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-docs-agents)<a href="https://agentmods.dev/rules/vudz/roslynmcpserver/roslyn-mcp-docs-agents"><img src="https://agentmods.dev/badge/rules/vudz/roslynmcpserver/roslyn-mcp-docs-agents/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-docs-agents"><img src="https://agentmods.dev/badge/rules/vudz/roslynmcpserver/roslyn-mcp-docs-agents.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 | $0.00603 | $0.00603 |
| Opus 5 | $0.00302 | $0.00302 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
roslyn-mcp-docs-agents 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs & agent conventions
Layers
| Layer | Role |
|---|---|
MCP tool [Description] |
Per-tool API: params, caps, anti-patterns |
AGENTS.md.sample |
Session policy only (when / MCP vs host / bans) — copy to app repos as AGENTS.md |
| README «Agent tools by version» + Reference: MCP Tools | Human changelog + tool catalog |
| README Agent Initialization | Short pointer to sample — not a full copy of AGENTS |
Keep in sync (when tools change)
When adding/changing MCP tools, Descriptions, or agent-visible behavior, update together:
AGENTS.md.sample— only if session policy changes (init, bans, hybrid search, edit/secrets). Do not paste tool params/caps into AGENTS.README.md— «Agent tools by version» (semver row) and Reference: MCP Tools (EN; RU Reference as needed) when the public tool surface changes.- Version in
RoslynMcpServer.csprojwhen shipping tool changes (seeroslyn-mcp-version-bump.mdc).
Copy AGENTS.md.sample → app repo AGENTS.md — no machine-specific paths.
Agent workflow (summary)
- Quick read-only:
load_workspace→ symbol tools / Grep. - Edit/build/test/run: full init → MCP
dotnet_*only (no shelldotnet build/test). - After MCP rebuild:
get_mcp_server_infoexpect current version (1.1.0+). - Windows PowerShell 5.x: use
;between commands, not&&. - Secrets: never PAT/passwords in chat/commits; env / user-secrets; report configured yes/no only.
- IDE edits: host edit/write; headless: MCP
apply_patch/ AST tools. - Rename:
previewOnly=truefirst.
App repos should document
Executable .csproj for run_dotnet_run, sample args, global.json pin, integration notes (TFS vs Azure) in README or .cursor/rules — not in portable AGENTS alone.
Spec archive
Epoch plans and review packages: see roslyn-mcp-docs-lifecycle.mdc (start-of-work junk check; remind to archive when the series is closed).
Engineering style (this repo)
Base Truth: minimal diffs; no wholesale rewrites. Async I/O; no .Result/.Wait(). Null-check references. Tests: xUnit (+ Moq when mocking). Prefer Options/IOptions for config if adding settings.
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 · 48 lines · 603 tokens per session scan A dd53217be3c2
roslyn-mcp-docs-agents is a cursor rule published in the GitHub repository VuDZ/RoslynMcpServer (7 stars, last pushed yesterday), licensed MIT. It adds 603 tokens to every session, about $0.0030 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 2026-09-14.
Other cursor rules, from other repositories
aspnet-abp-cursorrules-prompt-file
Cursor rules for Aspnet Abp.
python-app
Here's how the python application is organized.
typescript
Here's how frontend code is organized in web/app/.
pn-php-backend
PHP backend style, env, and error handling. Use for API and server code (Laravel, Slim).
pn-ruby-backend
Ruby backend style, env, and error handling. Use for API and server code (Rails, Sinatra).
pn-rust-backend
Rust backend style, env, and error handling. Use for API and server code (Actix-web, Axum).