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 skills/managedcode/dotpilot/dotnet-microsoft-agent-frameworknpx skills add managedcode/dotPilot --skill dotnet-microsoft-agent-frameworkgit clone --depth 1 https://github.com/managedcode/dotPilotWhat 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 | $0.00040 | $0.01934 |
| Opus 5 | $0.00020 | $0.00967 |
| Sonnet 5 | $0.00008 | $0.00387 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
dotnet-microsoft-agent-framework 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Agent Framework
Trigger On
- building or reviewing
.NETcode that usesMicrosoft.Agents.*,Microsoft.Extensions.AI,AIAgent,AgentThread, or Agent Framework hosting packages - choosing between
ChatClientAgent, Responses agents, hosted agents, custom agents, workflows, or durable agents - adding tools, MCP, A2A, OpenAI-compatible hosting, AG-UI, DevUI, background responses, or OpenTelemetry
- migrating from Semantic Kernel agent APIs or aligning AutoGen-style multi-agent patterns to Agent Framework
Workflow
- Decide whether the problem should stay deterministic. If plain code or a typed workflow without LLM autonomy is enough, do that instead of adding an agent.
- Choose the execution shape first: single
AIAgent, explicitWorkflow, Azure Functions durable agent, ASP.NET Core hosted agent, AG-UI remote UI, or DevUI local debugging. - Choose the agent type and provider intentionally. Prefer the simplest agent that satisfies the threading, tooling, and hosting requirements.
- Keep agents stateless and keep conversation or long-lived state in
AgentThread. Treat serialized threads as opaque provider-specific state. - Add only the tools and middleware that the scenario needs. Narrow the tool surface, require approval for side effects, and treat MCP, A2A, and third-party services as trust boundaries.
- For workflows, model executors, edges, request-response ports, checkpoints, shared state, and human-in-the-loop explicitly rather than hiding control flow in prompts.
- Prefer Responses-based protocols for new remote/OpenAI-compatible integrations unless you specifically need Chat Completions compatibility.
- Use durable agents only when you truly need Azure Functions serverless hosting, durable thread storage, or deterministic long-running orchestrations.
- Verify preview status, package maturity, docs recency, and provider-specific limitations before locking a production architecture.
Architecture
flowchart LR
A["Task"] --> B{"Deterministic code is enough?"}
B -->|Yes| C["Write normal .NET code or a plain workflow"]
B -->|No| D{"One dynamic decision-maker is enough?"}
D -->|Yes| E["Use an `AIAgent` / `ChatClientAgent`"]
D -->|No| F["Use a typed `Workflow`"]
F --> G{"Needs durable Azure hosting or week-long execution?"}
G -->|Yes| H["Use durable agents on Azure Functions"]
G -->|No| I["Use in-process workflows"]
E --> J{"Need a remote protocol or UI?"}
F --> J
J -->|OpenAI-compatible HTTP| K["ASP.NET Core Hosting.OpenAI"]
J -->|Agent-to-agent protocol| L["A2A hosting"]
J -->|Web UI protocol| M["AG-UI"]
J -->|Local debug shell| N["DevUI (dev only)"]
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/agent-framework-router/AGENT.md 4.9 KB
- references/devui.md 1.9 KB
- references/examples.md 5.5 KB
- references/hosting.md 5.4 KB
- references/mcp.md 3.7 KB
- references/middleware.md 5.2 KB
- references/migration.md 4.1 KB
- references/official-docs-index.md 16 KB
- references/official-docs/integrations/ag-ui/backend-tool-rendering.md 23 KB
- references/official-docs/integrations/ag-ui/frontend-tools.md 18 KB
- references/official-docs/integrations/ag-ui/getting-started.md 24 KB
- references/official-docs/integrations/ag-ui/human-in-the-loop.md 39 KB
- references/official-docs/integrations/ag-ui/index.md 12 KB
- references/official-docs/integrations/ag-ui/security-considerations.md 10.0 KB
- references/official-docs/integrations/ag-ui/state-management.md 34 KB
- references/official-docs/integrations/ag-ui/testing-with-dojo.md 7.7 KB
- references/official-docs/migration-guide/from-autogen/index.md 68 KB
