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 zystem-io/zymtrace-skills --skill optimize-cpu-workloadsgit 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/skills/zystem-io/zymtrace-skills/optimize-cpu-workloads)<a href="https://agentmods.dev/skills/zystem-io/zymtrace-skills/optimize-cpu-workloads"><img src="https://agentmods.dev/badge/skills/zystem-io/zymtrace-skills/optimize-cpu-workloads.svg" alt="Measured on agentmods" 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 | $0.00419 | $0.03562 |
| Opus 5 | $0.00210 | $0.01781 |
| Sonnet 5 | $0.00084 | $0.00712 |
| Haiku 4.5 | $0.00042 | $0.00356 |
Grade A, and why
optimize-cpu-workloads 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 7d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize CPU Workloads
The MCP fetches the data — hot traces, flamegraphs, host metrics, top functions, top entities; you analyze: name the hot stacks, identify the pattern, recommend and apply the fix.
For CPU-only deployments. This skill stays entirely on the CPU side — no GPU view, no GPU metrics, no inference-server (vLLM/SGLang/Triton) framing. A CPU-only customer never needs any of that. Running GPU workloads? Use optimize-gpu-workloads instead — there, cross-checking the GPU and CPU sides together is the load-bearing step.
The common discipline — data-source policy, pre-flight, rank-first vs. drill-down, scope-to-own-code/ROI, the always-recommend-and-apply-the-fix rule, the output-template skeleton, severity sizing, and security — lives in shared/analysis-conventions.md. Read it. This skill adds the CPU-specific profiles and call-tree rendering on top.
Connection setup lives in configure-zymtrace-mcp; this skill assumes the MCP is connected.
Standard starter prompts (for users who don't know what to ask)
"What's consuming the most CPU over the last 1 hour?" · "Which of my apps should I optimize first?"
Most CPU requests are rank-first (see the shared doc): the user wants to know which thing is hottest or where the best return is. Start by ranking with the MCP's topentities (hottest container/pod/host/process) or topfunctions (hottest functions), then drill into the top user-owned code with hot_traces. The recap leads with the ranking, then the analysis of that entry. If the user already named a workload ("analyze my API service"), skip the ranking and drill straight in.
Default to the last 1 hour if no range is given, and the whole cluster if no workload is named (ask which to narrow if results look noisy).
The CPU analysis protocol
The MCP pulls the data; you do the analysis. Establish a data path first (pre-flight, in the shared doc).
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.
- 7d ago First seen · 125 lines · 419 tokens per session scan A 061cd45b2b0f
optimize-cpu-workloads is a skill published in the GitHub repository zystem-io/zymtrace-skills (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 419 tokens to every session and 3,562 once invoked, about $0.0021 per session on Opus 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.
Other skills, from other repositories
test-amplification
Methodical bug-driven test amplification for pygraphistry features. Use when hardening a feature area via user-workflow exploration, 5-Whys retrospectives, bug-taxonomy derivation, concrete test planning, implementation, and safety-gated validation.
cuda-kernel-optimizer
Use when optimizing or diagnosing GPU workload performance with CUDA, CUTLASS, Triton, PyTorch, vLLM or TensorRT-LLM; interpreting NCU, Nsys or PyTorch Profiler evidence; or preparing the workload and correctness checks for such optimization. General coding, skill maintenance and conceptual GPU questions do not…
fix-ci
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
fix-ci
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.