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/robium-ai/robium/1.0.2npx skills add robium-ai/robium --skill 1.0.2git clone --depth 1 https://github.com/robium-ai/robiumWrote 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/robium-ai/robium/1.0.2)<a href="https://agentmods.dev/skills/robium-ai/robium/1.0.2"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/1.0.2.svg" alt="Measured on agentmods" 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 | $0.00224 | $0.04600 |
| Opus 5 | $0.00112 | $0.02300 |
| Sonnet 5 | $0.00045 | $0.00920 |
| Haiku 4.5 | $0.00022 | $0.00460 |
Grade A, and why
cloud-run 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 5d 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.
probing a boot by hand from a shell, *hold the connection* (`curl -N --http1.1 This is a copy
97% identical to cloud-run — 62 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cloud-run
The deploy target for robium's headless robotics and demo containers: a sim + bridge (or a policy server) built into an image, pushed to Artifact Registry, and run on Google Cloud Run so a browser can reach it, optionally one private instance per visitor, scale-to-zero when idle. This skill consolidates the Cloud-Run-specific mechanics and the robotics/headless gotchas that were hard-won deploying a Gazebo Harmonic + Nav2 stack (robium's nav-trial demo, 2026-07-12/13). It stays thin on general gcloud/GCP usage (that lives in Google's own docs) and embeds only what a robotics container hits that a plain web service never does.
When to use this skill
- Building and deploying any headless robotics/sim/demo container to Cloud Run:
the
gcloud/ Cloud Build → Artifact Registry →gcloud run deploypath, and the flag set a sim workload needs (CPU/memory, timeout, concurrency, affinity). - Debugging a robotics container that runs locally but misbehaves on Cloud Run: gz/DDS discovery silent (no multicast), sim boot freezes (CPU throttled between requests), WebSocket drops, affinity cookie ignored, deploy fails on VPC IPs.
- Wiring deploy auth from CI/servers with a GCP service-account key.
- The trigger phrases in the description: 'deploy to Cloud Run', 'gcloud run deploy', 'Cloud Build', 'Artifact Registry', 'session affinity', '--no-cpu-throttling', 'GZ_RELAY on Cloud Run', 'Cloud Run WebSocket timeout'.
- Cross-references: go to the sibling skill instead when the question is:
- The demo orchestrator, session gateway (claim/status/shutdown + ws tunnel),
mission-control page, or viewer handoff →
live-demo(it uses this skill's deploy mechanics but owns everything demo-shaped above the container). - Whether to use uv vs Docker, local↔remote reproducibility, GPU passthrough,
or GPU-cloud/RunPod provisioning →
environments(Cloud Run is CPU-only and is one deploy target it points at; RunPod is the GPU one). foxglove_bridgemechanics, thefoxglove.sdk.v1subprotocol, MCAP → thefoxgloveskill (this skill only covers reaching the bridge through Cloud Run's proxy).- The whole-stack decision and where deploy sits →
architect(routes here).
- The demo orchestrator, session gateway (claim/status/shutdown + ws tunnel),
mission-control page, or viewer handoff →
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.
- 5d ago First seen · 293 lines · 224 tokens per session scan A 9a52c164b7bb
cloud-run is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 7d ago), licensed MIT. It adds 224 tokens to every session and 4,600 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 97% identical to cloud-run, differing in 62 lines, and is treated as a copy.
Other skills, from other repositories
dokploy-deploy
This skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Dokploy", "deploy Docker Compose on Dokploy", "manage Dokploy databases", "configure Dokploy domains", or "look up Dokploy CLI commands".
qdrant-deployment-options
Guides Qdrant deployment selection. Use when someone asks 'how to deploy Qdrant', 'Docker vs Cloud', 'local mode', 'embedded Qdrant', 'Qdrant EDGE', 'which deployment option', 'self-hosted vs cloud', or 'need lowest latency deployment'. Also use when choosing between deployment types for a new project.
diag-k8s-pod-crashloop
K8s Pod CrashLoopBackOff 全链排查。从 kubectl describe → events → logs → restart policy → resource limits → liveness/readiness probe → image pull → configmap/secret 挂载，定位根因并输出修复建议。.
aws-infrastructure
Use when working with AWS resources — ECS Fargate, ECR, EFS, Secrets Manager, gomplate templates, multi-env deployments — even when the user says 'deploy to staging' without naming AWS.
k8s-manifests
When writing K8s YAML, designing Helm charts, setting resource limits, configuring probes, or reviewing pod security.
Apache Airflow MCP
Skill "Apache Airflow MCP" from agentskillexchange/skills, covering apache airflow mcp, prerequisites, installation, documentation and source.