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 mindspore-ai/akg --skill pypto-case-norm-layernormgit clone --depth 1 https://github.com/mindspore-ai/akgWrote 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/mindspore-ai/akg/pypto-case-norm-layernorm)<a href="https://agentmods.dev/skills/mindspore-ai/akg/pypto-case-norm-layernorm"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/pypto-case-norm-layernorm/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/mindspore-ai/akg/pypto-case-norm-layernorm"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/pypto-case-norm-layernorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00539 |
| Opus 5 | $0.00021 | $0.00269 |
| Sonnet 5 | $0.00008 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
pypto-case-norm-layernorm 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 11d 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.
What it actually says
模式 C-1：2D Norm — LayerNorm
forward 中 reshape(batch, -1) 降为 2D，kernel 沿 batch 维 loop。
BASIC_BATCH = 4
def create_layernorm_kernel(batch, hidden, eps):
@pypto.frontend.jit(runtime_options=..., debug_options=...)
def kernel(
x: pypto.Tensor((batch, hidden), pypto.DT_FP32),
) -> pypto.Tensor((batch, hidden), pypto.DT_FP32):
output = pypto.tensor([batch, hidden], pypto.DT_FP32)
num_iters = ceil_div(batch, BASIC_BATCH)
pypto.set_vec_tile_shapes(1, 16384)
inv_h = 1.0 / hidden
for bi in pypto.loop(0, num_iters, 1, name="LOOP_LN", idx_name="bi"):
offset = bi * BASIC_BATCH
x_chunk = pypto.view(x, [BASIC_BATCH, hidden], [offset, 0])
mean = pypto.sum(x_chunk, dim=1, keepdim=True) * inv_h
var = pypto.sum(x_chunk * x_chunk, dim=1, keepdim=True) * inv_h - mean * mean
normed = (x_chunk - mean) / pypto.sqrt(var + eps)
pypto.assemble(normed, [offset, 0], output)
return output
return kernel
forward：reshape(B, -1) → kernel → reshape(x.shape)
GroupNorm 同模式：forward 中 reshape(B*G, -1) → 2D kernel。
模式要点
pypto.sum(dim=int)— dim 只能传单个 int- mean =
sum * (1/size)— 没有 mean API - 方差 =
E[x²] - E[x]²— 两次 sum 实现 set_vec_tile_shapes(1, 16384)— 2D，第一维小批量，第二维大 tile
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.
- 11d ago First seen · 47 lines · 42 tokens per session scan A 5f761d0a759f
pypto-case-norm-layernorm is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 539 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
triton-cuda-examples-torch
A set of complete examples showing how Triton CUDA kernels work inside PyTorch, including vector addition, matrix multiplication, layer normalization, and softmax.
triton-ascend-examples-mindspore
Integration examples for using Triton Ascend kernels inside MindSpore, a machine-learning framework. They show how to register a custom operation and pass tensors in and out.
pypto-case-norm-batchnorm
A worked example of BatchNorm, a machine-learning step that normalizes values in groups, for three-dimensional data. It demonstrates reducing dimensions, summing across several axes, and copying values across expanded dimensions.
pypto-case-loss-crossentropy
An example of implementing cross-entropy loss, a calculation commonly used to measure classification errors. It covers multiple inputs, tiled processing, softmax, selecting target values, summing, and producing one scalar result.
pypto-case-norm-layernorm
A PyPTO example showing how LayerNorm normalises values across a two-dimensional input using a loop. LayerNorm is a machine-learning operation that rescales values to help a model process them consistently.
pypto-case-elemwise-gelu
A PyPTO example for applying the GELU activation function element by element to a one-dimensional array. It demonstrates flattening, a hand-written formula without tanh, and operator use.