the user is writing a cron job or Kubernetes CronJob, asks why a scheduled job ran twice or didn't run…
scripting-automation
Covers writing operational scripts that survive contact with production — idempotency, real error handling and exit codes, structured logging, a dry-run mode, and recognizing when a script has outgrown scripting. Use this whenever the user is writing a bash or Python script that touches production, asks why a script…
artifact-management
Versions, stores, and promotes build outputs — registries, immutability, build-once-promote-many, retention and garbage collection, and provenance metadata. Use this whenever the user sets up an artifact or container registry, asks how to promote a build between environments without rebuilding, needs a retention or…
build-optimization
Makes builds fast and reproducible through incremental and hermetic builds, remote or shared caching, dependency caching, and parallelism, without trading correctness for speed. Use this whenever the user complains builds are slow, asks about build caching or cache keys, wants to cut cold-build time, is setting up a…
ci-pipelines
Designs continuous integration pipelines that give a fast, honest merge signal — stage ordering, reproducibility, safe caching, and required checks that actually gate merges. Use this whenever the user is writing or debugging a CI workflow (GitHub Actions, GitLab CI, Jenkins), complaining that CI is slow or flaky…
continuous-delivery
Builds the deployment pipeline that takes an artifact from a merged commit to production automatically and safely — promotion gates between environments, deploy-on-merge, and keeping main always releasable. Use this whenever the user is designing a deployment pipeline, asking how to ship changes faster, setting up…