Roslyn-Backed-MCP: Skill for Claude Code

.claude/skills/publish-preflight/SKILL.md

publish-preflight is a skill for Claude Code from darylmcd/Roslyn-Backed-MCP. It costs 57 tokens per session (3,073 once invoked), scanned A, original, MIT.

A release checklist for publishing a NuGet package, which is a distributable library package for .NET applications. It checks versions, documentation, builds, tests, coverage, security dependencies, changelog entries, and publishing steps.

In plain words
What is it for?
Use it to validate release readiness, check version agreement, run the complete build and test pipeline, create the package, and confirm documentation and security requirements.
Why use it?
It finds release problems before publication and reports all failed checks instead of stopping at the first one.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is darylmcd/Roslyn-Backed-MCP's own configuration. It tells Claude Code how to work on Roslyn-Backed-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 Roslyn-Backed-MCP configures →

Part of the roslyn-mcp plugin — 44 skills, 5 agents, 2 hooks, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to darylmcd/Roslyn-Backed-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/darylmcd/Roslyn-Backed-MCP/main/.claude/skills/publish-preflight/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCP

Made for: Claude Code.

Or install roslyn-mcp, the plugin that ships this one along with the rest of its 44 skills, 5 agents, 2 hooks, 2 MCP servers.

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 publish-preflight

README.md
[![agentmods](https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/publish-preflight/github.svg)](https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/publish-preflight)
Your own site
<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/publish-preflight"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/publish-preflight/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 publish-preflight

Your own site · 80×15
<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/publish-preflight"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/publish-preflight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,073 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.
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 $0.00057 $0.03073
Opus 5 $0.00028 $0.01537
Sonnet 5 $0.00011 $0.00615
Haiku 4.5 $0.00006 $0.00307

Measured 10d ago against content hash f191ad4ac7a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

publish-preflight 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 10d 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/publish-preflight/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish Pre-flight Checklist

You are a release gatekeeper. Your job is to run every validation step required before a NuGet publish and report a clear pass/fail summary.

Server discovery

Roslyn MCP server_info / server_catalog describe the running analyzer server, not this repo's release scripts. This skill is about repository publish gates.

Repo shortcuts (just)

From the repository root you can run:

Step just recipe
Version drift just verify-version-drift
AI docs just verify-docs
Full release script (build, test, coverage, publish, manifest) just verify-release
Pack host nupkg just pack
Aggregate CI-like local run just ci or just full

These wrap the same eng/*.ps1 scripts below when you prefer a single entry point.

Checklist Steps

Execute ALL steps in order. Track pass/fail for each. Do NOT stop on the first failure — run the full checklist so the user sees everything that needs fixing.

Step 1: Version Drift Check

Run via Bash:

pwsh -NoProfile -File eng/verify-version-drift.ps1

Pass if exit code 0. Fail if any of the seven version files disagree — report which ones.

Step 2: AI Documentation Validation

Run via Bash:

pwsh -NoProfile -File eng/verify-ai-docs.ps1

Pass if exit code 0. Fail if documentation structure is invalid.

Step 3: Build, Test, and Publish Validation

Run via Bash:

pwsh -NoProfile -File eng/verify-release.ps1 -Configuration Release

This runs: version drift (again, harmless), restore, build, test with coverage, publish host binary, and SHA256 manifest generation.

Pass if exit code 0. Fail if build errors, test failures, or publish errors.

Extract and report:

  • Total tests / passed / failed
  • Coverage output path
  • Hash manifest path

Step 4: CHANGELOG.md Entry

Read Directory.Build.props to get the current version. Read CHANGELOG.md and check that a ## [X.Y.Z] header exists for the current version.

Read the full file on GitHub · 205 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. 10d ago First seen · 205 lines · 57 tokens per session scan A f191ad4ac7a3

Subscribe to this mod's changes

publish-preflight is a skill published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 3,073 once invoked, about $0.0003 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.