dotnet-perf-full-probe

dotnet-perf-full-probe is an agent for coding agents from Attemainio/dotnet-toolkit. It costs 232 tokens per session (1,465 once invoked), scanned A, original, MIT.

A benchmark agent for comparing two kinds of tools while navigating C# code: this repository’s .NET tools and basic file and shell tools. It follows a separate performance protocol supplied by the caller.

In plain words
What is it for?
Use it in controlled .NET performance experiments. It answers stated C# navigation questions and reports results using the shared protocol.
Why use it?
It provides an unrestricted comparison point for measuring how tool restrictions affect speed and token use. It also explains why a listed tool may be unavailable when its schema has not been loaded.

Agent

Part of the dotnet-toolkit plugin — 9 skills, 6 agents, 2 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/attemainio/dotnet-toolkit/dotnet-perf-full-probe
Clone the repo
git clone --depth 1 https://github.com/Attemainio/dotnet-toolkit

Or install dotnet-toolkit, the plugin that ships this one along with the rest of its 9 skills, 6 agents, 2 hooks, 1 MCP server.

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 dotnet-perf-full-probe

README.md
[![agentmods](https://agentmods.dev/badge/agents/attemainio/dotnet-toolkit/dotnet-perf-full-probe.svg)](https://agentmods.dev/agents/attemainio/dotnet-toolkit/dotnet-perf-full-probe)
Your own site
<a href="https://agentmods.dev/agents/attemainio/dotnet-toolkit/dotnet-perf-full-probe"><img src="https://agentmods.dev/badge/agents/attemainio/dotnet-toolkit/dotnet-perf-full-probe.svg" alt="Measured on agentmods" height="20"></a>
Per session 232 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00232 $0.01465
Opus 5 $0.00116 $0.00732
Sonnet 5 $0.00046 $0.00293
Haiku 4.5 $0.00023 $0.00146

Measured 5d ago against content hash 7de48ac8ac25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotnet-perf-full-probe 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 5d 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.

agents/dotnet-perf-full-probe.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the third leg of a token-cost comparison run by dotnet-performance. The other two agents are each artificially restricted to one tool family — dotnet-perf-mcp-probe (MCP tools only, guards forced to block) and dotnet-perf-raw-probe (raw tools only, guards suspended) — to measure a ceiling and a floor. You are not restricted at all: you have both families, and the guards are in whatever state this repo ships by default. Your run is what a real Claude Code session with this plugin installed actually does, question by question.

This file is deliberately not self-contained. Your invoking prompt names a performance_protocol.md file and gives you the question list and a taskId. Read that file first — it is the single source of the output format and how to play each question, shared byte-for-byte with the other two agents in this run, so none of you defaults to a different reporting style.

If a tool call returns No such tool available

The schema is deferred, not missing. When a session carries many tools the harness advertises their names without their JSONSchema definitions, and a name with no schema loaded cannot be called. The symptom reads like a broken install; it isn't. Load what you need in one call — ToolSearch with select: and a comma-separated list of every dotnet-toolkit tool you expect this task to need, by exact name — then retry. Schema loads do not propagate from the session that launched you, so nobody can do this for you.

Use ToolSearch only for tools already in your tools: grant: it is a schema loader, not a way to acquire a tool you were not given.

A failed MCP call must never silently become a raw-tool answer. You hold both families, so this is the one way your run can go wrong without looking wrong: if the MCP half is unreachable and you simply use Grep/Read instead, your results are indistinguishable from dotnet-perf-raw-probe's and the report concludes that a real session never chooses the MCP route. If a tool will not call after a ToolSearch, say so explicitly in your final message as a blocker, naming the tool and the error, whatever else you answer. The ToolSearch call itself is setup, like your Read of performance_protocol.md — don't log it under any question.

Read the full file on GitHub · 88 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. 5d ago First seen · 88 lines · 232 tokens per session scan A 7de48ac8ac25

Subscribe to this mod's changes

dotnet-perf-full-probe is an agent published in the GitHub repository Attemainio/dotnet-toolkit (2 stars, last pushed 9d ago), licensed MIT. It adds 232 tokens to every session and 1,465 once invoked, about $0.0012 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 2026-08-31.

Related

Other agents, from other repositories

NUnit.Agent

Assists with NUnit development, documentation, and CI configuration.

nunit/nunit · 16 tokens

ahj

Programming language designer for four decades. Lead architect of Turbo Pascal (Borland, 1980s), Delphi (Borland, 1990s), C# (Microsoft, 2000s), and TypeScript (Microsoft, 2012–). Pragmatic, prolific, and rare among language designers in shipping multiple successful languages used by millions of working developers.

punt-labs/prfaq · 77 tokens

MAF Migration Agent

Use when migrating a .NET codebase to Microsoft Agent Framework (MAF) 1.3.0. Orchestrates the full migration using specialized skills for API lookup, plan generation, CS0618 detection, and fan-out validation. Handles NuGet package updates, namespaces, executors, sessions, workflows, streaming, events, and DevUI guards.

joslat/maf-doctor · 78 tokens

MAF Auditor Agent

Use when you need to audit a .NET codebase and generate a ready-to-execute MAF migration plan. Given a repository, this agent scans source files and packages, runs dotnet-inspect diff, cross-references the Obsolete API Registry, and outputs a complete migration-plan.md with a populated tracking table.

joslat/maf-doctor · 69 tokens

unity-simplifier

Simplifies Unity C# code for clarity and maintainability while preserving functionality. Focuses on Unity-specific patterns and conventions.

DmitriyYukhanov/claude-plugins · 29 tokens

csharp-reviewer

C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.

KevinZai/commander · 35 tokens