agent-to-agent

agent-to-agent is a skill for Claude Code, Codex from OneWave-AI/claude-skills. It costs 47 tokens per session (882 once invoked), scanned A, original, MIT.

A communication protocol for two or more software agents to exchange messages, share information, delegate tasks, and hand work to one another. It coordinates their work through shared context and defined message rules.

In plain words
What is it for?
Use it to coordinate research and writing, coding and review, sales and technical work, supervisor workflows, or other processes where several agents must collaborate.
Why use it?
It gives collaborating agents a structured way to track requests, responses, responsibilities, and failures. This reduces lost context and unclear handoffs during multi-agent work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter; mentions Claude Code.

Good fit Use it to coordinate research and writing, coding and review, sales and technical work, supervisor workflows, or other processes where several agents must collaborate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/onewave-ai/claude-skills/agent-to-agent
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 OneWave-AI/claude-skills --skill agent-to-agent
Clone the repo
git clone --depth 1 https://github.com/OneWave-AI/claude-skills

Made for: Claude Code, Codex.

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 agent-to-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/onewave-ai/claude-skills/agent-to-agent/github.svg)](https://agentmods.dev/skills/onewave-ai/claude-skills/agent-to-agent)
Your own site
<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/agent-to-agent"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/agent-to-agent/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 agent-to-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/agent-to-agent"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/agent-to-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 882 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00047 $0.00882
Opus 5 $0.00023 $0.00441
Sonnet 5 $0.00009 $0.00176
Haiku 4.5 $0.00005 $0.00088

Measured 12d ago against content hash 27ec1c2e4e73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-to-agent 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 12d 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.

agent-to-agent/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-to-Agent (A2A) Communication Protocol

Act as the A2A Coordinator: a protocol layer that lets multiple Claude Code agents communicate, collaborate, and delegate work through structured message passing, shared context, and formal handoffs. Orchestrate every interaction through the shared context file .a2a-context.json and the Agent tool.

Contents

  • references/protocol.md — message format, message types, lifecycle, shared context schema, atomic read-modify-write, context size management.
  • references/registry.md — agent registration, capability discovery, built-in agent templates.
  • references/patterns.md — request/response, pipeline, fan-out/fan-in, conversation, supervisor.
  • references/handoff.md — structured handoff, acceptance, rejection, chain tracking.
  • references/error-handling.md — timeouts, rejections, deadlock detection, degradation, escalation matrix.
  • references/workflows.md — worked examples (research+writer, code+review, sales+technical).
  • references/operations.md — coordination commands, best practices, monitoring, security, init detail.

Workflow

  1. Understand the goal. Determine what the user wants to accomplish with multiple agents.
  2. Design the team. Decide which agents are needed; draw from the templates in references/registry.md or write custom specs.
  3. Choose the pattern. Select pipeline, fan-out/fan-in, conversation, or supervisor from references/patterns.md. Prefer pipeline when order matters, fan-out when subtasks are independent.
  4. Initialize. Locate the project root. Read .a2a-context.json if it exists and report current state; otherwise create it from the template in references/operations.md. Register every agent into the agents section per references/registry.md.
  5. Execute. Dispatch agents via the Agent tool following the chosen pattern. Structure each agent prompt with identity, context, task, output location, protocol, and constraints (see references/operations.md). For parallelism, issue multiple Agent tool calls in a single response.
  6. Coordinate handoffs. When an agent transfers a task, require a full handoff payload and an ACK, and append to the task chain. Follow references/handoff.md.
  7. Monitor and recover. Read .a2a-context.json to track progress. On timeout, rejection, deadlock, or failure, apply the procedures and escalation matrix in references/error-handling.md. Cap retries at 3 before escalating to the user.
  8. Deliver. Merge all agent findings into the conclusions section and present the final output.

Read the full file on GitHub · 55 lines

Files

What ships with it

7 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. 12d ago First seen · 55 lines · 47 tokens per session scan A 27ec1c2e4e73

Subscribe to this mod's changes

agent-to-agent is a skill published in the GitHub repository OneWave-AI/claude-skills (288 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 882 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

analytics-strategy

Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…

rampstackco/claude-skills · 126 tokens

content-strategy

Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…

rampstackco/claude-skills · 120 tokens

incident-response

Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…

rampstackco/claude-skills · 117 tokens

stakeholder-communication

Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…

rampstackco/claude-skills · 103 tokens

agb-begriff-vorformuliert-305

Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.

Klotzkette/claude-fuer-deutsches-recht · 68 tokens

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens