Borrowing it
Nothing to install: this file belongs to a2aproject/a2a-tck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/a2aproject/a2a-tck/main/.agents/skills/a2a-jakarta-sut/SKILL.mdgit clone --depth 1 https://github.com/a2aproject/a2a-tckWrote 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/a2aproject/a2a-tck/a2a-jakarta-sut)<a href="https://agentmods.dev/skills/a2aproject/a2a-tck/a2a-jakarta-sut"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-tck/a2a-jakarta-sut/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.
<a href="https://agentmods.dev/skills/a2aproject/a2a-tck/a2a-jakarta-sut"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-tck/a2a-jakarta-sut.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00054 | $0.02038 |
| Opus 5.5 | $0.00022 | $0.00815 |
| Sonnet 5.5 | $0.00011 | $0.00408 |
| Haiku 4.5 | $0.00005 | $0.00204 |
Grade C, and why
a2a-jakarta-sut scanned grade C with 2 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 2mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://localhost:8080/.well-known/agent-card.json | python3 -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(make:*) Bash(mvn:*) Bash(java:*) Bash(curl:*) Bash(kill:*) Bash(lsof:*) Bash(uv:*) Read Edit Write Glob Grep Agent How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work with the a2a-jakarta SUT
The a2a-jakarta SUT is a WildFly application generated from Gherkin .feature files in scenarios/. It implements the A2A protocol using the Jakarta EE A2A SDK and serves as a conformance target for TCK tests.
Architecture overview
scenarios/*.feature → codegen (parser + steps + jakarta_emitter) → sut/a2a-jakarta/
- Gherkin scenarios (
scenarios/*.feature) define SUT behavior via messageId prefix matching - Code generator (
codegen/) parses.featurefiles and emits a WildFly project - Jinja2 templates (
codegen/a2a-jakarta/*.j2) produce the Java sources,pom.xml,beans.xml, and JAX-RS Application class - Generated output (
sut/a2a-jakarta/) is a complete Maven WAR project
Key generated files
| File | Template | Purpose |
|---|---|---|
TckAgentExecutorProducer.java |
TckAgentExecutorProducer.java.j2 |
CDI producer for AgentExecutor; routes by messageId prefix |
TckAgentCardProducer.java |
TckAgentCardProducer.java.j2 |
CDI producer for AgentCard with all three transports |
TckApplication.java |
TckApplication.java.j2 |
JAX-RS @ApplicationPath("/") entry point |
beans.xml |
beans.xml.j2 |
CDI descriptor with gRPC exclusion |
pom.xml |
pom.xml.j2 |
Maven build with WildFly plugin and Jakarta SDK dependencies |
How the executor works
The generated AgentExecutor matches on the messageId prefix from incoming messages:
if (messageId.startsWith("tck-complete-task")) {
emitter.complete(A2A.toAgentMessage("Hello from TCK"));
return;
}
The TCK tests use tck_id("complete-task") which generates tck-complete-task-<session_hex>, matching the prefix.
Step 0: Inform the user of the version of the Jakarta SDK
The Jakarta SDK version is controlled by the A2A_JAKARTA_SDK_VERSION environment variable.
The default value is defined in codegen/jakarta_emitter.py (_DEFAULT_A2A_JAKARTA_SDK_VERSION).
Read the actual default version from codegen/jakarta_emitter.py (grep for _DEFAULT_A2A_JAKARTA_SDK_VERSION) and check the env var. Report to the user which version will be used and propose setting the env var if they want a different version:
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.
- 2mo ago First seen · 186 lines · 54 tokens per session scan C 405741929e88
a2a-jakarta-sut is a skill published in the GitHub repository a2aproject/a2a-tck (56 stars, last pushed 8d ago), licensed Apache-2.0. It adds 54 tokens to every session and 2,038 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.