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.
npx agentmods add skills/orcaqubits/agentic-commerce-skills-plugins/a2a-testingnpx skills add OrcaQubits/agentic-commerce-skills-plugins --skill a2a-testinggit clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-pluginsWrote 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.
[](https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-testing)<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-testing"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/a2a-testing.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00050 | $0.00873 |
| Opus 5 | $0.00025 | $0.00436 |
| Sonnet 5 | $0.00010 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
a2a-testing 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A2A Testing
Before writing code
Fetch live docs:
- Fetch
https://a2a-protocol.org/latest/specification/for protocol requirements to test against - Web-search
site:github.com a2aproject A2A testing conformancefor testing tools and guidance - Web-search
site:github.com a2aproject a2a-samples testfor test examples - Fetch SDK docs for test utilities, mock classes, and test helpers
Conceptual Architecture
Testing Levels
A2A implementations need testing at multiple levels:
1. Unit Tests
Test individual components in isolation:
- Agent handler logic (given input message, verify output)
- Task state management (verify state transitions)
- Message/Part construction and parsing
- Agent Card validation
- Error code generation
2. Integration Tests
Test the A2A server with a real HTTP stack:
- Send JSON-RPC requests, verify responses
- Test all supported methods (message/send, tasks/get, etc.)
- Verify Agent Card serving at
/.well-known/agent-card.json - Test authentication flows
- Test streaming with SSE client
3. Protocol Conformance Tests
Verify compliance with the A2A specification:
- All required methods are implemented
- Request/response schemas match the spec
- Error codes are correct
- State transitions follow the rules
- Agent Card schema is valid
4. End-to-End Tests
Test full multi-agent workflows:
- Client discovers agent via Agent Card
- Client sends task, agent processes, client receives result
- Multi-turn conversations complete successfully
- Error scenarios are handled gracefully
- Multiple agents collaborate on a complex task
Mock Agents
For testing clients, create mock A2A servers that:
- Return predefined responses
- Simulate different task states
- Simulate errors and failures
- Simulate slow responses and timeouts
- Support streaming with controlled events
For testing servers, create mock A2A clients that:
- Send various message types and parts
- Exercise multi-turn flows
- Send invalid requests to test error handling
- Simulate disconnections during streaming
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.
- 4d ago First seen · 114 lines · 50 tokens per session scan A 6f4a4164443e
a2a-testing is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 873 once invoked, about $0.0003 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.
Other skills, from other repositories
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
qa/test-strategy
测试策略和测试金字塔原则，定义单元测试、集成测试、E2E测试的分布和覆盖要求.
prd-auto-test-loop
PRD 驱动的自动化测试编排技能。用于把每版 PRD 的测试计划、AI 自测与自修复、测试报告标准化落地；适用于按验收标准拆分 Unit/Integration/E2E、划分自动化与人工边界、生成版本化 TESTPLAN/TESTREPORT 的场景。.
pact-testing-strategies
Testing strategies, test pyramid guidance, and quality assurance patterns for PACT Test phase. Use when: designing test suites, implementing unit tests, integration tests, E2E tests, performance testing, security testing, or determining test coverage priorities. Triggers on: test design, unit testing, integration…
test-writer
Skill "test-writer" from miniidealab/openlogos, covering skill: test writer, 触发条件, 前置依赖, 核心能力 and 执行步骤.
test-automator
Test automation framework expert for creating and maintaining automated tests. Use when user asks to write tests, automate testing, or improve test coverage.