cli-anything-nsight-graphics

cli-anything-nsight-graphics is a skill for Claude Code, Codex from HKUDS/CLI-Anything. It costs 29 tokens per session (961 once invoked), scanned A, original, Apache-2.0.

A Windows-focused command-line tool for NVIDIA Nsight Graphics, a program used to capture and inspect how applications use a graphics processor (GPU). It can launch or attach to applications, collect captures and GPU traces, and summarize or analyze them.

In plain words
What is it for?
Use it to capture frames, run GPU Trace, inspect .ngfx-capture files, attach to a running process, and generate C++ capture code.
Why use it?
It avoids performing graphics diagnostics manually in the Nsight interface and provides compatibility information when capture files cannot be analyzed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to capture frames, run GPU Trace, inspect .ngfx-capture files, attach to a running process, and generate C++ capture code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hkuds/cli-anything/cli-anything-nsight-graphics
About the project

CLI-Anything turns software and services into command-line interfaces that AI agents can use to perform tasks and produce artifacts. It is intended for people building or using agent workflows with tools such as coding assistants, design software, and other applications. The catalogue entries are skills, commands, a plugin, and a rule for working with CLI-Anything.

HKUDS/CLI-Anything · 52,110 stars · on GitHub · clianything.cc

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.

Any agent
npx skills add HKUDS/CLI-Anything --skill cli-anything-nsight-graphics
Clone the repo
git clone --depth 1 https://github.com/HKUDS/CLI-Anything

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for cli-anything-nsight-graphics

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/cli-anything/cli-anything-nsight-graphics/github.svg)](https://agentmods.dev/skills/hkuds/cli-anything/cli-anything-nsight-graphics)
Your own site
<a href="https://agentmods.dev/skills/hkuds/cli-anything/cli-anything-nsight-graphics"><img src="https://agentmods.dev/badge/skills/hkuds/cli-anything/cli-anything-nsight-graphics/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.

agentmods 80×15 button for cli-anything-nsight-graphics

Your own site · 80×15
<a href="https://agentmods.dev/skills/hkuds/cli-anything/cli-anything-nsight-graphics"><img src="https://agentmods.dev/badge/skills/hkuds/cli-anything/cli-anything-nsight-graphics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 961 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 5.1 $0.00029 $0.00961
Opus 5.5 $0.00012 $0.00384
Sonnet 5.5 $0.00006 $0.00192
Haiku 4.5 $0.00003 $0.00096

Measured 21d ago against content hash 5cd2df20fb09, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cli-anything-nsight-graphics 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 21d 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.

skills/cli-anything-nsight-graphics/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nsight Graphics CLI Skill

Command-line orchestration of official NVIDIA Nsight Graphics activities.

Capabilities

  • Probe installed Nsight binaries and compatibility mode
  • Launch an application detached under Nsight
  • Attach Nsight to a running PID
  • Trigger Graphics Capture or OpenGL Frame Debugger capture
  • Trigger GPU Trace capture, auto-export, and summarize
  • Analyze existing .ngfx-capture files through ngfx-replay
  • Report clear compatibility diagnostics for .ngfx-gputrace inputs
  • Trigger Generate C++ Capture

Commands

doctor

cli-anything-nsight-graphics --json doctor info
cli-anything-nsight-graphics --json doctor versions
cli-anything-nsight-graphics --nsight-path "C:\Path\To\Nsight Graphics 2024.2\host\windows-desktop-nomad-x64" --json doctor info

launch

cli-anything-nsight-graphics launch detached --activity "Graphics Capture" --exe "C:\Path\To\App.exe"
cli-anything-nsight-graphics launch attach --activity "Graphics Capture" --pid 12345

frame capture

cli-anything-nsight-graphics --output-dir D:\captures frame capture ^
  --exe "C:\Path\To\App.exe" ^
  --wait-frames 10

GPU Trace

cli-anything-nsight-graphics --output-dir D:\traces gpu-trace capture ^
  --exe "C:\Path\To\App.exe" ^
  --start-after-ms 1000 ^
  --limit-to-frames 1 ^
  --auto-export ^
  --summarize

cli-anything-nsight-graphics gpu-trace summarize ^
  --input-dir D:\traces

Replay analysis

cli-anything-nsight-graphics --json replay analyze ^
  --capture-file D:\captures\frame.ngfx-capture ^
  --output-dir D:\analysis

Generate C++ Capture

cli-anything-nsight-graphics --output-dir D:\cpp cpp capture ^
  --exe "C:\Path\To\App.exe" ^
  --wait-seconds 5

Agent Notes

  • Prefer doctor info first to discover the available compatibility mode.
  • Use doctor versions to list detected installs when multiple Nsight Graphics versions exist.
  • Use --nsight-path to force a specific install directory or ngfx.exe.
  • Use --json for programmatic workflows.
  • Prefer gpu-trace capture --auto-export --summarize for one-step performance triage. The summary includes exported table inventory, metric inventory, frame-budget classification, workload classification, throughput ranking, bottleneck hints, and warnings for empty event/regime tables.
  • Use replay analyze when the input is an existing .ngfx-capture file. With no analysis switches it exports metadata, logs, captured log errors, and a replay performance report, then adds structured analysis.highlights / analysis.warnings.
  • ngfx-replay documents its input as a Graphics Capture file. .ngfx-gputrace inputs are accepted for clear diagnostics, but on Nsight Graphics 2026.1.0 they may report Invalid file header; use gpu-trace summarize for exported GPU Trace table analysis.
  • replay analyze uses official ngfx-replay metadata/log/screenshot/perf-report outputs; it is not a RenderDoc-style shader, pipeline, texture, or resource inspector.
  • Frame/GPU/C++ capture commands require a launch target through --exe or a preconfigured root-level --project.
  • If a global cli-anything-nsight-graphics command points at an old worktree, reinstall from nsight-graphics/agent-harness with python -m pip install -e ..

Read the full file on GitHub · 111 lines

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. 21d ago First seen · 111 lines · 29 tokens per session scan A 5cd2df20fb09

Subscribe to this mod's changes

cli-anything-nsight-graphics is a skill published in the GitHub repository HKUDS/CLI-Anything (52,110 stars, last pushed 22d ago), licensed Apache-2.0. It adds 29 tokens to every session and 961 once invoked, about $0.0001 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 2026-09-23.

Related

Other skills, from other repositories

profiling

Diagnose frame-rate bottlenecks (CPU vs GPU bound FIRST), control Unreal Insights traces, sample live frame times, and annotate performance captures. Use when FPS is low/bad, the game is slow, or you need to find what is limiting the frame rate.

kevinpbuckley/VibeUE · 57 tokens

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…

troycheng/cuda-kernel-optimizer · 77 tokens

minecraft-debug-mcp

Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…

moeru-ai/airi · 68 tokens

console-get-logs

Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.

IvanMurzak/Unity-MCP · 35 tokens

editor-application-get-state

Return the current state of UnityEditor.EditorApplication — playmode, paused state, compilation state, and related flags.

IvanMurzak/Unity-MCP · 31 tokens

unity-console

Capture and query the Unity Editor console.

Besty0728/Unity-Skills · 10 tokens