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 SciMate-AI/HPC-Skills --skill hpc-toolchainsgit clone --depth 1 https://github.com/SciMate-AI/HPC-SkillsWrote 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/scimate-ai/hpc-skills/hpc-toolchains)<a href="https://agentmods.dev/skills/scimate-ai/hpc-skills/hpc-toolchains"><img src="https://agentmods.dev/badge/skills/scimate-ai/hpc-skills/hpc-toolchains/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/scimate-ai/hpc-skills/hpc-toolchains"><img src="https://agentmods.dev/badge/skills/scimate-ai/hpc-skills/hpc-toolchains.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00078 | $0.00810 |
| Opus 5 | $0.00039 | $0.00405 |
| Sonnet 5 | $0.00016 | $0.00162 |
| Haiku 4.5 | $0.00008 | $0.00081 |
Grade A, and why
hpc-toolchains 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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HPC Toolchains
Treat the toolchain as a coherent stack. Pick the compiler family, MPI family, math libraries, and build system together before tuning application-specific flags.
Start
- Read
references/compiler-family-selection.mdbefore choosing GCC, Clang, or vendor compilers. - Read
references/configure-and-build-matrix.mdwhen deciding between CMake, Make, Ninja, or wrapper-driven builds. - Read
references/cmake-and-find-package-playbook.mdwhen writing or repairingCMakeLists.txt,find_package, imported targets, or cache variables. - Read
references/toolchain-files-and-presets.mdwhen the build depends on reusable compiler, MPI, or site configuration. - Read
references/build-type-and-abi-hygiene.mdwhen debugging release versus debug mismatches, C++ standard mismatches, symbol issues, or ABI drift. - Read
references/blas-lapack-mpi-consistency.mdwhen linking against BLAS, LAPACK, ScaLAPACK, MPI, or vendor math stacks. - Read
references/modules-and-spack-playbook.mdwhen using environment modules, compiler wrappers, external packages, or Spack environments. - Read
references/error-recovery.mdwhen configure, compile, link, or runtime-loader failures occur.
Work sequence
- Decide the stack boundary first:
- site-provided modules
- Spack environment
- container image
- user-local source build
- Pick one compiler family and keep the full dependency graph aligned to it.
- Decide how dependencies are discovered:
- wrapper compilers
find_packagepkg-config- explicit include and library paths only as a last resort
- Keep build directories, cache state, and install prefixes separated by toolchain.
- Record the exact configure command before tuning warning or optimization flags.
Guardrails
- Do not mix compiler and MPI families casually across one build tree.
- Do not patch over a bad discovery path with many ad hoc include and library flags.
- Do not treat ABI, C++ standard, and release or debug mode as cosmetic metadata.
- Do not let one dependency come from a different module stack unless the site explicitly supports that mix.
What ships with it
15 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 255 B
- assets/templates/build-smoke-slurm.sh 699 B runs code
- assets/templates/configure-gcc-openmpi.sh 459 B runs code
- assets/templates/minimal-cmake-project/CMakeLists.txt 254 B
- assets/templates/minimal-cmake-project/main.cpp 319 B
- assets/templates/spack-env-minimal.yaml 91 B
- references/blas-lapack-mpi-consistency.md 970 B
- references/build-type-and-abi-hygiene.md 1.2 KB
- references/cmake-and-find-package-playbook.md 1.4 KB
- references/compiler-family-selection.md 1.4 KB
- references/configure-and-build-matrix.md 1.2 KB
- references/error-pattern-dictionary.md 1.5 KB
- references/error-recovery.md 1.1 KB
- references/modules-and-spack-playbook.md 1.0 KB
- references/toolchain-files-and-presets.md 1.0 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.
- 10d ago First seen · 74 lines · 78 tokens per session scan A bcc0a6781326
hpc-toolchains is a skill published in the GitHub repository SciMate-AI/HPC-Skills (85 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 810 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…