dotnet-dump-mcp: Skill for Claude Code

.claude/skills/dndump/SKILL.md

dndump is a skill for Claude Code from frankbolero/dotnet-dump-mcp. It costs 146 tokens per session (2,756 once invoked), scanned A, original, MIT.

A command-line tool for examining .NET memory dumps, which are saved snapshots of a program's state. It can inspect runtime details, heaps, threads, stacks, locks, and related data.

In plain words
What is it for?
Use it from a shell to select and validate a dump, inspect its runtime, and query objects, threads, call stacks, locks, and references.
Why use it?
It provides a repeatable way to investigate crashes, out-of-memory errors, memory leaks, hangs, deadlocks, and unhandled exceptions from a dump file.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is frankbolero/dotnet-dump-mcp's own configuration. It tells Claude Code how to work on dotnet-dump-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dotnet-dump-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to frankbolero/dotnet-dump-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/frankbolero/dotnet-dump-mcp/main/.claude/skills/dndump/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/frankbolero/dotnet-dump-mcp

Made for: Claude Code.

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 dndump

README.md
[![agentmods](https://agentmods.dev/badge/skills/frankbolero/dotnet-dump-mcp/dndump/github.svg)](https://agentmods.dev/skills/frankbolero/dotnet-dump-mcp/dndump)
Your own site
<a href="https://agentmods.dev/skills/frankbolero/dotnet-dump-mcp/dndump"><img src="https://agentmods.dev/badge/skills/frankbolero/dotnet-dump-mcp/dndump/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 dndump

Your own site · 80×15
<a href="https://agentmods.dev/skills/frankbolero/dotnet-dump-mcp/dndump"><img src="https://agentmods.dev/badge/skills/frankbolero/dotnet-dump-mcp/dndump.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,756 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 136
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • medium MCP Rug Pull · line 144
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • medium MCP Rug Pull · line 159
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
How audits are shown
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 $0.00146 $0.02756
Opus 5 $0.00073 $0.01378
Sonnet 5 $0.00029 $0.00551
Haiku 4.5 $0.00015 $0.00276

Measured 9d ago against content hash faf72c0aa2bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dndump 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 9d 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.

.claude/skills/dndump/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dndump — .NET dump analysis CLI

dndump is a per-invocation CLI over ClrMD. Each command starts, prints results, and exits — no persistent process, no tool-manifest context cost. Prefer it over any MCP-server equivalent whenever a shell is available.

Filter in the shell, not in your head. A dumpheap on a real dump can be thousands of rows. Never dump a full unfiltered result into context to eyeball it — use --format json/tsv with jq/grep/awk, or --limit, so only the rows you actually need cost tokens. See "Piping" below.

Selecting a dump

dndump use /path/to/dump.core   # writes .dndump/session.json; validates the dump opens
dndump info                     # runtime, arch, DAC match, heap/segment/thread counts — always run this first

After use, every later command in the same directory tree needs no --dump. Resolution order: --dump <path> flag → DNDUMP_PATH env var → .dndump/session.json (searched upward). Each shell invocation is a fresh process with no inherited env, which is exactly why use exists — set it once, not per command.

If dndump fails to load the dump locally (wrong OS/architecture for the dump, no local .NET runtime matching it, or no matching DAC available), see "Docker fallback" below before concluding the dump is unreadable.

Global options

Option Default Notes
--format md|json|tsv md json is a stable API contract (envelope {data, pagination}, camelCase, 16-hex addresses) — safe to jq against. tsv is header + tab-separated rows for grep/awk/cut.
--limit <n> / --offset <n> 50 / 0 Paging on every list command. dumpheap also accepts --top <n> as a friendlier alias for --limit (that command only).
--sort <field> / --order asc|desc per command Valid fields differ per command — run dndump <command> --help if unsure.
--quiet off Suppresses the informational header on stderr; doesn't affect stdout data.
--dump <path>, --dac <path> Override dump/DAC resolution for one call.

Read the full file on GitHub · 199 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. 9d ago First seen · 199 lines · 146 tokens per session scan A faf72c0aa2bd

Subscribe to this mod's changes

dndump is a skill published in the GitHub repository frankbolero/dotnet-dump-mcp (12 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 2,756 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

dotnet-performance

Evidence-first performance engineering workflow for coding agents combining portable .NET diagnostics with platform-native profiling, BenchmarkDotNet, application benchmarking, statistical validation, deployment, container, graphics, and GPU procedures.

wieslawsoltes/Performance-Skill · 42 tokens

profiling

Use the free official .NET diagnostics CLI tools for profiling and runtime investigation in .NET repositories. USE FOR: the repo needs performance or runtime profiling for a .NET application; the user asks about slow code, high CPU, GC pressure, allocation growth, exception storms, lock. DO NOT USE FOR: replacing…

managedcode/dotnet-skills · 119 tokens

roslyn-codelens

Use when working with any .NET / C# code (.cs/.csproj/.sln/.slnx files), finding callers/references/implementations, checking compiler errors or warnings, running dotnet build for diagnostics, searching for a type/method/interface by name, inspecting DI registrations, detecting dead code or circular dependencies…

MarcelRoozekrans/roslyn-codelens-mcp · 104 tokens

cs0618-hunter

Detects and fixes CS0618 obsolete API warnings in .NET builds. The compiler is the authoritative source for what your project actually triggers — it catches transitive obsoletions, overload-resolution surprises, and project-local [Obsolete] attributes that static inspection cannot see. Pair with the repository-pinned…

joslat/maf-doctor · 85 tokens

nuget-diff-analyzer

Post-processes the repository-pinned [email protected] -- diff output into a categorised report (breaking / additive / newly-obsolete) with each finding cross-referenced to the MAF obsolete-API registry.

joslat/maf-doctor · 56 tokens

rider-search

Routing rules for code search in JetBrains Rider projects — use the Rider MCP symbol/reference/file tools instead of Bash grep. Use whenever searching for a symbol, definition, function, variable, type, or finding usages/references in a C#/.NET or Unreal C++ codebase open in Rider.

JSungMin/rider-mcp-enforcer · 60 tokens