graphsignal-profiler

graphsignal-profiler is a skill for Claude Code from skillmds/skillmd. It costs 74 tokens per session (1,777 once invoked), scanned A, a copy of graphsignal-profiler, MIT.

A profiler for measuring and tracing machine-learning inference workloads, which are the tasks of running a trained model to produce results. It watches GPU services from outside the application and supports vLLM, SGLang, PyTorch, and dstack.

In plain words
What is it for?
Use it to profile inference services, collect traces and metrics, and connect GPU observations to monitoring systems such as Prometheus or OTLP.
Why use it?
It helps investigate GPU usage and inference performance without placing the profiler inside the same CUDA process as the workload.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agents-mcp plugin — 34 skills shipped together

Good fit Use it to profile inference services, collect traces and metrics, and connect GPU observations to monitoring systems such as Prometheus or OTLP.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skillmds/skillmd/graphsignal-profiler
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 skillmds/skillmd --skill graphsignal-profiler
Clone the repo
git clone --depth 1 https://github.com/skillmds/skillmd

Made for: Claude Code.

Or install agents-mcp, the plugin that ships this one along with the rest of its 34 skills.

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 graphsignal-profiler

README.md
[![agentmods](https://agentmods.dev/badge/skills/skillmds/skillmd/graphsignal-profiler/github.svg)](https://agentmods.dev/skills/skillmds/skillmd/graphsignal-profiler)
Your own site
<a href="https://agentmods.dev/skills/skillmds/skillmd/graphsignal-profiler"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/graphsignal-profiler/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 graphsignal-profiler

Your own site · 80×15
<a href="https://agentmods.dev/skills/skillmds/skillmd/graphsignal-profiler"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/graphsignal-profiler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00074 $0.01777
Opus 5.5 $0.00030 $0.00711
Sonnet 5 $0.00015 $0.00355
Haiku 4.5 $0.00007 $0.00178

Measured 4d ago against content hash 5a4a8446bac7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-23, from the pricing page.

Security

Grade A, and why

graphsignal-profiler scanned grade A with 1 finding 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.

Runs shell commandslowCapability

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

It enables GPU profiling in this process and starts the profiler sidecar to observe it. Returns the `subprocess.Popen` so the caller can `wait()` or `terminate()` it.
Origin

This is a copy

100% identical to graphsignal-profiler — 1 line 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.

plugins/agents-mcp/skills/graphsignal-profiler/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graphsignal Profiler

Graphsignal observes inference workloads from a sidecar process — the profiler. It never shares a process with CUDA: the profiler watches the workload externally via CUPTI, OTLP/gRPC, Prometheus scraping, and NVML. Auto-instrumentation covers vLLM, SGLang, and PyTorch out of the box.

Install

Two install patterns depending on how you'll launch the profiler.

For graphsignal-run (CLI, recommended): install as a uv tool, isolated from your workload env.

UV_TOOL_BIN_DIR=/usr/local/bin uv tool install 'graphsignal[cu12]'   # CUDA 12.x
# or
UV_TOOL_BIN_DIR=/usr/local/bin uv tool install 'graphsignal[cu13]'   # CUDA 13.x

UV_TOOL_BIN_DIR=/usr/local/bin puts graphsignal-run in a directory that is already on PATH for every shell, including non-interactive scripts and containers.

For graphsignal.watch() (in-process Python entry point): install into the app's own env.

uv add 'graphsignal[cu12]'    # or pip install -U 'graphsignal[cu12]'

The cu12 / cu13 extras are Linux-only and only needed for GPU profiling.

Configure

The profiler reads its config from environment variables.

Variable Purpose
GRAPHSIGNAL_API_KEY (required) Account API key.
GRAPHSIGNAL_API_BASE Override the API endpoint (defaults to https://api.graphsignal.com).
GRAPHSIGNAL_TAG_<KEY>=<value> Arbitrary tag attached to all signals (e.g. GRAPHSIGNAL_TAG_DEPLOYMENT=us-prod).

Set these before invoking graphsignal-run or calling graphsignal.watch().

Run

Option A — graphsignal-run CLI (recommended)

Wrap the launch command for your workload.

export GRAPHSIGNAL_API_KEY="..."
graphsignal-run vllm serve Qwen/Qwen1.5-7B-Chat --port 8000

Read the full file on GitHub · 206 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 206 lines · 74 tokens per session scan A 5a4a8446bac7

Subscribe to this mod's changes

graphsignal-profiler is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,777 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). It is 100% identical to graphsignal-profiler, differing in 1 line, and is treated as a copy.

Related

Other skills, from other repositories

glycobiology

Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.

synthetic-sciences/openscience · 67 tokens

shap

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…

synthetic-sciences/openscience · 109 tokens

cellxgene-census

Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.

synthetic-sciences/openscience · 67 tokens

esm

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…

synthetic-sciences/openscience · 86 tokens

aeon

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…

synthetic-sciences/openscience · 74 tokens

llm-as-judge-evaluation

Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.

synthetic-sciences/openscience · 56 tokens