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/managedcode/mcpgateway/agents-mdgit clone --depth 1 https://github.com/managedcode/MCPGatewayWhat 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 | $0.08489 | $0.08489 |
| Opus 5 | $0.04244 | $0.04244 |
| Sonnet 5 | $0.01698 | $0.01698 |
| Haiku 4.5 | $0.00849 | $0.00849 |
Grade A, and why
MCPGateway 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 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project: ManagedCode.MCPGateway Stack: .NET 10, C# 14, Microsoft.Extensions.AI, ModelContextProtocol, TUnit, GitHub Actions, NuGet
Follows MCAF
Purpose
This file defines how AI agents work in this solution.
- Root
AGENTS.mdholds the global workflow, shared commands, cross-cutting rules, and global skill routing. - The solution keeps project-local
AGENTS.mdfiles for the package and test projects so work can stay scoped. - Local
AGENTS.mdfiles refine entry points, boundaries, commands, and risks for their subtree without weakening root policy.
Solution Topology
- Solution root:
. - Projects or modules with local
AGENTS.mdfiles:src/ManagedCode.MCPGateway/benchmarks/ManagedCode.MCPGateway.Benchmarks/tests/ManagedCode.MCPGateway.Tests/
Conversations (Self-Learning)
Learn the user's habits, preferences, and working style. Extract rules from conversations, save to "## Rules to follow", and generate code according to the user's personal rules.
Update requirement (core mechanism):
Before doing ANY task, evaluate the latest user message.
If you detect a new rule, correction, preference, or change -> update AGENTS.md first.
Only after updating the file you may produce the task output.
If no new rule is detected -> do not update the file.
When to extract rules:
- prohibition words (never, don't, stop, avoid) or similar -> add NEVER rule
- requirement words (always, must, make sure, should) or similar -> add ALWAYS rule
- memory words (remember, keep in mind, note that) or similar -> add rule
- process words (the process is, the workflow is, we do it like) or similar -> add to workflow
- future words (from now on, going forward) or similar -> add permanent rule
Preferences -> add to Preferences section:
- positive (I like, I prefer, this is better) or similar -> Likes
- negative (I don't like, I hate, this is bad) or similar -> Dislikes
- comparison (prefer X over Y, use X instead of Y) or similar -> preference rule
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 · 386 lines · 8,489 tokens per session scan A 6a7b8160b39c
MCPGateway AGENTS.md is an instructions file published in the GitHub repository managedcode/MCPGateway (5 stars, last pushed 2d ago), licensed MIT. It adds 8,489 tokens to every session, about $0.0424 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
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.
ElBruno.ModelContextProtocol copilot-instructions.md
Instructions for elbruno/ElBruno.ModelContextProtocol, covering elbruno .net repository conventions, repository structure, solution format, project conventions and library projects.
nina AGENTS.md
Instructions for isbeorn/nina, covering agents.md, scope, documentation boundary, repository knowledge and code style and formatting.
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.
Bitfinex.Net copilot-instructions.md
Instructions for JKorf/Bitfinex.Net, covering copilot instructions for bitfinex.net, use bitfinex.net, not raw http, client setup, result handling and api structure.
appointme CLAUDE.md
Instructions for bravodev-hub/appointme, covering claude.md, build and development commands, running the full stack (recommended), backend only and frontend only.