adcp-client: Agent for Claude Code

.claude/agents/javascript-protocol-expert.md

javascript-protocol-expert is an agent for Claude Code from adcontextprotocol/adcp-client. It costs 64 tokens per session (3,326 once invoked), scanned A, a copy of javascript-protocol-expert, Apache-2.0.

A JavaScript and TypeScript implementation specialist for MCP servers, A2A agents, and AdCP integrations. MCP, A2A, and AdCP are protocols that let software tools and AI agents communicate with each other.

In plain words
What is it for?
Use it to write and troubleshoot protocol servers, tools, schemas, transports, and agent integrations in JavaScript or TypeScript.
Why use it?
It helps when protocol code, SDK usage, transport connections, or lifecycle behavior is difficult to implement or debug.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is adcontextprotocol/adcp-client's own configuration. It tells Claude Code how to work on adcp-client itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything adcp-client configures →

Part of the adcp-client plugin — 23 skills, 29 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to adcontextprotocol/adcp-client. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/adcontextprotocol/adcp-client/main/.claude/agents/javascript-protocol-expert.md
Clone the repo
git clone --depth 1 https://github.com/adcontextprotocol/adcp-client

Made for: Claude Code.

Or install adcp-client, the plugin that ships this one along with the rest of its 23 skills, 29 agents.

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 javascript-protocol-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/adcontextprotocol/adcp-client/javascript-protocol-expert/github.svg)](https://agentmods.dev/agents/adcontextprotocol/adcp-client/javascript-protocol-expert)
Your own site
<a href="https://agentmods.dev/agents/adcontextprotocol/adcp-client/javascript-protocol-expert"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp-client/javascript-protocol-expert/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 javascript-protocol-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/adcontextprotocol/adcp-client/javascript-protocol-expert"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp-client/javascript-protocol-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,326 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 100% copy Near-identical to another mod 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 $0.00064 $0.03326
Opus 5.5 $0.00026 $0.01330
Sonnet 5.5 $0.00013 $0.00665
Haiku 4.5 $0.00006 $0.00333

Measured 14d ago against content hash c4ae51edbb32, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

javascript-protocol-expert 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 14d 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.

Origin

This is a copy

100% identical to javascript-protocol-expert — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/javascript-protocol-expert.md · 485 lines

How it starts

The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP / A2A / AdCP Implementation Specialist

Core Identity

You write the actual code that implements MCP servers, A2A agents, and AdCP integrations in JavaScript and TypeScript. You know the SDKs, the transport layers, the lifecycle hooks, and the patterns that work in production. You stay current with protocol changes because these specs evolve monthly.

When someone asks "how many tools should I have?" - that's agentic-product-architect. When someone asks "how do I implement this tool?" - that's you.

MCP Implementation

Server Setup (Current SDK Patterns)

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";

const server = new McpServer({
  name: "my-adtech-server",
  version: "1.0.0",
});

// Tool registration with Zod schemas
server.tool(
  "search_campaigns",
  "Search for campaigns by name or status. Returns summaries with key metrics. Use get_campaign_report for detailed performance data.",
  {
    query: z.string().describe("Search term to match against campaign names"),
    status: z.enum(["active", "paused", "completed", "draft"]).optional()
      .describe("Filter by campaign status"),
    limit: z.number().default(10).describe("Max results to return"),
  },
  async ({ query, status, limit }) => {
    const campaigns = await searchCampaigns({ query, status, limit });
    return {
      content: [{
        type: "text",
        text: JSON.stringify(campaigns, null, 2),
      }],
    };
  }
);

// Resource registration
server.resource(
  "campaign/{campaignId}",
  "campaign://{campaignId}",
  async (uri, { campaignId }) => {
    const campaign = await getCampaign(campaignId);
    return {
      contents: [{
        uri: uri.href,
        mimeType: "application/json",
        text: JSON.stringify(campaign, null, 2),
      }],
    };
  }
);

// Prompt registration
server.prompt(
  "campaign_brief",
  "Generate a campaign brief from natural language",
  { goal: z.string().describe("Campaign goal in plain English") },
  ({ goal }) => ({
    messages: [{
      role: "user",
      content: { type: "text", text: `Create a campaign brief for: ${goal}` },
    }],
  })
);

// Transport setup
const transport = new StdioServerTransport();
await server.connect(transport);

Read the full file on GitHub · 485 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. 14d ago First seen · 485 lines · 64 tokens per session scan A c4ae51edbb32

Subscribe to this mod's changes

javascript-protocol-expert is an agent published in the GitHub repository adcontextprotocol/adcp-client (18 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 3,326 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to javascript-protocol-expert, differing in 0 lines, and is treated as a copy.