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.
/plugin marketplace add zystem-io/zymtrace-skillsnpx agentmods add plugins/zystem-io/zymtrace-skills/zymtracegit clone --depth 1 https://github.com/zystem-io/zymtrace-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/plugins/zystem-io/zymtrace-skills/zymtrace)<a href="https://agentmods.dev/plugins/zystem-io/zymtrace-skills/zymtrace"><img src="https://agentmods.dev/badge/plugins/zystem-io/zymtrace-skills/zymtrace.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
zymtrace 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 4d 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.
This is a copy
86% identical to zymtrace-skills marketplace — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "zymtrace",
"description": "Detect and optimize CPU and GPU workload bottlenecks with zymtrace continuous profiling — analyze flamegraphs through the MCP, plus install, upgrade, expose, and troubleshoot the platform.",
"version": "26.8.2",
"author": {
"name": "Zymtrace",
"email": "[email protected]",
"url": "https://zymtrace.com"
},
"homepage": "https://zymtrace.com",
"repository": "https://github.com/zystem-io/zymtrace-skills"
}
What it installs
The manifest is a name and a version. 10 skills, 1 agent travel with it, and installing the plugin installs all of them — 2,815 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill install-zymtrace-backend A 164 tokens
- Skill upgrade-zymtrace-backend A 143 tokens
- Skill install-zymtrace-profiler A 200 tokens
- Skill optimize-cpu-workloads A 419 tokens
- Skill expose-zymtrace-backend A 160 tokens
- Skill optimize-gpu-workloads A 398 tokens
- Skill optimize-memory-allocation A 411 tokens
- Skill troubleshoot-zymtrace-backend A 165 tokens
- Skill troubleshoot-zymtrace-profiler B 180 tokens
- Skill configure-zymtrace-mcp C 192 tokens
- Agent zymtrace-perf-engineer A 383 tokens
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.
- 4d ago First seen · 13 lines scan A 0cd3a7895a6e
zymtrace is a plugin published in the GitHub repository zystem-io/zymtrace-skills (5 stars, last pushed 21d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 86% identical to zymtrace-skills marketplace, differing in 20 lines, and is treated as a copy.
Other plugins, from other repositories
lepton-cli
Operate NVIDIA DGX Cloud Lepton through the globally installed lep CLI.
VeloQ
Agent-friendly GPU profile-query CLI.
skypilot
SkyPilot agent skill for launching cloud VMs, Kubernetes pods, and Slurm jobs across 25+ clouds.
gpu-server-setup
Prepare a Linux server with NVIDIA GPUs for LLM and neural-network workloads: NVIDIA driver + CUDA from the official repo, Docker Engine + NVIDIA Container Toolkit as the mandatory base, GPU passthrough into containers, staged verification gates, optional docker-compose presets for vLLM, Infinity, OpenWebUI and Ollama.
vmware-privateai
VMware Private AI (NVIDIA): GPU inventory, vGPU profiles, utilization, model serving — 17 tools.
gcloud-gpu-agent
Launch Google Cloud GPU VMs (L4/A100/H100) and run code on them over SSH, straight from Claude Code.