Borrowing it
Nothing to install: this file belongs to a2aproject/a2a-java. 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-java/main/.agents/skills/update-a2a-proto/SKILL.mdgit clone --depth 1 https://github.com/a2aproject/a2a-javaWrote 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-java/update-a2a-proto)<a href="https://agentmods.dev/skills/a2aproject/a2a-java/update-a2a-proto"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-java/update-a2a-proto/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-java/update-a2a-proto"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-java/update-a2a-proto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.00737 |
| Opus 5.5 | $0.00024 | $0.00295 |
| Sonnet 5.5 | $0.00012 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
update-a2a-proto 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.
compatibility: Requires curl How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update a2a.proto
Update the A2A gRPC proto file from the upstream specification repository and regenerate Java sources.
Step 1: Capture the current state
Before updating, record what we have now so we can diff later.
- Read
spec-grpc/src/main/proto/a2a.prototo note the current commit hash (located at the top of the file in a comment) - Save a copy of the file for diffing:
Step 2: Download the updated specification
- Ask the user if they want to update from the
mainbranch or pass atagor acommit cheksum - Download the latest
a2a.protofrom the upstream A2A repository at https://github.com/a2aproject/A2A/blob/main/specification/a2a.proto and save it tospec-grpc/src/main/proto/a2a.proto. - Update the
java_packageoption in the downloaded proto file to:option java_package = "org.a2aproject.sdk.grpc"; - Update the comment tracking the upstream commit hash (line starting with
// From commit) to the commit hash / tag of the downloaded proto file.
Step 3: Analyze specification changes
Compare the old and new versions of the specification to identify changes:
- Diff
specification/a2a.protowith the backup to find:- New or changed message types
- New or changed RPC methods
- New or changed fields
Step 4: Regenerate gRPC classes
-
Delete all the generated gRPC Java classes (in case of resources removed from the Protobuf definitions):
find spec-grpc/src/main/java/org/a2aproject/sdk/grpc -maxdepth 1 -name "*.java" -delete``` -
Regenerate gRPC Java classes by running:
mvn generate-sources -pl spec-grpc -Dskip.protobuf.generate=false
Step 5: Update the code
Based on the spec diff, update the relevant files
Summarize the changes for the user before proceeding.
Step 6: Validate
Run the tests on all modules to verify the update
mvn clean install
Fix any issues before proceeding.
Step 7: Audit changes
Before committing, audit all code 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.
- 2mo ago First seen · 86 lines · 60 tokens per session scan A 5fa2b7f041e4
update-a2a-proto is a skill published in the GitHub repository a2aproject/a2a-java (509 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 737 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.
update-a2a-proto compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| update-a2a-protoa2aproject/a2a-java | Skill | 509 | yesterday | Apache-2.0 | A | 60 | Claude Code |
| frankfurtera2aproject/a2a-samples | Skill | 1.8k | 17d ago | Apache-2.0 | A | 14 | Claude Code, Codex |
| searxng-settings-editorKnuckles-Team/searxng-mcp | Skill | 3 | yesterday | MIT | A | 152 | Claude Code, Codex |
| jellyfin-mcp-developmentKnuckles-Team/jellyfin-mcp | Skill | 3 | yesterday | MIT | A | 60 | Claude Code, Codex |
| searxng-kg-ingestionKnuckles-Team/searxng-mcp | Skill | 3 | yesterday | MIT | A | 126 | Claude Code, Codex |
| searxng-web-searchKnuckles-Team/searxng-mcp | Skill | 3 | yesterday | MIT | A | 138 | Claude Code, Codex |
| jellyfin-kg-ingestionKnuckles-Team/jellyfin-mcp | Skill | 3 | yesterday | MIT | A | 158 | Claude Code, Codex |