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/VuDZ/RoslynMcpServerWrote 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/rules/vudz/roslynmcpserver/roslyn-mcp-decompile)<a href="https://agentmods.dev/rules/vudz/roslynmcpserver/roslyn-mcp-decompile"><img src="https://agentmods.dev/badge/rules/vudz/roslynmcpserver/roslyn-mcp-decompile/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/rules/vudz/roslynmcpserver/roslyn-mcp-decompile"><img src="https://agentmods.dev/badge/rules/vudz/roslynmcpserver/roslyn-mcp-decompile.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 | $0.00000 | $0.00287 |
| Opus 5 | $0.00000 | $0.00143 |
| Sonnet 5 | $0.00000 | $0.00057 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
roslyn-mcp-decompile 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.
What it actually says
Decompile & assembly resolve
Exact resolve (v1.0.13+)
AssemblyReferenceResolver / DepsJsonAssemblyPathResolver / NuGetFallbackAssemblyResolver:
- Prefer exact
{assemblyName}.dll— no fuzzyContainsmatching (wrong DLL / BadImage). - Resolve via project
deps.json, then NuGet cache, then BCL / runtime pack maps (BclAssemblyPackageMap). - Tools accept
assemblyName(afterload_workspace) orassemblyPath.
DecompilerHost
ILSpy-backed; circuit breakers (e.g. decompile_type max ~500 lines). Large types → skeleton first.
API assumptions
Do not invent NuGet APIs from memory — decompile first. Especially Azure DevOps / TFS:
- Decompile
Microsoft.VisualStudio.Services.WebApi(or graph-named assembly). - Do not assume cloud
VssConnection.CreateAsync(organization)for on-prem — collection URI + Windows/PAT.
Tests
AssemblyReferenceResolverTests, DepsJsonAssemblyPathResolverTests, NuGetFallbackAssemblyResolverTests.
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 · 31 lines · 0 tokens per session scan A 8fabcd9816f5
roslyn-mcp-decompile is a cursor rule published in the GitHub repository VuDZ/RoslynMcpServer (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 287 tokens. 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 2026-09-14.
Other cursor rules, from other repositories
code-style
Formatting, lint, comments language.
python-app
Here's how the python application is organized.
typescript
Here's how frontend code is organized in web/app/.
python-code-style-for-apps
Python 3.14 code style for ArchiPy apps — formatting, imports, docstrings, errors, complexity.
codesynapse-cli
Use this rule to answer codebase architecture questions, trace dependencies, find callers/callees, calculate blast radius, and explore the code graph. Triggers on: "how does X work", "what handles Y", "where is Z defined", "explain the mechanism", "who calls", "blast radius", "shortest path", "trace request flow"…
pn-rust-backend
Rust backend style, env, and error handling. Use for API and server code (Actix-web, Axum).