server

server is a skill for Claude Code from skillmds/skillmd. It costs 8 tokens per session (4,625 once invoked), scanned A, original, MIT.

An agent server implementation imported from LangChain. It connects an AI agent to clients through the Agent Client Protocol, a standard way for agent software to exchange requests, messages, and tool updates.

In plain words
What is it for?
Use it as a starting point for running a DeepAgents-based coding agent and connecting it to an ACP-compatible client.
Why use it?
It provides the code needed for an agent to accept prompts, manage sessions, report progress, and handle permissions through that protocol.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agents-mcp plugin — 34 skills shipped together

Good fit Use it as a starting point for running a DeepAgents-based coding agent and connecting it to an ACP-compatible client.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skillmds/skillmd/server
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.

Any agent
npx skills add skillmds/skillmd --skill server
Clone the repo
git clone --depth 1 https://github.com/skillmds/skillmd

Made for: Claude Code.

Or install agents-mcp, the plugin that ships this one along with the rest of its 34 skills.

Wrote 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.

agentmods badge for server

README.md
[![agentmods](https://agentmods.dev/badge/skills/skillmds/skillmd/server/github.svg)](https://agentmods.dev/skills/skillmds/skillmd/server)
Your own site
<a href="https://agentmods.dev/skills/skillmds/skillmd/server"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/server/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.

agentmods 80×15 button for server

Your own site · 80×15
<a href="https://agentmods.dev/skills/skillmds/skillmd/server"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,625 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00008 $0.04625
Opus 5.5 $0.00003 $0.01850
Sonnet 5 $0.00002 $0.00925
Haiku 4.5 $0.00001 $0.00462

Measured 4d ago against content hash 1d05c28d0726, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-23, from the pricing page.

Security

Grade A, and why

server 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 4d 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.

plugins/agents-mcp/skills/server/SKILL.md · 664 lines

How it starts

The opening of the file, as written. The whole thing — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.

"""DeepAgents ACP server implementation."""

from future import annotations

import asyncio import uuid from typing import Any, Literal

from acp import ( Agent, AgentSideConnection, PROTOCOL_VERSION, stdio_streams, ) from acp.schema import ( AgentMessageChunk, InitializeRequest, InitializeResponse, NewSessionRequest, NewSessionResponse, PromptRequest, PromptResponse, SessionNotification, TextContentBlock, Implementation, AgentThoughtChunk, ToolCallProgress, ContentToolCallContent, LoadSessionResponse, SetSessionModeResponse, SetSessionModelResponse, CancelNotification, LoadSessionRequest, SetSessionModeRequest, SetSessionModelRequest, AgentPlanUpdate, PlanEntry, PermissionOption, RequestPermissionRequest, AllowedOutcome, DeniedOutcome, ToolCall as ACPToolCall, ) from deepagents import create_deep_agent from langchain_anthropic import ChatAnthropic from langchain_core.messages import AIMessage, AIMessageChunk, ToolMessage from langchain_core.messages.content import ToolCall from langchain_core.tools import tool from langgraph.checkpoint.memory import InMemorySaver from langgraph.graph.state import CompiledStateGraph from langgraph.types import Command, Interrupt

class DeepagentsACP(Agent): """ACP Agent implementation wrapping deepagents."""

def __init__(
    self,
    connection: AgentSideConnection,
    agent_graph: CompiledStateGraph,
) -> None:
    """Initialize the DeepAgents agent.

    Args:
        connection: The ACP connection for communicating with the client
        agent_graph: A compiled LangGraph StateGraph (output of create_deep_agent)
    """
    self._connection = connection
    self._agent_graph = agent_graph
    self._sessions: dict[str, dict[str, Any]] = {}
    # Track tool calls by ID for matching with ToolMessages
    # Maps tool_call_id -> ToolCall TypedDict
    self._tool_calls: dict[str, ToolCall] = {}

async def initialize(
    self,
    params: InitializeRequest,
) -> InitializeResponse:
    """Initialize the agent and return capabilities."""
    return InitializeResponse(
        protocolVersion=PROTOCOL_VERSION,
        agentInfo=Implementation(
            name="DeepAgents ACP Server",
            version="0.1.0",
            title="DeepAgents ACP Server",
        ),
    )

async def newSession(
    self,
    params: NewSessionRequest,
) -> NewSessionResponse:
    """Create a new session with a deepagents instance."""
    session_id = str(uuid.uuid4())
    # Store session state with the shared agent graph
    self._sessions[session_id] = {
        "agent": self._agent_graph,
        "thread_id": str(uuid.uuid4()),
    }

    return NewSessionResponse(sessionId=session_id)

async def _handle_ai_message_chunk(
    self,
    params: PromptRequest,
    message: AIMessageChunk,
) -> None:
    """Handle an AIMessageChunk and send appropriate notifications.

    Args:
        params: The prompt request parameters
        message: An AIMessageChunk from the streaming response

    Note:
        According to LangChain's content block types, message.content_blocks
        returns a list of ContentBlock unions. Each block is a TypedDict with
        a "type" field that discriminates the block type:
        - TextContentBlock: type="text", has "text" field
        - ReasoningContentBlock: type="reasoning", has "reasoning" field
        - ToolCallChunk: type="tool_call_chunk"
        - And many others (image, audio, video, etc.)
    """
    for block in message.content_blocks:
        # All content blocks have a "type" field for discrimination
        block_type = block.get("type")

        if block_type == "text":
            # TextContentBlock has a required "text" field
            text = block.get("text", "")
            if not text:  # Only yield non-empty text
                continue
            await self._connection.sessionUpdate(
                SessionNotification(
                    update=AgentMessageChunk(
                        content=TextContentBlock(text=text, type="text"),
                        sessionUpdate="agent_message_chunk",
                    ),
                    sessionId=params.sessionId,
                )
            )
        elif block_type == "reasoning":
            # ReasoningContentBlock has a "reasoning" field (NotRequired)
            reasoning = block.get("reasoning", "")
            if not reasoning:
                continue

Read the full file on GitHub · 664 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. 4d ago First seen · 664 lines · 8 tokens per session scan A 1d05c28d0726

Subscribe to this mod's changes

server is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 4,625 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 2026-09-19.