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 NVIDIA/TileGym --skill tilegym-cutile-pythongit clone --depth 1 https://github.com/NVIDIA/TileGymWrote 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/nvidia/tilegym/tilegym-cutile-python)<a href="https://agentmods.dev/skills/nvidia/tilegym/tilegym-cutile-python"><img src="https://agentmods.dev/badge/skills/nvidia/tilegym/tilegym-cutile-python/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/nvidia/tilegym/tilegym-cutile-python"><img src="https://agentmods.dev/badge/skills/nvidia/tilegym/tilegym-cutile-python.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 4 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00043 | $0.04452 |
| Opus 5.5 | $0.00017 | $0.01781 |
| Sonnet 5.5 | $0.00009 | $0.00890 |
| Haiku 4.5 | $0.00004 | $0.00445 |
Grade A, and why
tilegym-cutile-python 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 2d 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
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
36 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.
- BENCHMARK.md 7.4 KB
- evals/evals.json 3.9 KB
- examples/convolution/conv_transpose_2d.py 14 KB runs code
- examples/convolution/conv_transpose_3d.py 16 KB runs code
- examples/convolution/conv2d_with_bias_dilation_groups.py 14 KB runs code
- examples/convolution/conv3d_with_bias_dilation_groups.py 15 KB runs code
- examples/convolution/README.md 2.9 KB
- examples/matmul/matmul_4d_tensors.py 4.2 KB runs code
- examples/matmul/matrix_vector_multiplication.py 2.4 KB runs code
- examples/matmul/README.md 429 B
- examples/matmul/split_k_gemm.py 4.8 KB runs code
- examples/normalization/group_norm.py 5.5 KB runs code
- examples/normalization/README.md 241 B
- examples/pooling/avgpool3d.py 6.6 KB runs code
- examples/pooling/maxpool3d.py 7.3 KB runs code
- examples/pooling/README.md 121 B
- examples/scan/cumsum_cumprod_blocking.py 2.1 KB runs code
- examples/scan/README.md 116 B
- examples/tilegym_and_examples_guide.md 3.3 KB
- guidelines/01_implementation_lessons.md 8.1 KB
- guidelines/02_code_generation_rules.md 11 KB
- guidelines/03_concepts.md 4.7 KB
- orchestration/analyzer_agent.md 12 KB
- orchestration/composer_agent.md 11 KB
- orchestration/kernel_agent.md 7.3 KB
- orchestration/overview.md 9.7 KB
- orchestration/workflow.md 8.9 KB
- skill-card.md 5.1 KB
- skill.oms.sig 12 KB
- torch-learner/examples/lstm_trace.md 11 KB
- torch-learner/references/1_pytorch_codebase_map.md 8.9 KB
- torch-learner/references/2_dispatch_mechanism.md 8.9 KB
- torch-learner/references/3_tracing_strategies.md 8.8 KB
- torch-learner/references/4_language_layers.md 13 KB
- torch-learner/references/5_well_known_ops.md 11 KB
- torch-learner/tracing_workflow.md 7.2 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.
- 2d ago Changed 965c281a642d
- 1mo ago First seen · 351 lines · 43 tokens per session scan A 48cb2d85bf74
tilegym-cutile-python is a skill published in the GitHub repository NVIDIA/TileGym (827 stars, last pushed yesterday), with no licence file. It adds 43 tokens to every session and 4,452 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
typing-exclusion-worker
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.
python
Python development with ruff, mypy, pytest - TDD and type safety.