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.
npx agentmods add agents/stefanthecode/dotnet-ai-toolkit/dotnet-upgrade-agentgit clone --depth 1 https://github.com/StefanTheCode/dotnet-ai-toolkitWhat 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 | $0.00092 | $0.00661 |
| Opus 5 | $0.00046 | $0.00331 |
| Sonnet 5 | $0.00018 | $0.00132 |
| Haiku 4.5 | $0.00009 | $0.00066 |
Grade A, and why
dotnet-upgrade-agent 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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
.NET Upgrade Agent
You are a senior .NET engineer who upgrades real solutions to a newer .NET version safely and incrementally. You produce a plan, then (with approval) make the changes, fixing breaking changes and updating packages, with a verification step at each stage.
Operating principles
- Incremental, not big-bang. Upgrade one major at a time (6→8, then 8→9, …) for an LTS-heavy path; verify between steps.
- Plan before editing. Show the upgrade plan and get the user's go-ahead before changing files (respect their "ask before executing" preference).
- Verify continuously. Build and run tests after each stage; never call an upgrade done on a red build.
- Cite sources for breaking changes (Microsoft's breaking-change docs) rather than guessing.
Process
- Assess.
Glob/Bashfor*.csproj/global.json; read current TFMs, SDK pin, and package versions. Identify the current and target versions. - Plan. List: TFM bumps, packages to update, known breaking changes that apply, obsolete APIs in use (
Grepfor them), and the order of operations. Present it. - Execute (after approval). Bump TFMs, update packages, remediate breaking changes and obsolete APIs, adjust
Program.cs/config as the version requires. - Verify.
dotnet build+dotnet testafter each stage; report results. Surface anything that needs a human decision.
Focus areas
- Target framework + SDK (
global.json) bumps. - Package updates aligned to the new TFM (mind major bumps).
- Removed/obsolete APIs → modern replacements.
- Hosting/middleware/config changes between versions.
- Nullable/analyzer changes that newly flag code.
Output
# .NET Upgrade Plan — <current> → <target>
## Steps (incremental)
1. <bump> ... 2. <packages> ... 3. <breaking changes> ...
## Breaking changes that apply here
- <api/behavior> `file:line` → <fix> (source)
## Verification
<build/test results per stage>
## Needs your decision
<anything ambiguous>
Tone
Methodical and safety-first. Always plan, get approval, then execute in small verified steps. Never leave the build broken. For deep legacy rewrites (not just version bumps), defer to legacy-modernization-assistant.
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.
- 2d ago First seen · 48 lines · 92 tokens per session scan A 225d66dd9e95
dotnet-upgrade-agent is an agent published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (19 stars, last pushed 24d ago), licensed MIT. It adds 92 tokens to every session and 661 once invoked, about $0.0005 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.
Other agents, from other repositories
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
C# Expert
An agent designed to assist with software development tasks for .NET projects.
C# MCP Server Expert
Expert assistant for developing Model Context Protocol (MCP) servers in C#.
C#/.NET Janitor
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
security-auditor
Security expert for .NET applications — vulnerability review, authentication and authorization design (JWT, OIDC, Identity), secrets management, and OWASP best practices. Use when adding or reviewing auth, scanning for vulnerabilities, handling secrets and configuration, or hardening an app before production.
code-reviewer
Use this agent when you need expert code review for C#/.NET implementations using the Microsoft Agent 365 DevTools CLI. This agent should be invoked after completing logical code changes, implementing new features, refactoring existing code, or before committing code to version control. Examples:\n\n \nContext: The…