A method for investigating memory use in .NET applications, especially suspected memory leaks. It relies on the MemoryLens MCP server to inspect an already-running process.

Use it to list running .NET processes, take and compare heap snapshots, and analyze memory findings. The required MCP server must be available.

It provides a systematic way to examine high memory use, out-of-memory errors, slow garbage collection, or memory that keeps growing.

memorylens — Skill for Claude Code by MarcelRoozekrans/memorylens-mcp

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 MarcelRoozekrans/memorylens-mcp --skill memorylens

Clone the repo

git clone --depth 1 https://github.com/MarcelRoozekrans/memorylens-mcp

Made for: Claude Code.

Or install memorylens, the plugin that ships this one along with the rest of its 1 skill.

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/marcelroozekrans/memorylens-mcp/memorylens/github.svg)](https://agentmods.dev/skills/marcelroozekrans/memorylens-mcp/memorylens)

Your own site

<a href="https://agentmods.dev/skills/marcelroozekrans/memorylens-mcp/memorylens"><img src="https://agentmods.dev/badge/skills/marcelroozekrans/memorylens-mcp/memorylens/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/marcelroozekrans/memorylens-mcp/memorylens"><img src="https://agentmods.dev/badge/skills/marcelroozekrans/memorylens-mcp/memorylens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 901 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	$0.00027	$0.00901
Opus 5.5	$0.00011	$0.00360
Sonnet 5.5	$0.00005	$0.00180
Haiku 4.5	$0.00003	$0.00090

Measured 2mo ago against content hash ccd29869624d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memorylens 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.

plugins/memorylens/skills/memorylens/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MemoryLens — Memory Profiling Skill

Prerequisites

This skill requires the memorylens MCP server tools (list_processes, snapshot, compare_snapshots, analyze, get_rules). Collection happens in-process over EventPipe, so there is nothing to install or verify before profiling — if the MCP tools aren't available at all, inform the user to install the memorylens plugin.

When to Use

On demand: User requests memory analysis (/memorylens)
During debugging: When systematic-debugging identifies symptoms like high memory usage, OutOfMemoryException, slow GC, or growing memory over time
During brainstorming: When designing performance-sensitive features that involve caching, event systems, or long-lived objects

Announce Line

"MemoryLens activated. I'll profile your application's memory and suggest concrete fixes."

Workflow

Step 1: Identify target

MemoryLens attaches to an already-running .NET process. It cannot launch one.

Call list_processes and let the user pick, or take a pid the user supplies.
If the app is not running yet, ask the user to start it first, then re-run list_processes.
snapshot and compare_snapshots both require a pid. Do not pass command — the parameter is accepted for compatibility but is not implemented, and a call without a pid returns an error.

Step 2: Choose profiling mode

Based on the user's ask:

"How does my memory look?" → Single snapshot
"Is there a leak?" / "What changed?" → compare_snapshots
Unclear → Ask: "Do you want a single snapshot of current state, or a before/after comparison to detect growth?"

Step 3: Capture

Execute snapshot or compare_snapshots with the target parameters.

Step 4: Analyze

Call analyze with the returned snapshotId and nothing else — the id is all it needs.

Rule configuration is not a parameter. The server reads .memorylens.json from its own working directory once at startup; changing that file needs a server restart to take effect. Use get_rules to see which rules are currently active.

Read the full file on GitHub · 95 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.

2mo ago First seen · 95 lines · 27 tokens per session scan A ccd29869624d

Subscribe to this mod's changes

memorylens is a skill published in the GitHub repository MarcelRoozekrans/memorylens-mcp (11 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 901 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 2026-08-31.

C# and .NET Claude Code Debugging ai-agents dotnet eventpipe mcp

memorylens next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
memorylensMarcelRoozekrans/memorylens-mcp	Skill	11	yesterday	MIT	A	27	Claude Code
blazing-fast-dotnetmanagedcode/dotnet-skills	Skill	508	yesterday	MIT	A	72	Claude Code, Codex
profilingmanagedcode/dotnet-skills	Skill	508	yesterday	MIT	A	119	Claude Code, Codex
roslyn-codelensMarcelRoozekrans/roslyn-codelens-mcp	Skill	70	yesterday	MIT	A	104	Claude Code
cs0618-hunterjoslat/maf-doctor	Skill	14	12d ago	MIT	A	85	Claude Code, Codex
nuget-diff-analyzerjoslat/maf-doctor	Skill	14	12d ago	MIT	A	56	Claude Code, Codex
binlog-generationCratis/AI	Skill	4	yesterday	MIT	A	41	Claude Code, Codex