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 lkaesberg/gwdg-gipplab-skill --skill gwdg-hpcgit clone --depth 1 https://github.com/lkaesberg/gwdg-gipplab-skillWrote 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/lkaesberg/gwdg-gipplab-skill/gwdg-hpc)<a href="https://agentmods.dev/skills/lkaesberg/gwdg-gipplab-skill/gwdg-hpc"><img src="https://agentmods.dev/badge/skills/lkaesberg/gwdg-gipplab-skill/gwdg-hpc/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/lkaesberg/gwdg-gipplab-skill/gwdg-hpc"><img src="https://agentmods.dev/badge/skills/lkaesberg/gwdg-gipplab-skill/gwdg-hpc.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 | $0.00278 | $0.04558 |
| Opus 5 | $0.00139 | $0.02279 |
| Sonnet 5 | $0.00056 | $0.00912 |
| Haiku 4.5 | $0.00028 | $0.00456 |
Grade C, and why
gwdg-hpc scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
IdentityFile ~/.ssh/id_ed25519 How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GWDG HPC: Emmy & Grete (SCC / KISSKI / NHR / REACT)
The mental model (read this first)
There is one unified HPC system in Göttingen, operated by GWDG. It is not three separate clusters. It is made of compute "islands":
- Emmy — the CPU islands (Emmy Phase 1/2/3), e.g. Intel Sapphire Rapids and Cascade Lake nodes.
- Grete — the GPU islands (Grete Phase 1/2/3), with Nvidia V100 / A100 / H100 GPUs.
- Plus the older SCC Legacy island and a few group-restricted islands (CIDBN, FG, SOE).
SCC, KISSKI, NHR, and REACT are not different machines — they are different account types on this shared system. The account type is the single most important fact, because it determines three things at once:
- which login nodes you can reach,
- which filesystems ($HOME, scratch) you land on, and
- which Slurm partitions you are allowed to submit to.
So the first job is always to figure out what kind of account the user has, and then read everything else off that. Do not assume; a user may have several accounts (e.g. an SCC account and an NHR project).
The default software environment everywhere is the gwdg-lmod Lmod module stack.
Step 1 — Establish the account type
If it isn't already clear from the conversation, determine it. Signals:
- Username shape. A Project-Portal username looks like
u12345(aufollowed by five digits) and is project-specific — each project the user belongs to is a separate account with its own storage and allocation. The user's AcademicID (the name they use for other GWDG services) cannot be used for SSH (the only exception is the storage transfer nodes). - Legacy usernames (being phased out, must be migrated): a name-based login
like
jdoe,john.doe2,doe15is a legacy SCC user; a login likenimjdoe/hbbmustr(3 letters, 2 of them the German state code, then 5 chosen characters) is a legacy NHR/HLRN user. - Project Portal tree. In https://hpcproject.gwdg.de, the project's path
reveals the type:
Projects / Scientific Compute Cluster (SCC)→ SCC;Projects / Extern / KISSKI→ KISSKI;Projects / Extern / NHR-NORD@Göttingen→ NHR;Projects / Extern / EFRE-REACT …→ REACT (CIDAS and Research Units are treated like NHR). - On the cluster itself,
show-quotalists the data stores assigned to the current user, and the login banner shows which partitions are available.
What ships with it
6 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.
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.
- 12d ago First seen · 336 lines · 278 tokens per session scan C ca118534d561
gwdg-hpc is a skill published in the GitHub repository lkaesberg/gwdg-gipplab-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 278 tokens to every session and 4,558 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
exploring-data
Exploratory data analysis. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Small files get ydata-profiling HTML/JSON reports; large files (over 200MB or 5M rows) get fixed-memory DuckDB/sketch profiling. Also covers near-duplicate row…
math-modeling-solver
A Chinese-language guide for solving mathematical modeling competition problems. It covers China’s CUMCM and America’s MCM/ICM, where teams use mathematics and code to answer real-world problem statements.
duan-jianye
A Chinese-language skill for discussing Bazi, a traditional Chinese birth-chart system, from Duan Jianye’s blind-school interpretation style. It reads the chart as symbolic scenes and relationships rather than starting with fixed categories or rules.
mathmodel-skill
An end-to-end workflow for mathematical-modeling competitions, including CUMCM, MCM/ICM, and the Electrical Cup. It guides teams from choosing a problem through modeling, solving, checking, writing, rule compliance, and final review.