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 triton-ascend-case-reduction-amin-largegit 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/triton-ascend-case-reduction-amin-large)<a href="https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-case-reduction-amin-large"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-case-reduction-amin-large/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/triton-ascend-case-reduction-amin-large"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-case-reduction-amin-large.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 | $0.00090 | $0.00617 |
| Opus 5 | $0.00045 | $0.00309 |
| Sonnet 5 | $0.00018 | $0.00123 |
| Haiku 4.5 | $0.00009 | $0.00062 |
Grade A, and why
triton-ascend-case-reduction-amin-large 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 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.
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
极大规模 1D Amin 归约优化
任务特征
- 数据尺寸：(4194304,)，极大规模1D数据
优化 1：二次切分
pid = tl.program_id(0)
for start in range(0, BLOCK_SIZE, SUB_BLOCK_SIZE):
offsets = pid * BLOCK_SIZE + start + tl.arange(0, SUB_BLOCK_SIZE)
优化 2：计算重组
# 错误：简单
row_min = float('inf')
for n_start in range(0, BLOCK_SIZE, SUB_BLOCK_SIZE):
curr_min = tl.min(block_data)
row_min = tl.minimum(curr_min, row_min)
# 正确：优化
curr_min = tl.full((SUB_BLOCK_SIZE,), float('inf'), dtype=tl.float32)
for start in range(0, BLOCK_SIZE, SUB_BLOCK_SIZE):
curr_min = tl.minimum(curr_min, block_data)
min_val = tl.min(curr_min)
Autotune 配置
# （AI core=40）
# 1. grid=16<40, UB用满 -> 15.12 us
triton.Config({'BLOCK_SIZE': 262144, 'SUB_BLOCK_SIZE': 16384})
# 2. grid=32<40, UB用满 -> 9.61 us 最优
triton.Config({'BLOCK_SIZE': 131072, 'SUB_BLOCK_SIZE': 16384})
# 3. grid=32, UB未用满 -> 10.29 us
triton.Config({'BLOCK_SIZE': 131072, 'SUB_BLOCK_SIZE': 8192})
# 4. grid=40, UB用满, 有尾块 -> 10.17 us
triton.Config({'BLOCK_SIZE': 104858, 'SUB_BLOCK_SIZE': 16384})
# 5. grid=64>40, UB用满 -> 11.64 us
triton.Config({'BLOCK_SIZE': 65536, 'SUB_BLOCK_SIZE': 32768})
总结
网格数接近AI Core数量、UB用满、无尾块时性能最优。二次切分避免超出硬件缓存。
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 · 63 lines · 90 tokens per session scan A a362b601e2ea
triton-ascend-case-reduction-amin-large is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 617 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
text-transformer
Text encoding, decoding, and transformation utilities - Base64, URL, HTML, hashing, case conversion, and string manipulation.
triton-ascend-case-reduction-amin-atomic
A case study for optimizing amin reductions with atomic operations when the non-reduced dimension is small and the reduced dimension is very large. An amin reduction finds the smallest value.
triton-ascend-case-matmul-large-k
A case study for optimizing matrix multiplication when the shared K dimension is much larger than the output dimensions. It uses Split-K to divide that dimension across cores, then combines the partial results.
triton-ascend-case-elemwise-concat
A guide to combining slicing and concatenation operations in Triton Ascend kernels, which are GPU programs. It describes loading only needed data and calculating joined indexes without a separate concatenation step.
triton-ascend-case-index-histogram
A case study for speeding up histogram calculations, which count how many values fall into each group or range.
triton-ascend-case-matmul-swizzle2d
A case study for optimizing matrix multiplication in Triton on Ascend hardware using 2D block swizzling and a fixed number of cores.