Plugin Claude Code
Compiler-aware C# code intelligence for Claude Code, built on Roslyn.
Plugin Claude Code
Compiler-aware C# code intelligence for Claude Code, built on Roslyn.
Plugin Claude Code
Compiler-aware C# code intelligence for .NET repos — Roslyn-backed symbol search, reference tracing, and edits validated against the compiler before they touch disk.
Settings file Claude Code
Agent settings declaring 23 allowed tools.
MCP server Claude CodeCodexCursor +2
MCP server "dotnet" as configured in Attemainio/dotnet-toolkit. Launched with dotnet ${CLAUDE_PLUGIN_ROOT}/dist/DotnetToolkit.McpServer.dll.
Instructions file
Instructions for Attemainio/dotnet-toolkit, covering claude.md, what this is, non-negotiable workflow, commands and where to read what.
Agent
Reviews C#/.NET code across ALL quality aspects at once — correctness, naming, styling, best practices, performance, concurrency, security, test coverage, XML documentation, and dead code/duplication — within one precisely stated scope. Designed to run in parallel with other instances of itself: partition a large…
Agent
Locates the C# symbols, references, and files a task touches, and reports the blast radius — before any code is written. Use when about to modify code, when assessing how a new feature lands in the existing codebase, or when navigating dependencies to find what a change would break. Returns symbolIds and file:line…
Agent
Audit-only instrument for dotnet-guard-audit. Attempts a battery of known and improvised bypasses against this repo's own guard-cs-edit, guard-cs-read, guard-cs-bash-read and guard-cs-bash-write PreToolUse hooks — unusual quoting, spaced paths, symlinks, copies, variable expansion, and writing to a .cs file through…
Agent
Benchmark-only instrument for dotnet-performance. Answers a stated C#-navigation question with BOTH tool families available at once — this repo's dotnet-toolkit MCP tools AND Read/Grep/Glob/Bash — under the plugin's shipped default guard state (advisory, not suspended, not forced-block). Plays a real, unrestricted…
Agent
Benchmark-only instrument for dotnet-performance. Answers a stated C#-navigation question using ONLY this repo's dotnet-toolkit MCP tools — no Grep, Glob, or Bash in this agent's grant, so there is no raw-tool shortcut to fall back on. Pairs with dotnet-perf-raw-probe: the two are identical except for which tool…
Agent
Benchmark-only instrument for dotnet-performance. Answers a stated C#-navigation question using ONLY Read/Grep/Glob/Bash — no MCP tool of any kind in this agent's grant, so there is nothing to reach for beyond raw search and reads. Pairs with dotnet-perf-mcp-probe: the two are identical except for which tool family…
Hook
Runs before the agent uses a tool for Edit, Write, NotebookEdit, Read, Bash and mcp__plugin_dotnet-toolkit_dotnet__validate_patch tool calls, running an inline shell check (5 commands). From Attemainio/dotnet-toolkit.
Hook
Runs after a tool call finishes for Write tool calls, running an inline shell check (2 commands). From Attemainio/dotnet-toolkit.
Skill Claude CodeCodex
Use when auditing this plugin's own docs, skills, agents, rules, hooks, CLAUDE.md and README.md — three axes at once. (1) Do they match the actual MCP tool implementation under src/DotnetToolkit.McpServer? Run after adding, removing, renaming, or changing the signature/return shape/[Description] of a tool, or after…
Skill Claude CodeCodex
Use before changing C#/.NET code when the set of symbols the task touches is not already known — surveying an unfamiliar subsystem, assessing how a new feature lands in the existing codebase, or finding out what a change would break. Delegates the wide searchindex/getreferences sweep to the plugin's dotnet-explore…
Skill Claude CodeCodex
Use when asked to check whether this plugin's own guard hooks actually enforce what they claim — "try to break the .cs guards", "red-team the hooks", "does the read guard actually fire on X", "audit guard-cs-edit/read/bash-read/bash-write for bypasses", "can you get an edit past validatepatch through Bash". Launches…
Skill Claude CodeCodex
Use when the user asks to set up, install, wire up, verify, refresh, or remove dotnet-toolkit in a project — "set up dotnet-toolkit here", "/dotnet-init", "make Claude use the MCP tools in this repo", and equally "did the init work", "check the dotnet-toolkit installation", "is this repo wired up correctly", "are my…
Skill Claude CodeCodex
Use when asked what dotnet-toolkit actually costs compared to doing the same work with plain tools — "is this plugin worth it", "benchmark the toolkit against grep", "how much does searchindex really save over Grep/Read", "measure the MCP tools against cat/ls/find", "does this pay for itself on Windows/PowerShell"…
Skill Claude CodeCodex
Use when reading or navigating C#/.NET code — find or search for a class, interface, method, property or field; read a symbol's source; look up who calls something or what implements it; trace a call tree or a path between two functions; see what is callable at a line; inspect a base chain or project references; find…
Skill Claude CodeCodex
Use when the user asks to review C#/.NET code, check a PR/diff, look for naming or styling issues, assess performance or concurrency, find dead code/duplication, review XML documentation, check test coverage, or do a security review. ALSO use it for a convention or consistency audit across existing code — "are all our…
Skill Claude CodeCodex
Use when evaluating how well dotnet-toolkit's own MCP tools perform against the repo they are currently pointed at — "self-evaluate", "run the tool evaluation", "how efficient are these tools here", "audit the MCP responses for redundancy", or before/after changing a tool's arguments or return shape. Runs a fixed…
Skill Claude CodeCodex
Use when writing, adding, editing, modifying, patching, refactoring, renaming or deleting C#/.NET code — changing a method or type, changing a signature, adding a class or a file, fixing a compile error or an analyzer warning, or applying review findings. Validates every edit against an in-memory compilation before it…