- references/official-docs/migration-guide/from-semantic-kernel/index.md 29 KB
- references/official-docs/migration-guide/from-semantic-kernel/samples.md 1.0 KB
- references/official-docs/overview/agent-framework-overview.md 9.2 KB
- references/official-docs/support/faq.md 1.1 KB
- references/official-docs/support/index.md 1.1 KB
- references/official-docs/support/troubleshooting.md 887 B
- references/official-docs/support/upgrade/index.md 221 B
- references/official-docs/tutorials/agents/agent-as-function-tool.md 5.0 KB
- references/official-docs/tutorials/agents/agent-as-mcp-tool.md 4.8 KB
- references/official-docs/tutorials/agents/create-and-run-durable-agent.md 22 KB
- references/official-docs/tutorials/agents/enable-observability.md 9.2 KB
- references/official-docs/tutorials/agents/function-tools-approvals.md 10 KB
- references/official-docs/tutorials/agents/function-tools.md 6.8 KB
- references/official-docs/tutorials/agents/images.md 3.8 KB
- references/official-docs/tutorials/agents/memory.md 17 KB
- references/official-docs/tutorials/agents/middleware.md 10 KB
- references/official-docs/tutorials/agents/multi-turn-conversation.md 6.0 KB
- references/official-docs/tutorials/agents/orchestrate-durable-agents.md 18 KB
- references/official-docs/tutorials/agents/persisted-conversation.md 6.0 KB
- references/official-docs/tutorials/agents/run-agent.md 8.9 KB
- references/official-docs/tutorials/agents/structured-output.md 7.7 KB
- references/official-docs/tutorials/agents/third-party-chat-history-storage.md 20 KB
- references/official-docs/tutorials/overview.md 1.2 KB
- references/official-docs/tutorials/plugins/use-purview-with-agent-framework-sdk.md 6.7 KB
- references/official-docs/tutorials/quick-start.md 8.2 KB
- references/official-docs/tutorials/workflows/agents-in-workflows.md 13 KB
- references/official-docs/tutorials/workflows/checkpointing-and-resuming.md 21 KB
- references/official-docs/tutorials/workflows/requests-and-responses.md 20 KB
- references/official-docs/tutorials/workflows/simple-concurrent-workflow.md 15 KB
- references/official-docs/tutorials/workflows/simple-sequential-workflow.md 13 KB
- references/official-docs/tutorials/workflows/workflow-builder-with-factories.md 5.0 KB
- references/official-docs/tutorials/workflows/workflow-with-branching-logic.md 79 KB
- references/official-docs/user-guide/agents/agent-background-responses.md 7.2 KB
- references/official-docs/user-guide/agents/agent-memory.md 18 KB
- references/official-docs/user-guide/agents/agent-middleware.md 19 KB
- references/official-docs/user-guide/agents/agent-rag.md 13 KB
- references/official-docs/user-guide/agents/agent-tools.md 9.8 KB
- references/official-docs/user-guide/agents/agent-types/a2a-agent.md 4.3 KB
- references/official-docs/user-guide/agents/agent-types/anthropic-agent.md 13 KB
- references/official-docs/user-guide/agents/agent-types/azure-ai-foundry-agent.md 9.9 KB
- references/official-docs/user-guide/agents/agent-types/azure-ai-foundry-models-chat-completion-agent.md 3.2 KB
- references/official-docs/user-guide/agents/agent-types/azure-ai-foundry-models-responses-agent.md 2.9 KB
- references/official-docs/user-guide/agents/agent-types/azure-openai-chat-completion-agent.md 8.2 KB
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 · 118 lines · 40 tokens per session scan A b3c644b46f30
dotnet-microsoft-agent-framework is a skill published in the GitHub repository managedcode/dotPilot (23 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 1,934 once invoked, about $0.0002 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 skills, from other repositories
with-frontmatter
Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.
codebase-context-extractor
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
skill-creator
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
Research Synthesis Workflow
A step-by-step guide to synthesizing research from multiple sources into a coherent summary.
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.