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 datathings/marketplace --skill blas_lapackgit clone --depth 1 https://github.com/datathings/marketplaceWrote 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/datathings/marketplace/blas_lapack)<a href="https://agentmods.dev/skills/datathings/marketplace/blas_lapack"><img src="https://agentmods.dev/badge/skills/datathings/marketplace/blas_lapack/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/datathings/marketplace/blas_lapack"><img src="https://agentmods.dev/badge/skills/datathings/marketplace/blas_lapack.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 | $0.00133 | $0.02974 |
| Opus 5 | $0.00067 | $0.01487 |
| Sonnet 5 | $0.00027 | $0.00595 |
| Haiku 4.5 | $0.00013 | $0.00297 |
Grade A, and why
blas_lapack 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CBLAS & LAPACKE API Reference
Complete C API documentation for BLAS (Basic Linear Algebra Subprograms) and LAPACK (Linear Algebra PACKage), version 3.12.1.
- 152 CBLAS functions - Level 1/2/3 vector and matrix operations
- 1,132 LAPACKE functions - Linear systems, eigenvalues, SVD, factorizations, and more
- Source of truth:
cblas.handlapacke.hfrom Reference-LAPACK v3.12.1
Quick Start
1. Include Headers
#include <cblas.h> // BLAS operations
#include <lapacke.h> // LAPACK operations
2. Compile and Link
# GCC/Clang
gcc myprogram.c -o myprogram -llapacke -llapack -lcblas -lblas -lm
# With pkg-config (if available)
gcc myprogram.c -o myprogram $(pkg-config --cflags --libs lapacke)
# With OpenBLAS (optimized)
gcc myprogram.c -o myprogram -lopenblas -lm
# With Intel MKL
gcc myprogram.c -o myprogram -lmkl_rt -lm
3. Typical Workflow
- Allocate matrices/vectors as flat arrays (row-major or column-major)
- Call CBLAS for basic operations (multiply, solve triangular, etc.)
- Call LAPACKE for advanced operations (factorize, solve systems, eigenvalues, SVD)
- Check
inforeturn value (0 = success, <0 = bad argument, >0 = numerical issue) - Free allocated memory
When to Use This Skill
- API Lookup: Find the right CBLAS/LAPACKE function for a specific operation
- Code Generation: Write correct C code using BLAS/LAPACK with proper parameters
- Linking Help: Resolve compilation/linking issues with BLAS/LAPACK libraries
- Solver Selection: Choose the right solver for your matrix type and problem
- Performance: Select optimized routines for specific matrix structures
Core Concepts
Precision Prefixes
Every routine comes in up to 4 precision types:
| Prefix | Type | C Type | Description |
|---|---|---|---|
s |
Single real | float |
32-bit floating point |
d |
Double real | double |
64-bit floating point |
c |
Single complex | void* (lapack_complex_float) |
2x32-bit complex |
z |
Double complex | void* (lapack_complex_double) |
2x64-bit complex |
What ships with it
10 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/blas-level1.md 39 KB
- references/blas-level2.md 42 KB
- references/blas-level3.md 31 KB
- references/lapacke-auxiliary.md 91 KB
- references/lapacke-eigenvalues.md 105 KB
- references/lapacke-factorizations.md 85 KB
- references/lapacke-least-squares.md 64 KB
- references/lapacke-linear-systems.md 91 KB
- references/lapacke-svd.md 66 KB
- references/workflows.md 58 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.
- 8d ago First seen · 248 lines · 133 tokens per session scan A 87784e451f72
blas_lapack is a skill published in the GitHub repository datathings/marketplace (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 133 tokens to every session and 2,974 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 2026-08-30.
Other skills, from other repositories
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
cuopt-developer
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
huawei-cloud-ascendc-operator-performance-optim
Develop and optimize custom operators using AscendC programming language. Analyze operator performance bottlenecks and conduct optimization validation. Based on AscendC and CANN toolkit Use this skill when the user wants to: (1) optimize performance-critical operators on Ascend NPU, (2) develop custom operators for…
torchtalk-analyzer
Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.
torchtalk-trace
Trace a PyTorch function's cross-language binding chain (Python -> C++ -> CUDA).
cuda-c-basics
A beginner’s guide to CUDA C, the C/C++ programming model for running work in parallel on NVIDIA GPUs. It covers kernels, threads, blocks, grids, and the GPU’s memory types.