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 skills add darylmcd/Roslyn-Backed-MCP --skill snippet-evalgit clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCPWrote 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/skills/darylmcd/roslyn-backed-mcp/snippet-eval)<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/snippet-eval"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/snippet-eval/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/skills/darylmcd/roslyn-backed-mcp/snippet-eval"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/snippet-eval.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 | $0.00039 | $0.00747 |
| Opus 5 | $0.00019 | $0.00374 |
| Sonnet 5 | $0.00008 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
snippet-eval 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snippet and Script Evaluation
You use analyze_snippet and evaluate_csharp for fast feedback when loading a full .sln is unnecessary or impossible.
Input
$ARGUMENTS should indicate either:
- A short C# fragment to analyze or run, or
- A file path to read and treat as snippet/script (if the user points at a scratch file)
Server discovery
Full solution workflows live in roslyn://server/catalog. This skill is for ephemeral analysis only.
When to use which tool
| Goal | Tool |
|---|---|
| Parse, bind, diagnostics on a fragment | analyze_snippet |
| Run a script / evaluate an expression (side effects, output) | evaluate_csharp |
| Production refactor / cross-file impact | Load workspace with workspace_load and use symbol tools |
Workflow
- For compile/bind questions: call
analyze_snippetwith the code and appropriate options (as exposed by the tool schema). - For execution: call
evaluate_csharp; warn the user that scripts run in a killable child process but remain inside the host's security trust boundary. - If results imply real-project dependencies, recommend
workspace_loadon the actual solution.
Explain mode — semantic walk-through for teaching or learning
Invoke with --explain or ask "explain this snippet" / "what does this do?". The skill produces a step-by-step semantic walkthrough instead of a pass/fail result:
- Call
analyze_snippetto bind the snippet and gather diagnostics. - Call
get_operations(if available) on the snippet to walk the IOperation tree — this yields the full semantic tree: local declarations, invocations, branches, loops, lambdas, await points. - For each top-level construct (declaration, expression, statement):
- Name the operation kind (e.g.,
LocalReference,InvocationOperation,ConditionalAccessOperation) - State the inferred type and (for numeric/string literals) the value
- Explain data-flow implications: what variables are read, what gets assigned, what captures (for lambdas/closures)
- Name the operation kind (e.g.,
- If the snippet uses
await, show the async flow: where the state machine suspends, what continuation happens on completion vs exception. - If the snippet uses LINQ, explain deferred vs immediate execution and what the query translates to.
- Conclude with a single-sentence summary: "This snippet X, producing Y, with no/these side effects."
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.
- 10d ago First seen · 57 lines · 39 tokens per session scan A 6d83f3ad567c
snippet-eval is a skill published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 747 once invoked, about $0.0002 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.
Other skills, from other repositories
dotnet-reverse
A guide for analyzing compiled .NET and C# programs, including managed Windows executables and libraries. Reverse engineering means studying compiled software to understand how it works, and decompiling turns it back into readable approximate source code.
check-bin-obj-clash
Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath. USE FOR: builds failing with 'Cannot create a file when that file already exists', 'The process cannot access the file because it is being used by another process', intermittent build failures that succeed on retry, or missing/overwritten…
build-perf-diagnostics
Diagnose MSBuild build performance bottlenecks using binary log analysis. USE FOR: identifying why builds are slow by analyzing binlog performance summaries, detecting ResolveAssemblyReference (RAR) taking >5s, Roslyn analyzers consuming >30% of Csc time, single targets dominating >50% of build time, node utilization…
dump-collect
Configure and collect crash dumps for modern .NET applications. USE FOR: enabling automatic crash dumps for CoreCLR or NativeAOT, capturing dumps from running .NET processes, setting up dump collection in Docker or Kubernetes, using dotnet-dump collect or createdump. DO NOT USE FOR: analyzing or debugging dumps…
binlog-generation
Generate MSBuild binary logs (binlogs) for build diagnostics and analysis. USE FOR: adding /bl:{} to any dotnet build, test, pack, publish, or restore command to capture a full build execution trace, prerequisite for binlog-failure-analysis and build-perf-diagnostics skills, enabling post-build investigation of errors…
binlog-failure-analysis
Analyze MSBuild binary logs to diagnose build failures. USE FOR: build errors that are unclear from console output, diagnosing cascading failures across multi-project builds, tracing MSBuild target execution order, and generally any MSBuild build issues. Requires an existing .binlog file. DO NOT USE FOR: generating…