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/archibate/dotfiles-claude/cpp-hpc-optimizationnpx skills add archibate/dotfiles-claude --skill cpp-hpc-optimizationgit clone --depth 1 https://github.com/archibate/dotfiles-claudeWhat 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 | $0.00107 | $0.02180 |
| Opus 5 | $0.00053 | $0.01090 |
| Sonnet 5 | $0.00021 | $0.00436 |
| Haiku 4.5 | $0.00011 | $0.00218 |
Grade A, and why
cpp-hpc-optimization 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 3d 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
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
60 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.
- agents/openai.yaml 226 B
- LICENSE 20 KB
- references/accelerator-throughput.md 8.8 KB
- references/allocation-and-memory-resources.md 18 KB
- references/data-layout-and-memory.md 30 KB
- references/hotpath-polymorphism.md 7.7 KB
- references/numerics-and-quantization.md 10.0 KB
- references/parallel101-case-studies.md 19 KB
- references/parallel101/course/04/3_pointers/01_pointer_aliasing/main.cpp 64 B
- references/parallel101/course/04/3_pointers/02_restrict_pointer/main.cpp 97 B
- references/parallel101/course/04/5_loops/01_worry_pointer_aliasing/main.cpp 102 B
- references/parallel101/course/04/5_loops/02_no_pointer_aliasing/main.cpp 124 B
- references/parallel101/course/04/5_loops/04_no_pointer_aliasing_ivdep/main.cpp 120 B
- references/parallel101/course/04/5_loops/06_loop_with_external_call/main.cpp 156 B
- references/parallel101/course/04/5_loops/07_loop_with_inlineable_call/main.cpp 159 B
- references/parallel101/course/04/5_loops/08_loop_with_random_access/main.cpp 97 B
- references/parallel101/course/04/5_loops/09_loop_with_skip_access/main.cpp 90 B
- references/parallel101/course/04/5_loops/10_loop_with_ordered_access/main.cpp 86 B
- references/parallel101/course/04/5_loops/11_loop_invariant_motion/main.cpp 149 B
- references/parallel101/course/04/5_loops/12_loop_invariant_failed/main.cpp 147 B
- references/parallel101/course/04/5_loops/13_loop_unrolling/main.cpp 106 B
- references/parallel101/course/04/6_structs/01_vec2_simd_ok/main.cpp 146 B
- references/parallel101/course/04/6_structs/02_vec3_simd_fail/main.cpp 159 B
- references/parallel101/course/04/6_structs/03_vec3_with_padding_ok/main.cpp 180 B
- references/parallel101/course/04/6_structs/04_vec3_with_alignas_ok/main.cpp 171 B
- references/parallel101/course/04/6_structs/05_vec3_aos/main.cpp 159 B
- references/parallel101/course/04/6_structs/06_vec3_soa/main.cpp 171 B
- references/parallel101/course/04/6_structs/07_vec3_aosoa/main.cpp 234 B
- references/parallel101/course/04/6_structs/08_benchmark/aos_aligned.cpp 248 B
- references/parallel101/course/04/6_structs/08_benchmark/aos_parallel.cpp 253 B
- references/parallel101/course/04/6_structs/08_benchmark/aos.cpp 219 B
- references/parallel101/course/04/6_structs/08_benchmark/aosoa.cpp 320 B
- references/parallel101/course/04/6_structs/08_benchmark/common.h 55 B
- references/parallel101/course/04/6_structs/08_benchmark/main.cpp 1.1 KB
- references/parallel101/course/04/6_structs/08_benchmark/profile.h 464 B
- references/parallel101/course/04/6_structs/08_benchmark/soa_parallel.cpp 259 B
- references/parallel101/course/04/6_structs/08_benchmark/soa_simd.cpp 247 B
- references/parallel101/course/04/6_structs/08_benchmark/soa_size_t.cpp 259 B
- references/parallel101/course/04/6_structs/08_benchmark/soa_unroll.cpp 347 B
- references/parallel101/course/04/6_structs/08_benchmark/soa.cpp 225 B
