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/pto-isa/supernpubench/workflownpx skills add PTO-ISA/SuperNPUBench --skill workflowgit clone --depth 1 https://github.com/PTO-ISA/SuperNPUBenchWrote 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/pto-isa/supernpubench/workflow)<a href="https://agentmods.dev/skills/pto-isa/supernpubench/workflow"><img src="https://agentmods.dev/badge/skills/pto-isa/supernpubench/workflow.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 | $0.00157 | $0.03952 |
| Opus 5 | $0.00078 | $0.01976 |
| Sonnet 5 | $0.00031 | $0.00790 |
| Haiku 4.5 | $0.00016 | $0.00395 |
Grade B, and why
linx-bench-workflow scanned grade B with 1 finding 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Linux: `sudo apt-get install -y git make cmake ninja-build gcc g++ python3 autoconf m4` 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
1 file 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.
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.
- 4d ago First seen · 385 lines · 157 tokens per session scan B 7bc74be99b2b
linx-bench-workflow is a skill published in the GitHub repository PTO-ISA/SuperNPUBench (11 stars, last pushed 6d ago), with no licence file. It adds 157 tokens to every session and 3,952 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
add-uint-support
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
at-dispatch-v2
Convert PyTorch ATDISPATCH macros to ATDISPATCHV2 format in ATen C++ code. Use when porting ATDISPATCHALLTYPESAND, ATDISPATCHFLOATINGTYPES, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
sqlitecpp-doxygen-guide
SQLiteCpp Doxygen standards and templates for public API docs and file headers.
cuda-index-width
Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64t, canUse32BitIndexMath, CUDAKERNELLOOPTYPE, or ATDISPATCHINDEXTYPES, and when considering binary-size or performance impact of index-type templating.
cpu-kernels
Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes a two-phase workflow: Phase 1 correctness (generic → AVX2) and Phase 2 performance exploration (AVX512 with branching trial loop), runtime CPU dispatch, OpenMP…
qiskit-to-cudaq
Use when porting Qiskit Python circuits to CUDA-Q kernels while preserving algorithms and validation fidelity.