Microsoft TypeAgent is sample code exploring how a personal software agent can use natural-language interfaces to work with application agents. It is intended for investigating how language models can combine with structured software components for actions, memory, planning, and collaboration. The catalogue entries provide agents, skills, instructions, and an MCP integration for this project.
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 skills add microsoft/TypeAgent --skill typeagent-setupgit clone --depth 1 https://github.com/microsoft/TypeAgentWrote 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/skills/microsoft/typeagent/typeagent-setup)<a href="https://agentmods.dev/skills/microsoft/typeagent/typeagent-setup"><img src="https://agentmods.dev/badge/skills/microsoft/typeagent/typeagent-setup/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/skills/microsoft/typeagent/typeagent-setup"><img src="https://agentmods.dev/badge/skills/microsoft/typeagent/typeagent-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00012 | $0.00659 |
| Opus 5.5 | $0.00005 | $0.00264 |
| Sonnet 5.5 | $0.00002 | $0.00132 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade A, and why
typeagent-setup 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeAgent Setup
Configure the TypeAgent integration for Copilot CLI.
Current Configuration
Read the config file at ${PLUGIN_DATA}/config.json (create if it doesn't exist).
Options
Ask the user which integration mode they'd like:
- direct (default) - Hook handles requests directly, bypassing the LLM. Fastest response time (~2-3s) but no streaming.
- mcp - Choose a routing policy: delegate (default) sends the original request to TypeAgent; mixed lets Copilot choose whole-request delegation or own the task and use structured TypeAgent tools for intermediate steps.
- dev - Hook tries registered PowerShell development actions first and lets Copilot handle misses.
- bypass - Disable TypeAgent routing and reject TypeAgent MCP calls.
The typeagent-workspace read/glob/grep/fetch tools are available in direct,
mcp, and dev modes. They do not require a separate macro mode.
Use @typeagent mode mcp mixed or /typeagent-mode mcp mixed to opt in;
use mcp delegate to restore the existing policy. Plain mcp preserves the
saved policy. @typeagent mode, @typeagent status, and /typeagent-status
report the effective policy. Mixed mode is not search-first: user requests
such as "show my lists" still delegate intact via processCommand. Copilot
uses searchActions/executeAction for TypeAgent steps it selects while
coordinating broader work only under MCP mixed routing, not the default
delegate policy. Structured tools remain available in both policies; switching
policy changes routing guidance, not the tool catalog or permissions.
Recording prefixes always preserve natural-language
delegation. MCP tool-card titles distinguish natural-language delegation from
structured discovery/execution in both policies, without relying on model
narration or claiming action success.
Also ask for:
- TypeAgent host (default: localhost) - The host where the TypeAgent agent-server is running
- TypeAgent port (default: 8999) - The port for the agent-server
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 Changed · +20 lines ddbb457a185c
- 1mo ago First seen · 50 lines · 12 tokens per session scan A 069a5f1a6e32
typeagent-setup is a skill published in the GitHub repository microsoft/TypeAgent (748 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 659 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.