getting-started

A quick-start guide for running a C# software agent with the Conductor AI SDK, a .NET package for connecting agents to a Conductor server. It covers creating a .NET 8 console project, configuring the server, and setting environment variables.

In plain words
What is it for?
Use it to create a new C# agent project, install or reference the SDK, connect to a local or cloud Conductor server, configure an AI model, and provide authentication credentials.
Why use it?
It removes the setup guesswork needed to get a first agent running and explains the difference between a local server and Orkes Cloud authentication. It also points out that older AGENTSPAN settings no longer work.

Agent

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/conductor-oss/csharp-sdk/getting-started
Clone the repo
git clone --depth 1 https://github.com/conductor-oss/csharp-sdk
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 921 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 $0.00000 $0.00921
Opus 5 $0.00000 $0.00461
Sonnet 5 $0.00000 $0.00184
Haiku 4.5 $0.00000 $0.00092

Measured yesterday against content hash 8b6ad8a7e111, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

getting-started 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.

docs/agents/getting-started.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Getting Started

Get an agent running in under 30 seconds.

1. Install

The SDK ships as the conductor-ai NuGet package (target framework: .NET 8).

dotnet new console -n MyAgent
cd MyAgent
dotnet add package conductor-ai

Working inside this repository instead of from NuGet? Reference the project directly:

<ItemGroup>
  <ProjectReference Include="path/to/sdk/csharp/src/Conductor.AI/Conductor.AI.csproj" />
</ItemGroup>

2. Point at a server

You need a running Conductor server. The defaults assume a local one at http://localhost:8080/api.

Variable Default Description
CONDUCTOR_SERVER_URL http://localhost:8080/api Server URL.
CONDUCTOR_AUTH_KEY Auth key. Unset = no-auth mode (local / OSS).
CONDUCTOR_AUTH_SECRET Auth secret. Set together with the key for Orkes Cloud.

The legacy AGENTSPAN_* names were removed and have no effect — see ../upgrading.md.

export CONDUCTOR_SERVER_URL=http://localhost:8080/api
export OPENAI_API_KEY=<YOUR-KEY>
export CONDUCTOR_AGENT_LLM_MODEL=openai/gpt-4o-mini
# Orkes Cloud only:
# export CONDUCTOR_AUTH_KEY=...
# export CONDUCTOR_AUTH_SECRET=...

The runtime reads the CONDUCTOR_* connection variables on construction. You can also pass them explicitly via AgentRuntimeOptions (see concepts/deploy-serve-run.md).

CONDUCTOR_AGENT_LLM_MODEL is a convention of the bundled examples, not something the SDK itself reads — an Agent takes its model from the Model property. It's shown here because every example under Conductor.AI.Examples/ picks it up.

3. Run an agent

Replace Program.cs with:

using Conductor.AI;

var agent = new Agent("greeter")
{
    Model        = "anthropic/claude-sonnet-4-6",
    Instructions = "You are a friendly assistant. Keep responses brief.",
};

await using var runtime = new AgentRuntime();
var result = await runtime.RunAsync(agent, "Say hello and tell me a fun fact about C#.");
result.PrintResult();

Read the full file on GitHub · 96 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 · 96 lines · 0 tokens per session scan A 8b6ad8a7e111

Subscribe to this mod's changes

getting-started is an agent published in the GitHub repository conductor-oss/csharp-sdk (53 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 921 tokens. 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

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens

brainstorm-facilitator

Runs the operator's brainstorm phase (phase 2, machine/phases-registry.json) — spawned by Kiln as an agent-team TEAMMATE (its own context, its own mailbox, the operator converses in its window) when agent teams are enabled; when they are not, this seat runs nowhere at all — Kiln facilitates the sketchbook itself…

Fredasterehub/kiln · 235 tokens

i18n

你是一个精通 Vue3 国际化架构的前端专家(专注于 Vue3 + TypeScript + Composition API)。同时,你也是一位专业的 UI/UX 翻译专家,擅长将中文界面语言翻译为地道、简洁的英文。.

zhimaAi/chatwiki · 7 tokens

data-etl-worker

Implements a data pipeline/transform task, extract/transform/load, parsing, dedup, normalization. Write-capable; prefers DuckDB SQL for the transform per the house stack. Dispatched by /kit:execute step 2b-0 as the data-etl domain implementer.

dwarvesf/dwarves-kit · 64 tokens

test-deduplicator

Duplicate test removal agent. Use in Step 4 (Refactoring) of the development workflow. Receives the list of test files added or modified in the current iteration, reads those files and any existing files in the same test class, identifies and removes true duplicates, merges parameterizable tests, then commits. Returns…

nowsprinting/unity-coding-skills · 83 tokens

test-designer

Test design specialist agent. Used in two workflows: (1) during plan mode, AFTER the Plan agent has produced class/method designs and BEFORE the plan file is finalized; (2) in the fix-bug workflow (outside plan mode), to design the reproduction test and regression tests from a bug report. Takes requirements (feature…

nowsprinting/unity-coding-skills · 161 tokens