choose-agent-integration-protocol

A decision guide for choosing how an editor, agent, tool, terminal, or application should communicate. It explains when to use A2A, ACP, MCP, a native host integration, a terminal thread, or Hermes interfaces.

In plain words
What is it for?
Use it when designing or reviewing an integration between coding agents, editors, tool servers, terminals, or custom applications.
Why use it?
It removes ambiguity about which process owns the conversation, model, tools, and credentials. That prevents choosing a protocol based only on vague goals such as connecting two agents.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/gaelic-ghost/socket/choose-agent-integration-protocol
Any agent
npx skills add gaelic-ghost/socket --skill choose-agent-integration-protocol
Clone the repo
git clone --depth 1 https://github.com/gaelic-ghost/socket

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 800 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.00800
Opus 5 $0.00024 $0.00400
Sonnet 5 $0.00010 $0.00160
Haiku 4.5 $0.00005 $0.00080

Measured 2d ago against content hash cf108a4b081f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

choose-agent-integration-protocol 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 2d 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/agent-portability-skills/skills/choose-agent-integration-protocol/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Choose Agent Integration Protocol

Name the processes and the direction of control before selecting a protocol. Do not use “connect the agents” or “hook into Xcode” as an architecture.

Decision Workflow

  1. Identify the process that owns the conversation UI.
  2. Identify the process that owns the agent loop, model, credentials, tools, and persistent sessions.
  3. Identify whether the other endpoint is an editor, a tool provider, another agent, a terminal, or a custom application.
  4. Select one primary boundary:
    • Use ACP when an editor or compatible client launches and renders an external coding agent.
    • Use A2A when independently operated agents discover each other and exchange messages or stateful tasks across a process, machine, or framework boundary.
    • Use MCP when an agent calls tools or resources supplied by another process. An externally running agent uses Xcode through xcrun mcpbridge.
    • Use a native host agent when the host should own the model, instructions, skills, permissions, and tools.
    • Use a terminal thread when the original CLI or TUI experience is the requirement and editor-native diffs or approvals are unnecessary.
    • Use the Hermes TUI gateway or API server when a custom program drives Hermes directly and no ACP client owns the interaction.
    • Use a host plug-in only for capabilities that the host's documented skills, MCP, ACP, or configuration surfaces cannot provide.
  5. Record authentication, working-directory, permission, session, and lifecycle ownership separately. A transport choice does not make those boundaries identical.

Read references/protocol-decision-map.md when the request spans more than one host or appears to require multiple transports.

Required Distinctions

  • ACP makes an agent editor-native; it is not a general tool protocol.
  • A2A connects independently operated peer agents; it does not provide an editor UI or replace in-process subagents.
  • MCP gives an agent callable tools; it does not provide an editor conversation or review UI.
  • Hermes running hermes acp is the ACP agent/server. Zed or Xcode is the ACP client that launches or connects to it.
  • A Hermes provider that internally launches another ACP program is a provider-specific integration, not proof that Hermes is a universal ACP client or agent orchestrator.
  • Xcode-hosted ACP and an external agent using Xcode MCP are different paths.

Read the full file on GitHub · 78 lines

Files

What ships with it

2 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.

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. 2d ago First seen · 78 lines · 49 tokens per session scan A cf108a4b081f

Subscribe to this mod's changes

choose-agent-integration-protocol is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 7d ago), licensed Apache-2.0. It adds 49 tokens to every session and 800 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 2026-08-31.

Related

Other skills, from other repositories

use-gemini-web

Use the user's logged-in Gemini Web session as an untrusted auxiliary model when its public YouTube audio/visual understanding, public-URL context, or an independent second analysis materially helps Codex answer or verify a request. Use for one or multiple public videos, follow-up questions, cross-checking, or a fresh…

andrewLi1994/gemini-web-bridge · 110 tokens

create-skill

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

warpdotdev/warp · 64 tokens

factory-files

Create and edit file-based Warp software factory definitions, in a repository tree rooted at a factory.yaml. Use when authoring or changing that factory.yaml, Agent, Automation, Scorer, Runner, or Webhook files under that root, or its factory and agent skill trees, and when fixing Factory file diagnostics. Do not use…

warpdotdev/warp · 101 tokens

skill-management

Create, edit, and delete custom managed skills in the user's workspace. Use whenever the user wants to author a new skill from a description, scaffold a SKILL.md, or remove a skill they no longer need.

vellum-ai/vellum-assistant · 46 tokens

archon

Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across context windows. Use for work that spans multiple sessions and needs persistent state, quality judgment, and strategic decomposition.

SethGammon/Citadel · 54 tokens

create-app

End-to-end app creation from a single description. Five tiers: blank project, guided, templated, fully generated, or feature addition to existing codebase. Routes through PRD, architecture, and Archon campaign with verification at every step.

SethGammon/Citadel · 52 tokens