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 jsgerman-oss/blackrim-nimbus-skills --skill do-computegit clone --depth 1 https://github.com/jsgerman-oss/blackrim-nimbus-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/jsgerman-oss/blackrim-nimbus-skills/do-compute)<a href="https://agentmods.dev/skills/jsgerman-oss/blackrim-nimbus-skills/do-compute"><img src="https://agentmods.dev/badge/skills/jsgerman-oss/blackrim-nimbus-skills/do-compute/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jsgerman-oss/blackrim-nimbus-skills/do-compute"><img src="https://agentmods.dev/badge/skills/jsgerman-oss/blackrim-nimbus-skills/do-compute.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.02367 |
| Opus 5 | $0.00043 | $0.01184 |
| Sonnet 5 | $0.00017 | $0.00473 |
| Haiku 4.5 | $0.00009 | $0.00237 |
Grade A, and why
do-compute 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 11d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DigitalOcean Compute
When to use
- Choosing between a Droplet, App Platform, DOKS, or Functions for a new workload.
- Right-sizing a Droplet family or selecting a Premium AMD / Premium Intel plan.
- Configuring DOKS node pools, autoscaling, or cluster upgrades.
- Designing App Platform services with autoscaling and build pipelines.
- Reviewing snapshot strategies for backup and restore coverage.
- Auditing the IAM surface attached to compute (PAT scoping, project membership).
Decision tree
- Event-driven, short-lived, stateless, irregular load → Functions (Serverless). No infrastructure to manage; billed per invocation.
- HTTP service with no Kubernetes investment — managed build pipeline, simple autoscaling → App Platform. Pick Basic for low-traffic, Professional for persistent workers or higher concurrency.
- Container fleet with sidecars, custom networking, GitOps, multi-tenant concerns → DOKS. Managed control plane, node pools, integrated load balancer provisioning.
- Long-running VM, custom kernel, GPU workload, license-restricted software, database self-hosting → Droplet. Pick family by workload shape (see below).
- Burstable dev or very low-traffic staging → Basic Droplet (shared vCPU). Never use shared vCPU for production CPU-sensitive work.
Droplet families
| Family | When to pick |
|---|---|
| Basic (shared vCPU) | Dev, CI runners, low-traffic staging. Never prod for compute-sensitive paths. |
| General Purpose | Balanced CPU-to-memory ratio; the default for most production web services and APIs. |
| CPU-Optimized | Video encoding, scientific computing, compilation, high-traffic reverse proxies. |
| Memory-Optimized | In-memory caches, real-time analytics, large JVM heaps, self-hosted databases with large working sets. |
| Storage-Optimized | High-IOPS self-hosted databases, time-series, search engines — NVMe-backed local storage. |
| GPU | Machine learning inference and training. Available in selected regions; price per hour is significant — reserve only when actively training. |
| Premium AMD / Premium Intel | Drop-in for General Purpose when you need deterministic single-core performance (e.g. latency-sensitive game servers, high-frequency trading data feeds). |
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.
- 11d ago First seen · 123 lines · 86 tokens per session scan A d5019d94b318
do-compute is a skill published in the GitHub repository jsgerman-oss/blackrim-nimbus-skills (8 stars, last pushed 25d ago), licensed MIT. It adds 86 tokens to every session and 2,367 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…