helix.mcp: Skill for Claude Code

.squad/skills/mcp-sdk-major-upgrade/SKILL.md

mcp-sdk-major-upgrade is a skill for Claude Code, Codex from lewing/helix.mcp. It costs 39 tokens per session (5,125 once invoked), scanned A, original, MIT.

A guide for upgrading the C# ModelContextProtocol SDK across a major version. The SDK is the library used to build MCP servers and tools in C#.

In plain words
What is it for?
Use it when upgrading the ModelContextProtocol and ModelContextProtocol.AspNetCore packages. It requires both packages to move together and calls for checking authoritative release information.
Why use it?
Major upgrades can change APIs and behavior, so the guide helps verify release facts, identify breaking changes, and choose a safe rollback version.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is lewing/helix.mcp's own configuration. It tells Claude Code and Codex how to work on helix.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 helix.mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lewing/helix.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/lewing/helix.mcp/main/.squad/skills/mcp-sdk-major-upgrade/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lewing/helix.mcp

Made for: Claude Code, Codex.

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 mcp-sdk-major-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-sdk-major-upgrade/github.svg)](https://agentmods.dev/skills/lewing/helix.mcp/mcp-sdk-major-upgrade)
Your own site
<a href="https://agentmods.dev/skills/lewing/helix.mcp/mcp-sdk-major-upgrade"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-sdk-major-upgrade/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 mcp-sdk-major-upgrade

Your own site · 80×15
<a href="https://agentmods.dev/skills/lewing/helix.mcp/mcp-sdk-major-upgrade"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-sdk-major-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,125 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.05125
Opus 5 $0.00019 $0.02563
Sonnet 5 $0.00008 $0.01025
Haiku 4.5 $0.00004 $0.00513

Measured 11d ago against content hash 253eb2b9b2c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-sdk-major-upgrade scanned grade A with 2 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://api.nuget.org/v3-flatcontainer/modelcontextprotocol/index.json"

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

proc = subprocess.Popen(["dotnet", "<dll>", "mcp"], stdin=PIPE, stdout=PIPE, stderr=PIPE, text=True)
.squad/skills/mcp-sdk-major-upgrade/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

Applies when the ModelContextProtocol / ModelContextProtocol.AspNetCore packages get a new major version. Complements dependency-audit (which finds the gap) — this skill is about deciding how to cross it. Earned on the 1.4.0 → 2.2.0 migration (2026-08-20).

Both MCP packages live in Directory.Packages.props and must move in lockstep.

Patterns

1. Establish ground truth before reading anyone's analysis

Agent-written migration reports are unreliable on release metadata. Verify first — it costs seconds:

# Real versions + real publish dates
curl -s "https://api.nuget.org/v3-flatcontainer/modelcontextprotocol/index.json"
gh release list --repo modelcontextprotocol/csharp-sdk --limit 12

# The authoritative breaking-change list
gh release view v2.0.0 --repo modelcontextprotocol/csharp-sdk --json body -q .body

Two traps seen repeatedly:

  • Invented dates. Reports dated the release to "today" and the old baseline to "early ". Both wrong.
  • The missed servicing release. Reports enumerate the new major's releases and skip the patch on the old major (e.g. 1.4.1). That patch is the correct rollback target, not the version you were pinned to.

2. Read the SDK source, not just the release notes, for anything you'll touch

Release notes state what changed; the source states what the API now looks like. Confirm each API the repo actually uses still exists with the same shape:

# List public members of a type at the target tag
curl -s "https://raw.githubusercontent.com/modelcontextprotocol/csharp-sdk/vX.Y.Z/src/<path>.cs" \
  | grep -nE "^\s*(public|\[)"

# Find files at a tag without cloning
curl -s "https://api.github.com/repos/modelcontextprotocol/csharp-sdk/git/trees/vX.Y.Z?recursive=1" \
  | python3 -c "import sys,json; [print(e['path']) for e in json.load(sys.stdin)['tree'] if e['path'].startswith('src/') and 'Filters' in e['path']]"

Our standing surface to re-verify each time: McpServerFilters.Request.CallToolFilters · WithToolsFromAssembly(Assembly?, JsonSerializerOptions?) · WithResourcesFromAssembly(Assembly?) · WithStdioServerTransport() · WithHttpTransport(...) · IProgress<ProgressNotificationValue> injection · McpServerToolAttribute · McpException.

Read the full file on GitHub · 341 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. 11d ago First seen · 341 lines · 39 tokens per session scan A 253eb2b9b2c9

Subscribe to this mod's changes

mcp-sdk-major-upgrade is a skill published in the GitHub repository lewing/helix.mcp (4 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 5,125 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

blazor

Use for Blazor Server development with Fluent UI Blazor, Razor components, layouts, pages, scoped UI services, culture switching, localization, forms, loading/empty/error states, and Studio-style dashboard workflows.

AterDev/Perigon.CLI · 45 tokens

cli

Use for .NET command-line tool development with Spectre.Console/Spectre.Console.Cli, Microsoft.Extensions.Hosting, dependency injection, localized help text, command settings, aliases, examples, terminal output, exit codes, and stdio-safe command paths.

AterDev/Perigon.CLI · 52 tokens

codegen

Use for .NET code generation work with Roslyn, Microsoft.OpenApi, Razor templates, DTO/manager/controller generation, REST API generation, C# HttpClient generation, Angular/Axios TypeScript request clients, generated formatting, and deterministic output.

AterDev/Perigon.CLI · 53 tokens

dotnet

Use for .NET application development involving services, managers, dependency injection, Microsoft.Extensions.Hosting, dependency direction, MiniDb persistence, DTOs, Mapster mapping, shared entities/helpers, MCP tools, module workflows, solution analysis, cancellation, logging, and logic shared by CLI and Blazor.

AterDev/Perigon.CLI · 61 tokens

generate-code-cs

Generate the code from typespec for C#. Parameter: C# SDK repository root location .

Azure/azure-sdk-for-net · 26 tokens

author-test

Generate a test given sample. Parameters: C# SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; the sample to use as a starting point for the test.

Azure/azure-sdk-for-net · 68 tokens