Guidance for building, reviewing, debugging, and tuning hypre-based sparse solvers. hypre is a software library for solving large systems of mathematical equations, often across many computers.

Use it with hypre's IJ, Struct, or SStruct interfaces, BoomerAMG, Krylov solvers, MPI-distributed systems, PETSc integrations, and build or runtime failures.

It helps choose the right matrix interface, solver, preconditioner, data ownership, and parallel setup instead of treating every hypre problem the same way.

hpc-hypre — Skill for Codex by SciMate-AI

Install

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.

Any agent

npx skills add SciMate-AI/HPC-Skills --skill hpc-hypre

Clone the repo

git clone --depth 1 https://github.com/SciMate-AI/HPC-Skills

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/scimate-ai/hpc-skills/hpc-hypre/github.svg)](https://agentmods.dev/skills/scimate-ai/hpc-skills/hpc-hypre)

Your own site

<a href="https://agentmods.dev/skills/scimate-ai/hpc-skills/hpc-hypre"><img src="https://agentmods.dev/badge/skills/scimate-ai/hpc-skills/hpc-hypre/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/scimate-ai/hpc-skills/hpc-hypre"><img src="https://agentmods.dev/badge/skills/scimate-ai/hpc-skills/hpc-hypre.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 818 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00069	$0.00818
Opus 5	$0.00034	$0.00409
Sonnet 5	$0.00014	$0.00164
Haiku 4.5	$0.00007	$0.00082

Measured 11d ago against content hash 9d2301be4d67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hpc-hypre 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 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (assets/templates/hypre_build_example.sh, assets/templates/hypre_ij_slurm.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/hpc-hypre/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HPC hypre

Treat hypre as a solver-library family with distinct matrix interfaces and multigrid-heavy preconditioning workflows.

Start

Read references/interface-selection.md before creating or repairing a hypre solve path.
Read references/matrix-and-ownership-playbook.md when choosing row ownership, indexing, or assembly discipline.
Read references/boomeramg-and-krylov-playbook.md when choosing BoomerAMG, Krylov solvers, or a first stable parameter set.
Read references/boomeramg-parameter-matrix.md when changing coarsening, interpolation, smoothing, or cycle choices.
Read references/krylov-and-preconditioner-matrix.md when the operator class does not fit the default PCG plus BoomerAMG baseline.
Read references/structured-and-sstruct-playbook.md when the problem is logically structured or semi-structured.
Read references/build-and-integration.md when building hypre directly or consuming it through PETSc or another host code.
Read references/error-recovery.md when setup, solve, or parallel behavior fails.

Work sequence

Classify the discretization storage first:
- general sparse assembled system -> IJ
- structured grid with regular stencil semantics -> Struct
- mostly structured with coupled variable blocks or irregular pieces -> SStruct
Choose a baseline solver pair that matches the operator:
- SPD-like problems -> PCG with BoomerAMG
- general nonsymmetric problems -> GMRES or FlexGMRES with BoomerAMG as the preconditioner
Get the baseline solve working before changing coarsening, interpolation, or relaxation details.
Keep distributed row ownership and matrix assembly consistent across ranks.

Guardrails

Do not use the structured interfaces when the data model is really an unstructured sparse matrix.
Do not start by over-tuning BoomerAMG; defaults are the first checkpoint.
Do not debug multigrid parameters before confirming the operator, nullspace, and boundary conditions are coherent.
Do not assume host applications expose every hypre knob unless the integration layer documents it.

Read the full file on GitHub · 69 lines

Files

What ships with it

13 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.

Changes

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.

11d ago First seen · 69 lines · 69 tokens per session scan A 9d2301be4d67

Subscribe to this mod's changes

hpc-hypre is a skill published in the GitHub repository SciMate-AI/HPC-Skills (86 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 818 once invoked, about $0.0003 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.

Debugging Scientific

trace

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode.

Yeachan-Heo/oh-my-claudecode · 18 tokens

smiles-validation

Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.

synthetic-sciences/openscience · 24 tokens

social-physics-filter

Unified boundary enforcement, interpersonal diagnostic, and relational audit engine. Absorbs 40 psychology + 2 social protocols and all relationship case studies.

winstonkoh87/Athena-Public · 34 tokens

cnsplots

Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise physical figure dimensions…

faridrashidi/cnsplots · 79 tokens

relax-dev-debug

Develop and debug the Relax reinforcement learning project. Use this skill whenever modifying code in the relax/ directory, or running remote training jobs on a Ray cluster for validation. Also use it when the user mentions training, debugging training runs, submitting Ray jobs, or fixing training errors.

redai-infra/Relax · 60 tokens

anomaly-characterization

SOP: Describe and classify anomalous phenomena that existing theory cannot explain.

yogsoth-ai/de-anthropocentric-research-engine · 19 tokens