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/samfold/mcp.net/agents-mdgit clone --depth 1 https://github.com/SamFold/Mcp.NetWhat 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 | $0.01417 | $0.01417 |
| Opus 5 | $0.00709 | $0.00709 |
| Sonnet 5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
Mcp.Net AGENTS.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 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mcp.Net AGENTS.md
Project Structure
Mcp.Net.slnis the root solution.- Core libraries live in
Mcp.Net.Core,Mcp.Net.Client,Mcp.Net.Server, andMcp.Net.LLM. - Runnable samples live under
Mcp.Net.Examples.*andMcp.Net.WebUi. - Automated tests live in
Mcp.Net.Tests. - Ongoing planning and dev history live under
docs/.
Build, Test, and Development Commands
dotnet restore Mcp.Net.slndotnet build Mcp.Net.sln -c Releasedotnet test Mcp.Net.Tests/Mcp.Net.Tests.csproj -c Releasedotnet formatdotnet run --project Mcp.Net.Examples.SimpleServer/Mcp.Net.Examples.SimpleServer.csprojdotnet run --project Mcp.Net.Examples.SimpleClient/Mcp.Net.Examples.SimpleClient.csproj -- --url http://localhost:5000 --auth-mode pkce
Working Style
- Default to TDD.
- For non-trivial changes, write or update a failing test first, then implement the smallest code change to make it pass.
- After the focused test passes, run the next broader relevant test scope before finishing.
- Keep each change set to one coherent vertical slice. Do not mix unrelated refactors into the same slice.
- Prefer minimal, comprehensible changes over broad rewrites.
- Keep each active
docs/vnext/*.mdslice roughly commit-sized.
Planning and Docs
docs/vnext.mdis the repo-level planning index for active component and system tracks.- Detailed next-slice planning lives in per-component files under
docs/vnext/. - Update the relevant
docs/vnext/*.mdtrack file or files before substantial implementation when the planned slice changes. - Update the same
docs/vnext/*.mdtrack file or files again after completing a slice so they point at the next slice for that area. - If a change spans multiple components, update each affected track or create a dedicated cross-cutting track.
docs/roadmap.mdis the repo-level roadmap index for medium-term sequencing and should be updated whenever priorities, milestones, or major decisions change.- Detailed medium-term planning lives in project-specific files under
docs/roadmap/. docs/testing.mdis the canonical testing policy for this repo.- Keep design notes, technical plans, and deeper writeups in
docs/rather than scattering new markdown files at the repo root.
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 · 114 lines · 1,417 tokens per session scan A 32215dbcc3de
Mcp.Net AGENTS.md is an instructions file published in the GitHub repository SamFold/Mcp.Net (38 stars, last pushed 5mo ago), licensed MIT. It adds 1,417 tokens to every session, about $0.0071 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 2026-08-30.
Other instructions, from other repositories
atc-claude-kanban CLAUDE.md
Instructions for atc-net/atc-claude-kanban, covering claude.md, project overview, build & test, build (release mode enforces all analyzer rules as errors) and run tests (115 tests across 11 test classes).
ElBruno.MempalaceNet copilot-instructions.md
Instructions for elbruno/ElBruno.MempalaceNet, covering github copilot instructions for mempalace.net, installation, nuget package, cli tool and basic usage patterns.
seq-mcp-server CLAUDE.md
Instructions for willibrandon/seq-mcp-server, covering claude.md, commands, development environment setup, powershell and bash.
fieldcure-mcp-essentials CLAUDE.md
Claude Code instructions for fieldcure/fieldcure-mcp-essentials, covering fieldcure.mcp.essentials, tool authoring conventions, runcommandtool subtleties, tests and release process.
moorestech AGENTS.md
AGENTS.md instructions for moorestech/moorestech, covering コーディングの指針, qa（必須）, 互換性とパフォーマンス, 既知の制約（設計上の割り切り） and regionの活用.
bitfinex-net
Use Bitfinex.Net when generating C#/.NET code that interacts with Bitfinex, including Spot, margin, derivatives symbols, funding, REST endpoints, WebSocket subscriptions, account management, market data, or order placement. Triggers on Bitfinex integration requests in C#, .NET, dotnet, F#, or VB.NET context.