caddis-plugin gpu.instructions.md

Instructions for using graphics processors (GPUs) in artificial-intelligence and machine-learning work.

In plain words
What is it for?
GPU computing patterns for AI and machine-learning projects.
Why use it?
It helps guide code that uses GPUs for these workloads, though the description does not say which tasks or tools it covers.

Instructions file for GitHub Copilot

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.

agentmods
npx agentmods add instructions/saajunaid/caddis-plugin/gpu
Clone the repo
git clone --depth 1 https://github.com/saajunaid/caddis-plugin

Made for: GitHub Copilot.

Per session 2,386 This file is loaded in full into every session.
When invoked 2,386 The same file — it is already loaded in full.
Security scan C 3 findings. Scan, not verified.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5 $0.02386 $0.02386
Opus 5 $0.01193 $0.01193
Sonnet 5 $0.00477 $0.00477
Haiku 4.5 $0.00239 $0.00239

Measured yesterday against content hash 052c7a1641af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

caddis-plugin gpu.instructions.md scanned grade C with 3 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 yesterday.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl https://ollama.ai/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://ollama.ai/install.sh | sh

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(
.github/instructions/gpu.instructions.md · 404 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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.

  1. yesterday First seen · 404 lines · 2,386 tokens per session scan C 052c7a1641af

Subscribe to this mod's changes

caddis-plugin gpu.instructions.md is an instructions file published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 4d ago), with no licence file. It adds 2,386 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it C with 3 findings (downloads and executes remote code, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.