Borrowing it
Nothing to install: this file belongs to managedcode/dotPilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/managedcode/dotPilot/main/.codex/skills/dotnet-microsoft-agent-framework/references/official-docs/tutorials/agents/middleware.mdgit clone --depth 1 https://github.com/managedcode/dotPilotWrote 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/agents/managedcode/dotpilot/middleware)<a href="https://agentmods.dev/agents/managedcode/dotpilot/middleware"><img src="https://agentmods.dev/badge/agents/managedcode/dotpilot/middleware/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/agents/managedcode/dotpilot/middleware"><img src="https://agentmods.dev/badge/agents/managedcode/dotpilot/middleware.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 | $0.00007 | $0.02236 |
| Opus 5.5 | $0.00003 | $0.00894 |
| Sonnet 5.5 | $0.00001 | $0.00447 |
| Haiku 4.5 | $0.00001 | $0.00224 |
Grade A, and why
middleware 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 1mo 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding Middleware to Agents
Learn how to add middleware to your agents in a few simple steps. Middleware allows you to intercept and modify agent interactions for logging, security, and other cross-cutting concerns.
::: zone pivot="programming-language-csharp"
Prerequisites
For prerequisites and installing NuGet packages, see the Create and run a simple agent step in this tutorial.
Step 1: Create a Simple Agent
First, create a basic agent with a function tool.
using System;
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI;
[Description("The current datetime offset.")]
static string GetDateTime()
=> DateTimeOffset.Now.ToString();
AIAgent baseAgent = new AzureOpenAIClient(
new Uri("https://<myresource>.openai.azure.com"),
new AzureCliCredential())
.GetChatClient("gpt-4o-mini")
.AsAIAgent(
instructions: "You are an AI assistant that helps people find information.",
tools: [AIFunctionFactory.Create(GetDateTime, name: nameof(GetDateTime))]);
Step 2: Create Your Agent Run Middleware
Next, create a function that will get invoked for each agent run. It allows you to inspect the input and output from the agent.
Unless the intention is to use the middleware to stop executing the run, the function
should call RunAsync on the provided innerAgent.
This sample middleware just inspects the input and output from the agent run and outputs the number of messages passed into and out of the agent.
using System.Collections.Generic;
using System.Linq;
using System.Threading;
using System.Threading.Tasks;
async Task<AgentResponse> CustomAgentRunMiddleware(
IEnumerable<ChatMessage> messages,
AgentThread? thread,
AgentRunOptions? options,
AIAgent innerAgent,
CancellationToken cancellationToken)
{
Console.WriteLine($"Input: {messages.Count()}");
var response = await innerAgent.RunAsync(messages, thread, options, cancellationToken).ConfigureAwait(false);
Console.WriteLine($"Output: {response.Messages.Count}");
return response;
}
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.
- 1mo ago First seen · 323 lines · 7 tokens per session scan A 368441f61080
middleware is an agent published in the GitHub repository managedcode/dotPilot (25 stars, last pushed 6mo ago), licensed MIT. It adds 7 tokens to every session and 2,236 once invoked, about $0.0000 per session on Opus 5.5. 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 agents, from other repositories
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
harness-radar
Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — from the best-of-Agent-Harnesses dataset, which rescores itself every week. Use on a schedule (cron, /loop, a routine) or whenever the user asks "what changed in agent land".
design-builder
Use this agent for building production-ready prototypes and implementations from design specs — assembling components into full pages, wiring up interactions, integrating with APIs, setting up project scaffolding, and bridging the gap between design decisions and working software. Dispatch after the design-lead has…
inspiration-scout
Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.
world-agent
A world-state and turn-management agent for the Kagurajima setting. It sends each turn to the active character agents, combines their results, and closes the turn with the final story.