agent-rag

A guide for adding retrieval-augmented generation (RAG) to agents built with Microsoft Agent Framework. RAG lets an agent search connected documents or other text and use the results when answering.

In plain words
What is it for?
Building support or knowledge assistants that search documents and include that context in their answers, using C# examples.
Why use it?
It helps agents answer from relevant source material instead of relying only on their general training. It also shows how to provide source citations when available.

Agent for Codex

Install

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.

agentmods
npx agentmods add agents/managedcode/prompterone/agent-rag
Clone the repo
git clone --depth 1 https://github.com/managedcode/PrompterOne

Made for: Codex.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,729 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.02729
Opus 5 $0.00008 $0.01365
Sonnet 5 $0.00003 $0.00546
Haiku 4.5 $0.00002 $0.00273

Measured yesterday against content hash e21cea9b85dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-rag 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • agent-rag — 100% identical, 0 lines differ
.codex/skills/dotnet-microsoft-agent-framework/references/official-docs/user-guide/agents/agent-rag.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Retrieval Augmented Generation (RAG)

Microsoft Agent Framework supports adding Retrieval Augmented Generation (RAG) capabilities to agents easily by adding AI Context Providers to the agent.

::: zone pivot="programming-language-csharp"

Using TextSearchProvider

The TextSearchProvider class is an out-of-the-box implementation of a RAG context provider.

It can easily be attached to a ChatClientAgent using the AIContextProviderFactory option to provide RAG capabilities to the agent.

The factory is an async function that receives a context object and a cancellation token.

// Create the AI agent with the TextSearchProvider as the AI context provider.
AIAgent agent = azureOpenAIClient
    .GetChatClient(deploymentName)
    .AsAIAgent(new ChatClientAgentOptions
    {
        ChatOptions = new() { Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available." },
        AIContextProviderFactory = (ctx, ct) => new ValueTask<AIContextProvider>(
            new TextSearchProvider(SearchAdapter, ctx.SerializedState, ctx.JsonSerializerOptions, textSearchOptions))
    });

The TextSearchProvider requires a function that provides the search results given a query. This can be implemented using any search technology, e.g. Azure AI Search, or a web search engine.

Here is an example of a mock search function that returns pre-defined results based on the query. SourceName and SourceLink are optional, but if provided will be used by the agent to cite the source of the information when answering the user's question.

static Task<IEnumerable<TextSearchProvider.TextSearchResult>> SearchAdapter(string query, CancellationToken cancellationToken)
{
    // The mock search inspects the user's question and returns pre-defined snippets
    // that resemble documents stored in an external knowledge source.
    List<TextSearchProvider.TextSearchResult> results = new();

    if (query.Contains("return", StringComparison.OrdinalIgnoreCase) || query.Contains("refund", StringComparison.OrdinalIgnoreCase))
    {
        results.Add(new()
        {
            SourceName = "Contoso Outdoors Return Policy",
            SourceLink = "https://contoso.com/policies/returns",
            Text = "Customers may return any item within 30 days of delivery. Items should be unused and include original packaging. Refunds are issued to the original payment method within 5 business days of inspection."
        });
    }

    return Task.FromResult<IEnumerable<TextSearchProvider.TextSearchResult>>(results);
}

Read the full file on GitHub · 304 lines

Changes

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.

  1. yesterday First seen · 304 lines · 15 tokens per session scan A e21cea9b85dc

Subscribe to this mod's changes

agent-rag is an agent published in the GitHub repository managedcode/PrompterOne (42 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 2,729 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

release-manager

Owns the end-to-end modelcontextprotocol/csharp-sdk release process, orchestrating the prepare-release and publish-release skills (and the bump-version and breaking-changes skills they build on) across five stages: prepare (assess SemVer, bump the version, run ApiCompat/ApiDiff, review docs, draft release notes, open…

modelcontextprotocol/csharp-sdk · 317 tokens

wpf-data-binding-expert

WPF data binding specialist. Implements complex bindings (MultiBinding, PriorityBinding), custom converters, validation patterns, and debugging binding issues.

christian289/dotnet-with-claudecode · 34 tokens

wpf-control-designer

WPF CustomControl design and implementation specialist. Defines DependencyProperty, implements Parts and States Model, OnApplyTemplate patterns.

christian289/dotnet-with-claudecode · 30 tokens

serena-initializer

Serena MCP initialization agent. Checks if current project is activated and onboarded in Serena, performs activation and onboarding if not completed. Use when starting work on a new project or when Serena tools fail.

christian289/dotnet-with-claudecode · 46 tokens

theme-slot-auditor

Read-only auditor for Fluence.Wpf theming structure. Use after any theme, brush, color, accent, or ApplicationThemeManager change to verify the three-slot MergedDictionaries invariant, that slot [0] is rebuilt and replaced every Apply, DynamicResource usage, BrushFactory auto-twinning, canonical WinUI key names, and…

sintaxasn/Fluence.Wpf · 90 tokens

net472-feasibility-checker

Read-only checker that verifies new or changed code in Fluence.Wpf stays runnable on net472. Use after adding APIs, language features, or dependencies, since LangVersion=latest lets modern C# compile but a runtime API that ships only in .NET 10 fails on the separate net472 test lane. Enforces AGENTS.md section 4.3.

sintaxasn/Fluence.Wpf · 81 tokens