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 agents/microsoft/typeagent/agentserverconversationsgit clone --depth 1 https://github.com/microsoft/TypeAgentWhat 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 | $0.00000 | $0.05376 |
| Opus 5 | $0.00000 | $0.02688 |
| Sonnet 5 | $0.00000 | $0.01075 |
| Haiku 4.5 | $0.00000 | $0.00538 |
Grade A, and why
agentServerConversations 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentServer Conversations Architecture
Overview
The agentServer manages explicit, named conversations with full CRUD semantics. Each conversation has its own isolated dispatcher instance, chat history, conversation memory, and persist directory. Multiple clients can connect to the same conversation simultaneously and share state; clients connected to different conversations are fully isolated.
Conversations are identified by a UUIDv4 and carry a human-readable name. The server exposes conversation management via RPC, CLI commands, and natural-language actions routed through the system.conversation sub-agent.
Conversation Identity
Each conversation is described by:
| Field | Type | Description |
|---|---|---|
conversationId |
string (UUIDv4) |
Stable, globally unique identifier |
name |
string |
Human-readable label (1–256 chars), set at createConversation() time. Not enforced unique. |
createdAt |
string (ISO 8601) |
When the conversation was first created |
clientCount |
number |
Number of clients currently connected to this conversation (runtime-derived; 0 if the conversation is not loaded in memory). Never persisted. |
On-Disk Layout
A conversations.json file at instanceDir/conversations/conversations.json is the authoritative registry:
{
"sessions": [
{
"conversationId": "a1b2c3d4-...",
"name": "workout playlist setup",
"createdAt": "2026-04-01T10:00:00Z"
}
]
}
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 · 367 lines · 0 tokens per session scan A 0419d1d08566
agentServerConversations is an agent published in the GitHub repository microsoft/TypeAgent (738 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,376 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.