hpclisted

# /hpc — launch work on the HPC cluster You run the `hpc` launcher yourself to put the user's work on the cluster. That is the point of the tool — do not hand commands to the user to run, unless asked. ## 1. Find the launcher 1. Look for its path in the user's global `~/.claude/CLAUDE.md`, under an `## hpc-launcher location` heading. 2. If it isn't there, discover it: run `command -v hpc` with the **Bash tool** (Git Bash) and take the directory of that path. If that fails, ask the user where the `hpc-launcher` folder is. 3. Record it so later calls skip discovery — append to `~/.claude/CLAUDE.md`: ``` ## hpc-launcher location The `hpc` launcher (for the /hpc skill) is at: `<path>` ``` Keep `<path>` `~`-relative when it's under home — that file is public, so a machine-specific absolute won't travel (and needlessly shows the username). ## 2. Read the launcher's own docs - `<path>/README.md` — what it does, setup, every command. **Always.** - `<path>/clusters/<HPC_CLUSTER>.md` — facts for the cluster this repo targets (`HPC_CLUSTER` in `.hpc.env`; `hpc clusters` lists them). Read it when running or configuring a job — partitions, filesystem, gotchas (e.g. Roihu's split login hosts + 24 h SSH cert). - `<path>/AGENTS.md`, `DESIGN.md`, `TODO.md` — only when you need rationale, limitations, or current status. Read the live files. Do not rely on remembered defaults (partitions, modules, torch module/wheel, walltimes) — they live in the clust