a2a-error-handling

a2a-error-handling is a skill for Claude Code from OrcaQubits/agentic-commerce-skills-plugins. It costs 49 tokens per session (1,351 once invoked), scanned A, original, MIT.

An error-handling guide for A2A agents, where A2A is a protocol for agents to communicate and run tasks. It covers JSON-RPC errors, A2A error codes, failed tasks, retries, and graceful degradation.

In plain words
What is it for?
Use it when building or reviewing error handling in an A2A agent. It helps define error responses, task failure states, retry behavior, and fallback behavior.
Why use it?
It helps agents return consistent errors when requests are invalid, methods are missing, or task processing fails. It also addresses how to retry or continue safely when something goes wrong.

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 building or reviewing error handling in an A2A agent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orcaqubits/agentic-commerce-skills-plugins/a2a-error-handling
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-error-handling
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-error-handling

README.md
[![agentmods](https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-error-handling.svg)](https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-error-handling)
Your own site
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-error-handling"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-error-handling.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,351 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 $0.00049 $0.01351
Opus 5 $0.00024 $0.00675
Sonnet 5 $0.00010 $0.00270
Haiku 4.5 $0.00005 $0.00135

Measured 7d ago against content hash 3323d7368343, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

a2a-error-handling 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-error-handling/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A2A Error Handling

Before writing code

Fetch live docs:

  1. Fetch https://a2a-protocol.org/latest/specification/ for the error handling section
  2. Web-search site:github.com a2aproject A2A error codes for error code definitions
  3. Web-search site:github.com a2aproject a2a-samples error for error handling examples
  4. Fetch SDK docs for error classes and exception types

Conceptual Architecture

Error Categories

A2A has three categories of errors:

  1. JSON-RPC Protocol Errors — Malformed requests, invalid methods, parse failures
  2. A2A-Specific Errors — Protocol-level issues specific to A2A operations
  3. Task-Level Failures — The task itself fails during processing (task state → failed)

JSON-RPC 2.0 Error Format

All errors follow the JSON-RPC 2.0 error response format:

{
  "jsonrpc": "2.0",
  "id": "request-id",
  "error": {
    "code": -32600,
    "message": "Invalid Request",
    "data": { "details": "..." }
  }
}

Standard JSON-RPC Error Codes

Code Name Meaning
-32700 Parse error Invalid JSON
-32600 Invalid request Not a valid JSON-RPC request
-32601 Method not found Method doesn't exist or isn't supported
-32602 Invalid params Method parameters are invalid
-32603 Internal error Server internal error

A2A-Specific Error Codes

Code Name Meaning
-32001 TaskNotFoundError The referenced taskId doesn't exist
-32002 TaskNotCancelableError Task is in a state that can't be canceled (terminal state)
-32003 PushNotificationNotSupportedError Agent doesn't support push notifications
-32004 UnsupportedOperationError The requested operation is not supported
-32005 ContentTypeNotSupportedError Client's accepted output modes don't match agent's capabilities
-32006 InvalidAgentResponseError The agent returned an invalid or malformed response
-32007 ExtendedAgentCardNotConfiguredError Extended Agent Card is not configured
-32008 ExtensionSupportRequiredError A required extension is not supported
-32009 VersionNotSupportedError The requested protocol version is not supported

Read the full file on GitHub · 122 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 · 122 lines · 49 tokens per session scan A 3323d7368343

Subscribe to this mod's changes

a2a-error-handling is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,351 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.