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 jstzwj/ai-infra-plugins --skill raygit clone --depth 1 https://github.com/jstzwj/ai-infra-pluginsWrote 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/jstzwj/ai-infra-plugins/ray)<a href="https://agentmods.dev/skills/jstzwj/ai-infra-plugins/ray"><img src="https://agentmods.dev/badge/skills/jstzwj/ai-infra-plugins/ray/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/jstzwj/ai-infra-plugins/ray"><img src="https://agentmods.dev/badge/skills/jstzwj/ai-infra-plugins/ray.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 | $0.00339 | $0.09122 |
| Opus 5 | $0.00169 | $0.04561 |
| Sonnet 5 | $0.00068 | $0.01824 |
| Haiku 4.5 | $0.00034 | $0.00912 |
Grade D, and why
ray scanned grade D with 3 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 9d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
response = requests.post("http://localhost:8000/MyModel", json={"input": [1, 2, 3]}) Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
ssh_private_key: ~/.ssh/id_rsa Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.post("http://localhost:8000/MyModel", json={"input": [1, 2, 3]}) The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
25 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/01-overview-architecture.md 11 KB
- references/02-ray-core-tasks.md 8.1 KB
- references/03-ray-core-actors.md 9.7 KB
- references/04-ray-core-objects.md 7.6 KB
- references/05-ray-data.md 35 KB
- references/06-ray-serve.md 6.9 KB
- references/07-ray-train.md 6.1 KB
- references/08-ray-tune.md 7.3 KB
- references/09-ray-rllib.md 7.0 KB
- references/10-ray-cluster.md 36 KB
- references/11-runtime-environment.md 19 KB
- references/12-job-submission.md 28 KB
- references/13-dashboard-observability.md 11 KB
- references/14-fault-tolerance.md 9.4 KB
- references/15-scheduling-placement-groups.md 9.0 KB
- references/16-ray-workflow.md 7.6 KB
- references/17-ray-dag-compiled-graphs.md 8.0 KB
- references/18-ray-air.md 9.3 KB
- references/19-cross-language.md 6.3 KB
- references/20-security.md 7.9 KB
- references/21-cli-reference.md 9.6 KB
- references/22-internal-architecture.md 13 KB
- references/23-ray-llm.md 13 KB
- references/24-ray-client.md 7.7 KB
- references/25-performance-tuning.md 11 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.
- 9d ago First seen · 1,246 lines · 339 tokens per session scan D 6890bfa17f67
ray is a skill published in the GitHub repository jstzwj/ai-infra-plugins (4 stars, last pushed 4mo ago), with no licence file. It adds 339 tokens to every session and 9,122 once invoked, about $0.0017 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, reaches for credential files, 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
accelerate
Run PyTorch training across GPUs with minimal changes.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
developing-genkit-python
Develop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when encountering Genkit errors, import issues, or API problems.
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
minicpm5-deploy-transformers
Run MiniCPM5-1B or MiniCPM5-2B with Hugging Face Transformers for one-shot Python generation on GPU (bfloat16) or CPU (float32). Use when the user wants a quick Python script, no server, no extra deps, or asks for "Transformers", "AutoModelForCausalLM", "model.generate" with MiniCPM5.
azure-mgmt-fabric-py
Azure Fabric Management SDK for Python. Use for managing Microsoft Fabric capacities and resources. Triggers: "azure-mgmt-fabric", "FabricMgmtClient", "Fabric capacity", "Microsoft Fabric", "Power BI capacity".