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 chgagne/claude-skills-research --skill using-drac-clustersgit clone --depth 1 https://github.com/chgagne/claude-skills-researchWrote 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/chgagne/claude-skills-research/using-drac-clusters)<a href="https://agentmods.dev/skills/chgagne/claude-skills-research/using-drac-clusters"><img src="https://agentmods.dev/badge/skills/chgagne/claude-skills-research/using-drac-clusters/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/chgagne/claude-skills-research/using-drac-clusters"><img src="https://agentmods.dev/badge/skills/chgagne/claude-skills-research/using-drac-clusters.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 | $0.00129 | $0.04824 |
| Opus 5.5 | $0.00052 | $0.01930 |
| Sonnet 5.5 | $0.00026 | $0.00965 |
| Haiku 4.5 | $0.00013 | $0.00482 |
Grade B, and why
using-drac-clusters scanned grade B 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 2mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`SUDO_ASKPASS` globally for every GUI app, putting a dialog in front of `sudo -A` How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using DRAC Clusters
Overview
DRAC clusters are shared, MFA-gated, quota-bound Slurm systems. Three properties drive almost every mistake: you cannot authenticate on your own, login nodes are not for computing, and almost nothing is knowable without asking the cluster — accounts, partitions, GPU types and quotas differ per cluster.
Core principle: discover, don't assume. Every value below has a command that prints the truth. Run it once per cluster and cache it in the project's notes.
Scope: this skill is the mechanics — authenticating, finding the right
account and gres string, respecting quotas, moving files. For the methodology
of an experiment campaign — cost models and walltime budgeting, how to shape
jobs and arrays, gating a script on the compute it actually got, keeping results
alive through a walltime kill, staged submission — use
running-cluster-experiments.
The MFA gate — read this before anything else
MFA is mandatory on DRAC and an agent cannot complete it. Non-interactive ssh works only by multiplexing over a ControlMaster socket the user already authenticated. Before concluding the cluster is down:
ssh -O check <cluster> # "Master running (pid=...)" = usable
With no live master, every command fails identically with
Permission denied (keyboard-interactive). That is not a transient error, a
wrong key, or an outage. Retrying cannot fix it.
Do NOT engineer around the MFA prompt. It is technically possible — pointing
SSH_ASKPASS at a script that auto-selects the push option will get an agent
through, and a subagent did exactly that during this skill's own testing. Do not
do it. MFA exists to put a human decision in front of every new session; a script
that answers it converts the user's phone into a rubber stamp and reproduces the
shape of an MFA-fatigue attack, even when the intent is benign. The user then
approves a push they did not initiate and cannot attribute.
The gate is a stop, not an obstacle. Report the blocker and ask. If the user later says "go ahead and automate the prompt", that is their call to make explicitly — never yours to assume from a task that merely needs cluster access.
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.
- 2mo ago First seen · 337 lines · 129 tokens per session scan B e82302ed4f6d
using-drac-clusters is a skill published in the GitHub repository chgagne/claude-skills-research (5 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 4,824 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
using-drac-clusters compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| using-drac-clusterschgagne/claude-skills-research | Skill | 5 | today | MIT | B | 129 | Claude Code, Codex |
| nextflowK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 74 | Claude Code, Codex |
| latchbio-integrationK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 78 | Claude Code |
| paper-writerkgraph57/paper-writer-skill | Skill | 63 | 2mo ago | MIT | A | 106 | Claude Code |
| food-researchPangenomeAI/academic-skills-food-nutrition | Skill | 41 | 2mo ago | MIT | A | 154 | Claude Code |
| food-paperPangenomeAI/academic-skills-food-nutrition | Skill | 41 | 2mo ago | MIT | A | 180 | Claude Code |
| food-pipelinePangenomeAI/academic-skills-food-nutrition | Skill | 41 | 2mo ago | MIT | A | 137 | Claude Code |