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 ualberta-rcg/drac-agent-skills --skill alliance-cvmfsgit clone --depth 1 https://github.com/ualberta-rcg/drac-agent-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/ualberta-rcg/drac-agent-skills/alliance-cvmfs)<a href="https://agentmods.dev/skills/ualberta-rcg/drac-agent-skills/alliance-cvmfs"><img src="https://agentmods.dev/badge/skills/ualberta-rcg/drac-agent-skills/alliance-cvmfs/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/ualberta-rcg/drac-agent-skills/alliance-cvmfs"><img src="https://agentmods.dev/badge/skills/ualberta-rcg/drac-agent-skills/alliance-cvmfs.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 | $0.00076 | $0.02138 |
| Opus 5.5 | $0.00030 | $0.00855 |
| Sonnet 5.5 | $0.00015 | $0.00428 |
| Haiku 4.5 | $0.00008 | $0.00214 |
Grade A, and why
alliance-cvmfs 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 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.
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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alliance (DRAC) — CVMFS Software Stack
Software on Alliance clusters is served from CVMFS (read-only, network-mounted)
and accessed entirely through Lmod (module command). Login and compute nodes see
the same stack.
For cluster policies, storage limits, and account questions, check alliance-docs first.
/cvmfs/soft.computecanada.ca # Alliance software stack
/cvmfs/restricted.computecanada.ca # licensed software (MATLAB, etc.)
/cvmfs/containers.computecanada.ca # pre-built Apptainer/Singularity images
Discovery: always use module spider
Never guess versions. Module versions on CVMFS change; guessing one that doesn't
exist is the most common failure mode. Always confirm with module spider first.
module spider <name> # list all available versions
module spider <name>/<version> # show the exact prerequisite sequence to load it
The spider <name>/<version> output shows one or more valid "You will need to load"
lines. Pick one line and load it as a complete set — do not mix lines.
Why module avail is incomplete
Lmod is tiered. module avail only shows what the currently loaded modules have
unlocked; it will silently omit CUDA-tier packages (cuDNN, NCCL, etc.) until a
compiler and CUDA are already loaded. For discovery, use spider — it searches the
full tree regardless of what's loaded.
Core (always visible)
└── Compiler tier (unlocked after: gcc / intel / nvhpc)
└── CUDA tier (unlocked after: cuda)
└── MPI tier (unlocked after: openmpi / …)
StdEnv also loads a base stack (gcccore, UCX, OpenMPI, etc.). spider is the right
tool when you're not sure what tier a package lives in.
Discovery workflow
# 1. Find real versions for each component
module spider python
module spider gcc
module spider cuda
module spider cudnn
# 2. Get the exact prerequisite sequence for your chosen version
module spider cuda/<version>
module spider cudnn/<version>
# 3. Load the prescribed sequence, then verify
module load StdEnv/2023 gcc/<ver> cuda/<ver> python/<ver>
module list
which python && python --version
nvcc --version
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 · 264 lines · 76 tokens per session scan A 74f8edba7281
alliance-cvmfs is a skill published in the GitHub repository ualberta-rcg/drac-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,138 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
alliance-cvmfs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alliance-cvmfsualberta-rcg/drac-agent-skills | Skill | 2 | 1mo ago | MIT | A | 76 | Claude Code |
| gke-compute-classesgoogle/skills | Skill | 23k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 23k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 23k | yesterday | Apache-2.0 | A | 171 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 8d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |