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 cf-workers-and-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/cf-workers-and-compute)<a href="https://agentmods.dev/skills/jsgerman-oss/blackrim-nimbus-skills/cf-workers-and-compute"><img src="https://agentmods.dev/badge/skills/jsgerman-oss/blackrim-nimbus-skills/cf-workers-and-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/cf-workers-and-compute"><img src="https://agentmods.dev/badge/skills/jsgerman-oss/blackrim-nimbus-skills/cf-workers-and-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 | $0.00059 | $0.02230 |
| Opus 5 | $0.00030 | $0.01115 |
| Sonnet 5 | $0.00012 | $0.00446 |
| Haiku 4.5 | $0.00006 | $0.00223 |
Grade A, and why
cf-workers-and-compute scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Always use **ES module syntax** (`export default { fetch(request, env, ctx) {} }`) — avoid the legacy Service Worker format for new code. 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.
Cloudflare Workers and Compute
When to use
- Choosing between a Worker, Pages Function, Durable Object, or Container for a new workload.
- Designing a Worker that needs persistent state, coordination, or real-time connections.
- Debugging cold-start behaviour, CPU time exhaustion, or wall-clock timeout errors.
- Running AI inference at the edge via Workers AI.
- Designing a long-running or multi-step workflow with Cloudflare Workflows.
- Evaluating Smart Placement vs manual placement for latency-sensitive paths.
Decision tree
- Stateless HTTP handler, sub-millisecond response, global distribution → Workers (module syntax, standard isolate).
- Static site with dynamic edge logic, tied to a Pages project → Pages Functions.
- Single-instance coordinating state across many clients (real-time, rate limiting, session fan-out) → Durable Object.
- Multi-step durable execution: retries, sleeps, external calls that must complete even if the caller disconnects → Cloudflare Workflows.
- AI inference close to users with GPU-backed models → Workers AI (binding in the Worker, no separate deploy).
- Long-running process, arbitrary binaries, full OS environment, persistent disk → Cloudflare Containers (where available for your plan).
- Anything that needs >30 s CPU or a long-lived TCP connection that isolates can't hold → Containers or hybrid: Worker front-end + Container backend via Service Binding.
Defaults
Workers (module syntax)
- Always use ES module syntax (
export default { fetch(request, env, ctx) {} }) — avoid the legacy Service Worker format for new code. compatibility_dateinwrangler.toml/wrangler.jsonc: pin to a recent date and advance deliberately; breaking changes are gated here.- CPU time limit: 10 ms (Free / Workers Bundled) to 30 s (Unbound / Workers Paid). Wall-clock limit is up to 30 s for HTTP requests. Design handlers to be fast; offload slow work to Queues or Workflows.
- Use
ctx.waitUntil(promise)for fire-and-forget work (logging, analytics writes) after responding — do not block the response on it. - Bindings (KV, R2, D1, Durable Objects, Queues, Service Bindings, AI) are declared in
wrangler.tomland injected intoenv. Never hard-code resource names or access keys in code. - Secrets via
wrangler secret put— they appear inenvalongside bindings, are encrypted at rest, and never appear inwrangler.toml.
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.
- 12d ago First seen · 123 lines · 59 tokens per session scan A daa6bea24161
cf-workers-and-compute is a skill published in the GitHub repository jsgerman-oss/blackrim-nimbus-skills (8 stars, last pushed 27d ago), licensed MIT. It adds 59 tokens to every session and 2,230 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
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".
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…