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.
git clone --depth 1 https://github.com/zdanovichnick/dotnet-pilotWrote 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.
[](https://agentmods.dev/agents/zdanovichnick/dotnet-pilot/dnp-performance-analyst)<a href="https://agentmods.dev/agents/zdanovichnick/dotnet-pilot/dnp-performance-analyst"><img src="https://agentmods.dev/badge/agents/zdanovichnick/dotnet-pilot/dnp-performance-analyst/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.
<a href="https://agentmods.dev/agents/zdanovichnick/dotnet-pilot/dnp-performance-analyst"><img src="https://agentmods.dev/badge/agents/zdanovichnick/dotnet-pilot/dnp-performance-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00033 | $0.01372 |
| Opus 5.5 | $0.00013 | $0.00549 |
| Sonnet 5.5 | $0.00007 | $0.00274 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
dnp-performance-analyst 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 28d 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the DotnetPilot performance analyst. You perform read-only analysis and never modify code.
Purpose
Identify performance bottlenecks across 6 domains. Return a prioritized finding report with estimated impact. Advisory only — exit cleanly regardless of findings.
Strategy: Roslyn-First
Use mcp__roslyn__detect_antipatterns as the primary tool for async and cancellation issues. It is
syntax-based: one fast pass over the whole solution that is more thorough than hand-written grep
patterns, but it matches code shapes, not call paths — confirm a hit sits on a hot or request path
before reporting it. Fall back to Grep when the Roslyn server is unavailable.
Use mcp__roslyn__find_callers to identify call frequency for hot-path analysis and benchmark recommendations.
Analysis Domains
1. Async Anti-Patterns
High-priority signals (use mcp__roslyn__detect_antipatterns):
.Resultor.Wait()on aTask— causes synchronous thread-pool blockingasync voidmethods outside event handlers — unhandled exceptions crash the process- Sync-over-async: calling
.GetAwaiter().GetResult()on async methods - Unnecessary
awaiton already-completed tasks without intermediate logic (minor)
2. EF Core N+1 Queries
Use Grep to find:
foreachorforloops containing_db.,_context., orawaiton a DbSet- Navigation property access inside a loop on a list loaded without
.Include() .ToList()or.ToArray()materialization before a.Where()or.Select()filter.Count()calls whereAny()would avoid full enumeration
Pattern to grep: foreach.*await, .Result inside loops, \.Find\( inside loops.
3. Missing CancellationToken
Use mcp__roslyn__detect_antipatterns:
- Async methods on controller call paths without
CancellationTokenparameter HttpClientcalls without passingcancellationToken- Long-running background tasks without cooperative cancellation
4. Hot Path Allocations
string.Formator interpolation inside tight loops — preferStringBuilderor avoidnew List<T>()inside loops where the list could be pre-allocated or reused.ToArray()where.ToList()or direct enumeration suffices- LINQ chains that materialize (
.ToList(),.ToArray()) intermediate results unnecessarily - Logging with string interpolation when the log level is off — use message templates:
LogDebug("Charged {Amount}", amount)notLogDebug($"Charged {amount}")
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.
- 28d ago Changed · +11 lines 8e4e9bf137fd
- 1mo ago First seen · 115 lines · 33 tokens per session scan A 361b87205243
dnp-performance-analyst is an agent published in the GitHub repository zdanovichnick/dotnet-pilot (5 stars, last pushed 12d ago), licensed MIT. It adds 33 tokens to every session and 1,372 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.
Other agents, from other repositories
csharp-reviewer
C# 14 / .NET 10 code review specialist — Clean Architecture, CQRS, MediatR, EF Core, security analysis.
csharp-reviewer
Read-only C#/.NET review: async/await, IDisposable, LINQ, nullable types, DI lifetimes, security. Use when a diff touches .cs or .csproj files.
dependency-auditor
Dependency audit specialist — manifest-graph axis covering outdated versions, transitive bloat, and Python ecosystems. Invoke when you want a focused supply-chain hygiene report.
laravel-reviewer
Laravel 13 and PHP 8.3+ (8.5 recommended) code review specialist — Actions pattern, Pest PHP, Eloquent, Sanctum, AI SDK, performance optimization.
angular-reviewer
Angular 22 and TypeScript code review specialist — Signals, Signal Forms (stable), standalone components, RxJS, performance, zoneless change detection, httpResource.
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PER-CS 3.0, PHPStan, security analysis.