What is gc-pressure-auditor?

A guide for finding why .NET services are spending too much time doing garbage collection, the automatic process that frees memory no longer in use. It examines allocation rates, collection generations, large objects, memory retention, and garbage-collection settings.

Use it to investigate GC pauses, high GC CPU, memory growth, Gen2 collections, large-object-heap issues, or server-versus-workstation GC settings.

It helps distinguish excessive short-lived allocations, long-lived objects, large-object-heap fragmentation, and configuration problems from ordinary memory use. This gives developers evidence for reducing pauses, CPU use, or memory growth.

gc-pressure-auditor — Skill for Claude Code by StefanTheCode

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 StefanTheCode/dotnet-ai-toolkit --skill gc-pressure-auditor

Clone the repo

git clone --depth 1 https://github.com/StefanTheCode/dotnet-ai-toolkit

Made for: Claude Code.

Or install dotnet-ai-toolkit, the plugin that ships this one along with the rest of its 49 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/stefanthecode/dotnet-ai-toolkit/gc-pressure-auditor/github.svg)](https://agentmods.dev/skills/stefanthecode/dotnet-ai-toolkit/gc-pressure-auditor)

Your own site

<a href="https://agentmods.dev/skills/stefanthecode/dotnet-ai-toolkit/gc-pressure-auditor"><img src="https://agentmods.dev/badge/skills/stefanthecode/dotnet-ai-toolkit/gc-pressure-auditor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/stefanthecode/dotnet-ai-toolkit/gc-pressure-auditor"><img src="https://agentmods.dev/badge/skills/stefanthecode/dotnet-ai-toolkit/gc-pressure-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 662 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.

Model	Per session	Once invoked
Fable 5.1	$0.00105	$0.00662
Opus 5.5	$0.00042	$0.00265
Sonnet 5.5	$0.00021	$0.00132
Haiku 4.5	$0.00011	$0.00066

Measured 2mo ago against content hash 8b7d0556290e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gc-pressure-auditor 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 2mo 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/gc-pressure-auditor/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GC Pressure Auditor

Diagnose why the garbage collector is working hard in a .NET service and recommend concrete fixes — config, allocation reduction, and pooling — based on the symptoms.

Input — point it at your project / paste the symptoms

Works on a target (a project or GitHub URL) and/or counters the user shares (Gen0/1/2 counts, % Time in GC, allocation rate, LOH size). Check config: grep -rn "ServerGarbageCollection\|ConcurrentGarbageCollection\|GCHeapHardLimit" <target> and the .csproj/runtimeconfig.

What to check

Server vs Workstation GC — a throughput server should use Server GC (<ServerGarbageCollection>true</ServerGarbageCollection>). Workstation GC on a busy server = avoidable pauses.
Concurrent GC — keep background GC on for latency-sensitive services.
Allocation rate — high Gen0 churn means too many short-lived allocations. Trace the sources (memory-allocation-analyzer).
Gen2 churn — objects surviving to Gen2 then dying = mid-lifetime objects; often caching done wrong or large graphs held too long.
Large Object Heap (LOH) — arrays/strings ≥ 85 KB go to the LOH, which fragments and is collected with Gen2. Pool large buffers (ArrayPool<T>), stream instead of buffering, chunk large payloads.
Pinning / fragmentation — long-lived pinned buffers fragment the heap.
Hard limits in containers — set GCHeapHardLimit/honor cgroup limits so the GC sizes correctly in k8s.

Common fixes

Switch to Server GC + concurrent for throughput services.
Pool large/short-lived buffers with ArrayPool<T>.Shared / RecyclableMemoryStream.
Cut steady-state allocations on hot paths.
Avoid LOH: stream large files, chunk, reuse buffers.

Principles

GC pressure is an allocation problem first. Config tuning helps, but reducing what you allocate helps more.
Diagnose with data (dotnet-counters, dotnet-trace, GC stats) — don't tune blind.
LOH is the usual culprit for big, periodic pauses.

Read the full file on GitHub · 37 lines

Files

What ships with it

1 file 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.

USAGE.md 879 B

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.

2mo ago First seen · 37 lines · 105 tokens per session scan A 8b7d0556290e

Subscribe to this mod's changes

gc-pressure-auditor is a skill published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (26 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 662 once invoked, about $0.0004 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 2026-08-30.

Debugging performance

gc-pressure-auditor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gc-pressure-auditorStefanTheCode/dotnet-ai-toolkit	Skill	26	2mo ago	MIT	A	105	Claude Code
hotpath_init_grafanapawurb/hotpath-rs	Skill	1.9k	19d ago	MIT	A	109	Claude Code
hotpath_initpawurb/hotpath-rs	Skill	1.9k	19d ago	MIT	A	88	Claude Code
hotpath_cloudpawurb/hotpath-rs	Skill	1.9k	19d ago	MIT	A	110	Claude Code
syncmetapawurb/hotpath-rs	Skill	1.9k	19d ago	MIT	A	55	Claude Code
hotpath_bumppawurb/hotpath-rs	Skill	1.9k	19d ago	MIT	A	99	Claude Code
webperf-core-web-vitalsnucliweb/webperf-snippets	Skill	1.5k	yesterday	MIT	A	113	Claude Code