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/run-tck/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/run-tck)<a href="https://agentmods.dev/skills/a2aproject/a2a-tck/run-tck"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-tck/run-tck/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/run-tck"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-tck/run-tck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 102 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00050 | $0.01602 |
| Opus 5.5 | $0.00020 | $0.00641 |
| Sonnet 5.5 | $0.00010 | $0.00320 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
run-tck scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s <sut-host>/.well-known/agent-card.json | uv run python -m json.tool How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run TCK Against an SDK Implementation
Follow these steps to help an SDK implementor run the A2A TCK against their SUT.
Step 1: Verify prerequisites
Check that the TCK project is set up:
uv run python --version # Python 3.11+ required
If dependencies are not installed, run:
uv pip install -e .
Step 2: Confirm the SUT is running and reachable
Ask the user for their SUT URL (e.g., http://localhost:9999).
Verify the SUT is running by fetching its agent card:
curl -s <sut-host>/.well-known/agent-card.json | uv run python -m json.tool
The agent card must be served at {sut-host}/.well-known/agent-card.json per A2A spec Section 8.2.
Agent card requirements
The agent card must include a supportedInterfaces array. Each entry needs:
protocolBinding— one of"JSONRPC","GRPC", or"HTTP+JSON"url— the endpoint URL for that transport
Example:
{
"name": "My Agent",
"supportedInterfaces": [
{ "protocolBinding": "JSONRPC", "url": "http://localhost:9999/jsonrpc" },
{ "protocolBinding": "HTTP+JSON", "url": "http://localhost:9999/a2a" }
]
}
If the agent card is missing or malformed, help the user fix it before proceeding.
Step 3: Run the TCK
Important: Always use uv run to invoke the test runner so that the
project's virtual environment and dependencies are available.
Running ./run_tck.py directly may fail if the system Python lacks pytest or
other dependencies.
Reports are always generated in reports/ after every run. Point the user to
reports/compatibility.html and reports/tck_report.html after the run completes.
Important: Always run TCK commands from the TCK project root directory
(a2a-tck/), not from a subdirectory like sut/a2a-python/.
Start with MUST-level tests to catch blocking issues first:
uv run ./run_tck.py --sut-host <sut-host> --level must -v
Optionally filter by transport (grpc, jsonrpc, http_json):
uv run ./run_tck.py --sut-host <sut-host> --transport jsonrpc --level must -v
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 · 180 lines · 50 tokens per session scan A ce01efc06b83
run-tck is a skill published in the GitHub repository a2aproject/a2a-tck (56 stars, last pushed 8d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,602 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (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.