What is update-a2a-spec?

A procedure for updating the A2A TCK when the A2A protocol specification changes. A2A is a standard for communication between AI agents, and the TCK is its compatibility test suite.

Use it to sync the specification from the upstream A2A repository, regenerate gRPC code and schemas when needed, and update the TCK after protocol changes.

It reduces the risk of the test suite using an outdated specification or generated code. The procedure records the current state, downloads the selected upstream version, and regenerates affected files.

How a2aproject/a2a-tck configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/a2aproject/a2a-tck/main/.agents/skills/update-a2a-spec/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/a2aproject/a2a-tck

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/a2aproject/a2a-tck/update-a2a-spec.svg)](https://agentmods.dev/skills/a2aproject/a2a-tck/update-a2a-spec)

Your own site

<a href="https://agentmods.dev/skills/a2aproject/a2a-tck/update-a2a-spec"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-tck/update-a2a-spec.svg" alt="Measured on agentmods" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,972 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.01972
Opus 5	$0.00026	$0.00986
Sonnet 5	$0.00010	$0.00394
Haiku 4.5	$0.00005	$0.00197

Measured 7d ago against content hash a2a756eec33b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

update-a2a-spec 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

compatibility: Requires curl, git, buf, and uv

.agents/skills/update-a2a-spec/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update A2A Protocol Specification

Follow these steps to update the TCK after an A2A protocol specification change.

Step 1: Capture the current state

Before updating, record what we have now so we can diff later.

Read specification/version.json to note the current commit hash.
Save copies of the key spec files for diffing:
- specification/specification.md
- specification/a2a.proto

Step 2: Download the updated specification

Ask the user if they want to update from the main branch or pass a tag or a commit cheksum

Run:

make spec

This executes scripts/update_spec.sh, which downloads the latest spec files from the upstream a2aproject/A2A GitHub repository and updates specification/version.json.

If updating from a fork or a different branch, pass arguments:

./scripts/update_spec.sh --org <org> --branch <branch>

Step 3: Regenerate gRPC stubs and JSON schema

Skip this step if specification/a2a.proto did not change (diff shows no proto changes).

gRPC stubs

Run:

make proto

This executes scripts/generate_grpc_stubs.sh, which uses buf to regenerate specification/generated/a2a_pb2.py and specification/generated/a2a_pb2_grpc.py from the updated a2a.proto.

If buf is not installed, first run ./scripts/install_buf.sh.

After regenerating, check the protobuf version in the generated stubs (head -5 specification/generated/a2a_pb2.py) and verify it is compatible with the protobuf runtime version installed in the project (see pyproject.toml). If the gencode version is newer than the runtime allows, pin the plugin versions in specification/buf.gen.yaml to a compatible release (e.g., buf.build/protocolbuffers/python:v30.2).

JSON schema

Ask the user for the path to their local googleapis checkout, then run:

PATH="$HOME/go/bin:$PATH" GOOGLEAPIS_DIR=<path-to-googleapis> make jsonschema

This regenerates specification/a2a.json from the updated a2a.proto. It requires:

protoc-gen-jsonschema, installed via go install github.com/bufbuild/protoschema-plugins/cmd/protoc-gen-jsonschema@latest
GOOGLEAPIS_DIR set to the user's local googleapis checkout

Read the full file on GitHub · 177 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.

7d ago First seen · 177 lines · 52 tokens per session scan A a2a756eec33b

Subscribe to this mod's changes

update-a2a-spec is a skill published in the GitHub repository a2aproject/a2a-tck (49 stars, last pushed 5d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,972 once invoked, about $0.0003 per session on Opus 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.

Building agents Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

a2a-tck: Skill for Claude Code