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 JSungMin/rider-mcp-enforcer --skill rider-searchgit clone --depth 1 https://github.com/JSungMin/rider-mcp-enforcerWrote 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/jsungmin/rider-mcp-enforcer/rider-search)<a href="https://agentmods.dev/skills/jsungmin/rider-mcp-enforcer/rider-search"><img src="https://agentmods.dev/badge/skills/jsungmin/rider-mcp-enforcer/rider-search/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/jsungmin/rider-mcp-enforcer/rider-search"><img src="https://agentmods.dev/badge/skills/jsungmin/rider-mcp-enforcer/rider-search.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 | $0.00060 | $0.01542 |
| Opus 5.5 | $0.00024 | $0.00617 |
| Sonnet 5.5 | $0.00012 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
rider-search 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rider search routing
This project is open in JetBrains Rider with the Rider MCP server connected (server name: rider-search). Karpathy-style rules: do the listed thing, do not improvise.
Tools (real Rider MCP 2025.2+ names)
- Symbol / definition →
search_symbol(args:q,limit,include_external,paths,projectPath). Nevergrep/rgfor this. - File by name →
search_fileorfind_files_by_name_keyword/find_files_by_glob. Neverfind -namefor source files. - Text / regex in code (also the way to find references — see note) →
search_text/search_regex(orsearch_in_files_by_text/search_in_files_by_regex). - Type info / signature at a position →
get_symbol_info(args:filePath,line,column). - Rename a symbol →
rename_refactoring(args:pathInProject,symbolName,newName). Never sed/replace across files for a rename. read_file/get_file_text_by_pathto read, notcat.
projectPath / open projects
- Rider MCP only searches projects currently open in the IDE (and finished indexing). A path that isn't open returns "doesn't correspond to any open project" — tell the user to open it in Rider.
- Rider errors if multiple projects are open and
projectPathis omitted. PassprojectPath, or have the user setRIDER_PROJECT_PATHso the proxy injects it. If a call returns "Unable to determine the target project" with a numbered project list, ask the user which project, then pass its path.
No dedicated find-usages
This Rider MCP build has no semantic find-references/find-usages tool. To find references, use
search_text/search_regex on the symbol name (string match, like grep but indexed + token-capped).
Don't claim semantic usage results you didn't get.
Inline lookup vs. delegating to the code-locator subagent
- One or two quick lookups whose results you want in front of you: call the Rider tool inline. That's the cheapest path. A subagent spends ~15k tokens of its own to hand back ~300, so it's wasteful for a single lookup.
- The moment you reach a third related lookup, or you already know this is a multi-step trace (find
the symbol, then its callers, then where those are declared), hand the whole investigation to the
code-locatorsubagent in one call. It runs every lookup in its own context and returns one compactfile:linetable, so the raw results never pile up in yours. - Rule of thumb: inline for 1–2; batch-delegate at 3+ related lookups or any multi-step trace. Don't spawn a subagent for a single lookup, and don't run ten sequential inline lookups when one delegation would do. "Related" is the signal — count alone doesn't decide it.
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.
- 1mo ago First seen · 87 lines · 60 tokens per session scan A 6c4b24292415
rider-search is a skill published in the GitHub repository JSungMin/rider-mcp-enforcer (3 stars, last pushed 13d ago), licensed MIT. It adds 60 tokens to every session and 1,542 once invoked, about $0.0002 per session on Opus 5.5. 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
blazing-fast-dotnet
High-performance .NET guidance for writing and tuning C# apps and benchmarks (BenchmarkDotNet, ASP.NET, challenges). Use when asked to make .NET code faster, reduce allocations or GC overhead, fix lock contention or thread pool starvation, inspect JIT codegen, profile apps, or tune runtime/NativeAOT settings.
profiling
Use the free official .NET diagnostics CLI tools for profiling and runtime investigation in .NET repositories. USE FOR: the repo needs performance or runtime profiling for a .NET application; the user asks about slow code, high CPU, GC pressure, allocation growth, exception storms, lock. DO NOT USE FOR: replacing…
roslyn-codelens
Use when working with any .NET / C# code (.cs/.csproj/.sln/.slnx files), finding callers/references/implementations, checking compiler errors or warnings, running dotnet build for diagnostics, searching for a type/method/interface by name, inspecting DI registrations, detecting dead code or circular dependencies…
dotnet-analyzers
Run dotnet format to fix code style and analyzer diagnostics (IDE0005, CA, SA). Use when fixing unnecessary usings, code style violations, analyzer warnings, or verifying format compliance.
cs0618-hunter
Detects and fixes CS0618 obsolete API warnings in .NET builds. The compiler is the authoritative source for what your project actually triggers — it catches transitive obsoletions, overload-resolution surprises, and project-local [Obsolete] attributes that static inspection cannot see. Pair with the repository-pinned…
nuget-diff-analyzer
Post-processes the repository-pinned [email protected] -- diff output into a categorised report (breaking / additive / newly-obsolete) with each finding cross-referenced to the MAF obsolete-API registry.