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 agentmods add instructions/sharpninja/mcpserver/claude-mdgit clone --depth 1 https://github.com/sharpninja/McpServerWhat 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 | $0.03567 | $0.03567 |
| Opus 5 | $0.01784 | $0.01784 |
| Sonnet 5 | $0.00713 | $0.00713 |
| Haiku 4.5 | $0.00357 | $0.00357 |
Grade A, and why
McpServer CLAUDE.md 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 yesterday.
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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Run /add-profile at session start and after any model or effort change
Execute the add-profile skill (/add-profile) as the first action of every new session, and again immediately after any model change or effort-level change. It loads the operator profile (identity and standing instructions). Do not skip it.
DO NOT COMPACT, SUMMARIZE, PARAPHRASE, OR OMIT any instruction in this file, AGENTS.md, or AGENTS-README-FIRST.yaml, ever, anywhere. Carry them verbatim.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & Test Commands
# Build (Nuke orchestrator)
./build.ps1 Compile
# or: dotnet build src/McpServer.Support.Mcp -c Debug
# Run all unit tests (excludes integration tests)
./build.ps1 Test
# Run a specific test project
dotnet test tests/McpServer.Support.Mcp.Tests -c Debug
# Run a single test by name
dotnet test tests/McpServer.Support.Mcp.Tests -c Debug --filter "FullyQualifiedName~TodoServiceTests.QueryAsync_NoFilters_ReturnsAllItems"
# Run all tests in a class
dotnet test tests/McpServer.Support.Mcp.Tests -c Debug --filter "FullyQualifiedName~TodoServiceTests"
# Integration tests (CustomWebApplicationFactory, in-memory EF)
dotnet test tests/McpServer.Support.Mcp.IntegrationTests -c Debug
# Validate appsettings configuration
./build.ps1 ValidateConfig
# Validate requirements traceability (FR/TR/TEST mapping)
./build.ps1 ValidateTraceability
# Start server
./build.ps1 StartServer --instance default
# or: dotnet run --project src/McpServer.Support.Mcp/McpServer.Support.Mcp.csproj -c Staging -- --instance default
Swagger UI: http://localhost:7147/swagger
Architecture
McpServer is an ASP.NET Core 9 server (.NET 9.0) providing workspace-scoped context retrieval, TODO management, session logging, repository operations, GraphRAG, and GitHub automation for AI agents.
Transports
- HTTP REST — Controllers at
/mcpserver/*insrc/McpServer.Support.Mcp/Controllers/ - MCP Streamable HTTP — JSON-RPC wire protocol at
/mcp-transport - MCP STDIO —
--transport stdioflag; tools inMcpStdio/FwhMcpTools.cs
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.
- yesterday First seen · 255 lines · 3,567 tokens per session scan A 8363fc9ed580
McpServer CLAUDE.md is an instructions file published in the GitHub repository sharpninja/McpServer (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 3,567 tokens to every session, about $0.0178 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 instructions, from other repositories
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
com-example-config-AsyncTestConfig
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
UsageAtlas AGENTS.md
Instructions for SRX9/UsageAtlas, covering repository guidelines and coding approach.