a2a-multi-turn

a2a-multi-turn is a skill for Claude Code from OrcaQubits/agentic-commerce-skills-plugins. It costs 45 tokens per session (1,070 once invoked), scanned A, original, MIT.

A guide for building multi-step conversations between agents using the Agent2Agent (A2A) protocol, a standard way for agents to communicate. It covers cases where an agent pauses and asks a person or another agent for more information.

In plain words
What is it for?
Use it when an agent needs iterative refinement, must request missing input, or continues the same task after a reply.
Why use it?
It helps preserve the task's context while handling follow-up questions and human review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the a2a-multi-agent plugin — 16 skills, 1 agent, 1 hook shipped together

Good fit Use it when an agent needs iterative refinement, must request missing input…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orcaqubits/agentic-commerce-skills-plugins/a2a-multi-turn
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 OrcaQubits/agentic-commerce-skills-plugins --skill a2a-multi-turn
Clone the repo
git clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-plugins

Made for: Claude Code.

Or install a2a-multi-agent, the plugin that ships this one along with the rest of its 16 skills, 1 agent, 1 hook.

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 a2a-multi-turn

README.md
[![agentmods](https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-multi-turn.svg)](https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-multi-turn)
Your own site
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-multi-turn"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-multi-turn.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,070 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 $0.00045 $0.01070
Opus 5 $0.00023 $0.00535
Sonnet 5 $0.00009 $0.00214
Haiku 4.5 $0.00005 $0.00107

Measured 7d ago against content hash d221688ec0bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

a2a-multi-turn 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 7d 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.

a2a-multi-agent/skills/a2a-multi-turn/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A2A Multi-Turn Conversations

Before writing code

Fetch live docs:

  1. Fetch https://a2a-protocol.org/latest/specification/ for multi-turn and input-required handling
  2. Web-search site:github.com a2aproject A2A multi-turn input-required for multi-turn protocol details
  3. Web-search site:github.com a2aproject a2a-samples multi-turn for conversation examples
  4. Fetch SDK docs for multi-turn task handling patterns

Conceptual Architecture

What Multi-Turn Means in A2A

Multi-turn conversations allow agents to have iterative exchanges within a single task. The server agent can request more input from the client, creating a back-and-forth dialogue before reaching a final result.

The input-required State

The key mechanism for multi-turn is the input-required task state:

Client sends message → Task created (submitted)
Server processes → working
Server needs more info → input-required (with a message explaining what's needed)
Client sends follow-up → working (task continues with same taskId)
Server completes → completed

How It Works

  1. Initial request: Client sends message/send or message/stream without taskId
  2. Server processes: May transition to input-required if it needs clarification
  3. Server response: Returns the task with input-required state and a message explaining what's needed
  4. Client responds: Sends another message/send with the same taskId and the requested information
  5. Server continues: Resumes processing with the additional context
  6. Repeat or complete: May request more input or reach a terminal state

Context Preservation

Within a multi-turn task:

  • All messages are associated with the same taskId
  • The server maintains the full conversation history
  • Each new message from the client adds to the context
  • The server can reference previous messages when processing

Patterns

Clarification Loop

Agent asks for clarification when the request is ambiguous:

User: "Book a flight"
Agent: (input-required) "Where are you flying from and to? What dates?"
User: "NYC to London, March 15-22"
Agent: (input-required) "I found 3 options. Which do you prefer? [options]"
User: "Option 2"
Agent: (completed) "Booked! Confirmation #ABC123"

Read the full file on GitHub · 123 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. 7d ago First seen · 123 lines · 45 tokens per session scan A d221688ec0bd

Subscribe to this mod's changes

a2a-multi-turn is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 1,070 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 2026-08-30.

Related

Other skills, from other repositories

design-taste-frontend

Use for visual design direction on greenfield, user-facing surfaces — marketing and landing pages, generated apps, portfolio-style or standalone pages. NOT for routine Archestra platform UI work (dashboards, data tables, settings, forms, existing components) — use archestra-dev-frontend for that. Upstream intent…

archestra-ai/archestra · 0 tokens

lucid-agents

Build, modify, review, debug, or deploy TypeScript services made with the Lucid Agents SDK. Use whenever a project imports @lucid-agents packages or the user asks about Lucid runtimes, entrypoints, adapters, payments, MPP, identity, wallets, A2A tasks, service UI, scaffolding, or deployment.

daydreamsai/lucid-agents · 75 tokens

archestra-dev-rust-napi

Use when editing Rust in this repo — the NAPI crates under platform/archestra-rs (app-runtime, image, and sandbox core/-rs crate pairs plus napi-loader, with their generated TypeScript bindings) or the standalone ai-labs Rust workspace (core/runner/cli/analyzer/dashboard) — including Rust build/test checks.

archestra-ai/archestra · 76 tokens

archestra-dev-testing

Use when deciding whether a change needs a test and at which level — unit, backend route-level integration, MSW-backed frontend integration, or e2e — or when reviewing tests for the "fluff test" anti-pattern. Start here before archestra-dev-backend-tests or archestra-dev-e2e.

archestra-ai/archestra · 68 tokens

migrate-to-archestra

Migrate an existing agentic PoC/pilot (Claude Code project files, MCP configs, hooks, local tools, openclaw config, or similar hand-rolled setup artifacts) into an Archestra instance. Use when the user wants to move, port, or convert an existing agentic setup into an Archestra pilot.

archestra-ai/archestra · 73 tokens

archestra-dev-backend-tests

Use when writing or modifying Archestra backend unit tests (platform/backend/src//.test.ts) — mocking modules, stubbing globals, database fixtures, vitest projects/isolation, or test performance.

archestra-ai/archestra · 46 tokens