agent-interop

A guide to connecting an AI agent with systems outside its own process. It covers MCP tool servers, A2A communication between agents, registries, and gateways.

In plain words
What is it for?
Building or consuming MCP servers, calling another agent over A2A, publishing to an MCP Registry, and placing a gateway in front of agent traffic.
Why use it?
It explains the protocols and changing wire rules needed for agents to exchange data or call external tools. This reduces the risk of building against outdated protocol behavior.

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/ssheleg/agent-stack/agent-interop
Any agent
npx skills add ssheleg/agent-stack --skill agent-interop
Clone the repo
git clone --depth 1 https://github.com/ssheleg/agent-stack

Made for: Claude Code, Codex.

Per session 242 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,343 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 $0.00242 $0.03343
Opus 5 $0.00121 $0.01672
Sonnet 5 $0.00048 $0.00669
Haiku 4.5 $0.00024 $0.00334

Measured yesterday against content hash 8b73e9bc4a5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-interop 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.

plugins/agent-stack/skills/agent-interop/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent interop — the protocols an agent speaks outside its own process

agent-orchestrator builds the loop. agent-evals proves it behaves. This skill covers everything the loop reaches that is not in its process: a tool server, a peer agent, a registry, and the gateway between them.


Rule zero — a protocol claim without a date is a guess

Every one of these specifications moved in the twelve months before 2026-08-13 — the date every reference below was read — and each moved in a way that silently breaks code written against the previous revision. Concretely, and each one measured on that date against the live specification rather than recalled:

  • MCP replaced the initialize handshake with server/discover and made the protocol stateless; a client that opens with initialize is speaking a revision that is on its way out.
  • MCP deprecated sampling, roots and logging — three things an older model will reach for first, because for a year they were the interesting part of the client side.
  • A2A renamed its wire surface between v0.x and v1.0, and SDKs and blog posts still documented v0.3 as of 2026-08-13.
  • agentgateway deprecated binds in favour of gateways — while its own overview page still introduced binds as a core concept as of 2026-08-13.

So: every reference in this skill opens with a **Spec pinned:** line, and test/validate.py fails the build without one. That is a mechanical check, not an aspiration — the class of error it prevents is the one where prose reads as current because nothing on the page says otherwise.

Before you write wire-level code, fetch the spec. These references tell you what to look for and what changed; they are not a substitute for the document. Read the pinned revision, then check whether a newer one exists. Every entry in the link map below is fetchable.


Which protocol answers which question

The question you actually have The answer Where
I want to give a model a capability against a live system MCP server references/mcp.md
My server is written and the client cannot connect to it mounting and transports references/mcp-ship.md
I want my application to consume other people's tool servers MCP client references/mcp.md, then references/mcp-scale.md
I have more servers than fit in a context window client scaling patterns references/mcp-scale.md
I want another team's autonomous agent to accomplish an outcome for me A2A references/a2a.md
I want my agent discoverable and callable by other agents A2A agent card references/a2a.md
I want people to find and install my MCP server MCP Registry references/registry.md
I have many servers, many clients, and a security team a gateway references/gateway.md

Read the full file on GitHub · 177 lines

Files

What ships with it

6 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. yesterday First seen · 177 lines · 242 tokens per session scan A 8b73e9bc4a5b

Subscribe to this mod's changes

agent-interop is a skill published in the GitHub repository ssheleg/agent-stack (2 stars, last pushed 2d ago), licensed MIT. It adds 242 tokens to every session and 3,343 once invoked, about $0.0012 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

parallel-feature-managers

Run several independent Cotal features concurrently by creating one Git worktree and one spawn-capable mesh manager per feature; each manager staffs a review panel in a dedicated channel, adds one independent cold reviewer briefed under the cold-review skill, owns plan-to-commit delivery, and escalates unresolved…

Cotal-AI/Cotal · 107 tokens

pixel-face

Create or improve a 32×32 pixel-art persona face for the Frontier Faces demo (examples/04-frontier-faces/personas.mjs) — the animated agent avatars rendered by face-term.mjs / the browser / the gallery. Use when the user asks to add a new persona/face/avatar, improve an existing one (hair, eyes, likeness, expression)…

Cotal-AI/Cotal · 138 tokens

cotal-setup

Set up Cotal on this machine: install it, start a local agent mesh (NATS + JetStream), verify it, and put an agent on it. Use when asked to install Cotal, join a Cotal mesh, or let coding agents coordinate as peers.

Cotal-AI/Cotal · 60 tokens

cold-review

Write the brief for a single independent cold reviewer and grade what it returns, keeping it isolated from the panel that already graded the change. Read by whoever AUTHORS the brief; the graded seat never loads this file. Covers what the seat is given, what its verdict binds, who may override it, and how the rules…

Cotal-AI/Cotal · 119 tokens

team-topology

Define a multi-agent team for ANY task on ANY system as an explicit deployment topology - pick the shape from the task's dominant risk, specify the runtime/communication/trust layers, place model capability by lane, present it as a diagram + table + trust-boundary note + open choices, and deploy ONLY after the user…

Cotal-AI/Cotal · 168 tokens

create-release

Create releases with proper versioning, release notes, and Git tags.

GetBindu/Bindu · 16 tokens