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 agentmods add skills/makio64/gpu-perf-agent/skillnpx skills add Makio64/gpu-perf-agent --skill skillgit clone --depth 1 https://github.com/Makio64/gpu-perf-agentWrote 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/makio64/gpu-perf-agent/skill)<a href="https://agentmods.dev/skills/makio64/gpu-perf-agent/skill"><img src="https://agentmods.dev/badge/skills/makio64/gpu-perf-agent/skill.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 | $0.00077 | $0.01819 |
| Opus 5 | $0.00039 | $0.00910 |
| Sonnet 5 | $0.00015 | $0.00364 |
| Haiku 4.5 | $0.00008 | $0.00182 |
Grade A, and why
gpu-perf-agent 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 3d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebGPU & WebGL2 Performance Profiling
Overview
Profile any WebGPU or WebGL2 web application to capture declared VRAM footprints (textures/buffers), frame metrics (average FPS, frame-time p95/variance), and CPU memory behavior (JS heap growth rate). The tool prints automated performance recommendations and supports comparative regression checks between a base and a candidate run.
Setup
The CLI ships in the gpu-perf-agent npm package (binary has the same name).
# One-off (no install):
npx gpu-perf-agent doctor
# Or install into the project:
npm install -D gpu-perf-agent
npx gpu-perf-agent doctor
The fast runner uses an installed Chrome/Chromium directly. If none is found, install one via npx playwright install chromium or point at a binary with --executable-path / CHROME_PATH.
All commands below assume gpu-perf-agent is on the path (via npx gpu-perf-agent ...). When working inside a checkout of the tool itself, node src/cli.js ... is equivalent.
Commands
1. doctor
Checks that the local system and headless Chrome support WebGPU/WebGL2. Always run this first.
npx gpu-perf-agent doctor
2. run
Profiles a local file or live URL.
--url <url>: target URL, or--file <path>: local HTML file (served over localhost automatically).--auto-instrument: injects tracking code that hooks buffer/texture allocations. Without it, tracked VRAM reads0.00 MiB.--samples <n>(default5) and--duration-ms <ms>(default1000): sampling shape.--trace: include a Chrome trace summary (GPU, frame, memory-infra events). Add--raw-traceto keep the raw trace file.--out <file>: destination for the JSON report.--chromium-arg=<arg>: extra Chromium flags, repeatable (e.g.--chromium-arg=--ignore-certificate-errors).--json: print a machine-readable{ out, verdict, summary, diagnostics }object to stdout — prefer this when running as an agent.--screenshot: capture a screenshot for visual validation.
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.
- 3d ago First seen · 118 lines · 77 tokens per session scan A 41e933431b01
gpu-perf-agent is a skill published in the GitHub repository Makio64/gpu-perf-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,819 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…