- references/parallel101/course/05/02_async/01/main.cpp 735 B
- references/parallel101/course/05/02_async/02/main.cpp 866 B
- references/parallel101/course/05/02_async/03/main.cpp 1.1 KB
- references/parallel101/course/05/02_async/04/main.cpp 758 B
- references/parallel101/course/05/02_async/05/main.cpp 753 B
- references/parallel101/course/05/02_async/06/main.cpp 840 B
- references/parallel101/course/06/02_reduce/03/main.cpp 536 B
- references/parallel101/course/06/02_reduce/04/main.cpp 550 B
- references/parallel101/course/06/02_reduce/08/main.cpp 692 B
- references/parallel101/course/06/05_split/01/main.cpp 565 B
- references/parallel101/course/06/05_split/02/main.cpp 563 B
- references/parallel101/course/06/05_split/03/main.cpp 723 B
- references/parallel101/course/06/05_split/04/main.cpp 677 B
- references/parallel101/course/06/05_split/05/main.cpp 659 B
- references/parallel101/course/06/07_filter/01/main.cpp 332 B
- references/parallel101/course/06/07_filter/01/ticktock.h 472 B
- references/parallel101/course/06/07_filter/02/main.cpp 533 B
- references/parallel101/course/06/07_filter/02/ticktock.h 472 B
- references/parallel101/course/06/07_filter/03/main.cpp 716 B
- references/parallel101/course/06/07_filter/03/ticktock.h 472 B
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.
- 3d ago First seen · 206 lines · 107 tokens per session scan A fd673efacbe9
cpp-hpc-optimization is a skill published in the GitHub repository archibate/dotfiles-claude (40 stars, last pushed 11d ago), with no licence file. It adds 107 tokens to every session and 2,180 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 2026-08-30.
Other skills, from other repositories
cuda-cpp-kernel
Use when writing, debugging, porting, reviewing, or optimizing CUDA C++ or PTX kernels; investigating CUDA Runtime or Driver API behavior; profiling kernels with Nsight Systems or Nsight Compute; or reasoning about Tensor Core instructions, shared memory, bank conflicts, occupancy, async copy, TMA, WGMMA, and…
cuda-skill
Query current NVIDIA CUDA, PTX ISA, Runtime API, Driver API, Programming Guide, Best Practices, Nsight Compute, and Nsight Systems references. Use for direct CUDA C++ or PTX work, and for framework tasks only when they need NVIDIA ISA, API, architecture, or tool facts. Triggers include inline PTX, WMMA, WGMMA, TMA…
blas_lapack
Complete CBLAS and LAPACKE C API reference (LAPACK v3.12.1) covering 1284 functions for numerical linear algebra: BLAS Level 1/2/3 vector and matrix operations, linear system solvers (LU, Cholesky, LDL), eigenvalue/eigenvector computation, singular value decomposition, least squares, QR/LQ factorizations, and…
opencl
OpenCL SDK (Khronos Group) for cross-platform GPU/CPU parallel computing in C and C++. Use when writing OpenCL kernels, managing devices/contexts/queues, allocating and transferring buffers or images, building and executing programs, or using the C++ wrapper (opencl.hpp / cl::CommandQueue, cl::Buffer…
cuda
NVIDIA CUDA parallel computing platform — use when writing .cu kernels, using cuBLAS/cuDNN/cuFFT/cuSPARSE/cuRAND/cuSolver, Thrust, or Cooperative Groups for GPU-accelerated computing.
matlab-generate-code
Generate, verify, refine, and accelerate C/C++ or CUDA code from MATLAB with MATLAB Coder, Embedded Coder, GPU Coder, or MATLAB Test. Also covers writing codegen-ready MATLAB code: language constraints, coder. directives, and optimization patterns. Triggers on: codegen, MEX, deploy MATLAB as C/C++, GPU Coder…