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/jstzwj/ai-infra-plugins/tensorflownpx skills add jstzwj/ai-infra-plugins --skill tensorflowgit 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/tensorflow)<a href="https://agentmods.dev/skills/jstzwj/ai-infra-plugins/tensorflow"><img src="https://agentmods.dev/badge/skills/jstzwj/ai-infra-plugins/tensorflow.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 5.1 | $0.00135 | $0.05215 |
| Opus 5 | $0.00068 | $0.02608 |
| Sonnet 5 | $0.00027 | $0.01043 |
| Haiku 4.5 | $0.00014 | $0.00522 |
Grade A, and why
tensorflow 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 6d 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.
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
42 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-and-architecture.md 32 KB
- references/02-tensors-and-operations.md 39 KB
- references/03-variables-and-resources.md 31 KB
- references/04-automatic-differentiation.md 30 KB
- references/05-keras-overview.md 40 KB
- references/06-keras-layers.md 69 KB
- references/07-keras-training.md 49 KB
- references/08-keras-preprocessing.md 45 KB
- references/09-tf-data.md 45 KB
- references/10-distributed-training.md 42 KB
- references/11-saved-model.md 40 KB
- references/12-checkpoints.md 33 KB
- references/13-ops-reference.md 45 KB
- references/14-control-flow.md 25 KB
- references/15-special-tensors.md 30 KB
- references/16-cpp-framework.md 39 KB
- references/17-graph-construction.md 36 KB
- references/18-session-and-executor.md 34 KB
- references/19-kernels.md 46 KB
- references/20-ops-registration.md 39 KB
- references/21-platform-abstraction.md 41 KB
- references/22-protobuf-definitions.md 47 KB
- references/23-distributed-runtime.md 31 KB
- references/24-grappler-optimizer.md 35 KB
- references/25-tfrt-runtime.md 28 KB
- references/26-xla-overview.md 27 KB
- references/27-hlo-ir.md 33 KB
- references/28-xla-compiler.md 41 KB
- references/29-jit-compilation.md 29 KB
- references/30-aot-compilation.md 30 KB
- references/31-mlir-dialects.md 31 KB
- references/32-tensorrt-integration.md 29 KB
- references/33-tflite-overview.md 33 KB
- references/34-tflite-converters.md 28 KB
- references/35-tflite-delegates.md 50 KB
- references/36-tflite-operators.md 46 KB
- references/37-tflite-micro.md 36 KB
- references/38-c-api.md 40 KB
- references/39-cc-api.md 32 KB
- references/40-serving-and-deployment.md 30 KB
- references/41-profiler-and-debugging.md 28 KB
- references/42-performance-optimization.md 32 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.
- 6d ago First seen · 414 lines · 135 tokens per session scan A 23f0f9d48c27
tensorflow is a skill published in the GitHub repository jstzwj/ai-infra-plugins (4 stars, last pushed 4mo ago), with no licence file. It adds 135 tokens to every session and 5,215 once invoked, about $0.0007 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
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
accelerate
Run PyTorch training across GPUs with minimal changes.
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.
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…
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 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.