a2a-endpoint-validation

a2a-endpoint-validation is a skill for Claude Code, OpenCode from oaslananka/a2amesh. It costs 31 tokens per session (608 once invoked), scanned A, original, Apache-2.0.

A checker for A2A endpoints, the network addresses where software agents receive tasks, and their Agent Cards, which describe those agents. It checks metadata, health routes, and selected protocol behavior.

In plain words
What is it for?
Use it to inspect an Agent Card, check endpoint health, test protocol conformance, or compare declared capabilities with observed read-only behavior.
Why use it?
It provides bounded evidence about whether an endpoint responds as expected before an agent workflow relies on it. A successful check does not prove that the endpoint is trusted or approved for sensitive work.

Skill for Claude CodeOpenCode

Written for Claude Code and OpenCode: shipped in a Claude Code plugin, but also installed under .opencode/.

Part of the a2amesh plugin — 3 skills, 1 MCP server shipped together

Good fit Use it to inspect an Agent Card, check endpoint health, test protocol conformance, or compare declared capabilities with observed read-only behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oaslananka/a2amesh/a2a-endpoint-validation
Install

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.

Any agent
npx skills add oaslananka/a2amesh --skill a2a-endpoint-validation
Clone the repo
git clone --depth 1 https://github.com/oaslananka/a2amesh

Made for: Claude Code, OpenCode.

Or install a2amesh, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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.

agentmods badge for a2a-endpoint-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/oaslananka/a2amesh/a2a-endpoint-validation.svg)](https://agentmods.dev/skills/oaslananka/a2amesh/a2a-endpoint-validation)
Your own site
<a href="https://agentmods.dev/skills/oaslananka/a2amesh/a2a-endpoint-validation"><img src="https://agentmods.dev/badge/skills/oaslananka/a2amesh/a2a-endpoint-validation.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00608
Opus 5 $0.00015 $0.00304
Sonnet 5 $0.00006 $0.00122
Haiku 4.5 $0.00003 $0.00061

Measured 7d ago against content hash 5b01c33ec1df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

a2a-endpoint-validation 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 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.

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.

.opencode/skills/a2a-endpoint-validation/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A2A Endpoint Validation

Use this skill to establish bounded evidence about an A2A endpoint before sending work to it.

When to use

Use this skill when the user asks to:

  • inspect or validate an Agent Card;
  • discover an A2A endpoint;
  • check endpoint health or protocol conformance;
  • establish whether an endpoint is suitable for a later task workflow; or
  • compare declared capabilities with observed read-only behavior.

Do not treat a successful probe as proof that an endpoint is trustworthy, approved for production use, or authorized for sensitive data.

Required context

Collect or confirm:

  • the exact endpoint URL or Agent Card path;
  • whether the endpoint is local, public, or on a private network;
  • the expected protocol version and authentication method;
  • the expected tenant or trust boundary, when applicable; and
  • the permitted validation depth: metadata only, health, or conformance.

Never request concrete secret values in chat. Refer to credential variable names or an already configured runtime secret source.

Workflow

  1. Start with local CLI diagnostics: pnpm dlx @a2amesh/cli doctor --json.
  2. Validate a file-backed Agent Card with pnpm dlx @a2amesh/cli validate <path> or inspect an endpoint with discover.
  3. Run health before a broader conformance check.
  4. Use conformance only against an endpoint the user is authorized to test.
  5. Keep private-network access disabled unless the user explicitly authorizes the destination and --allow-private-network is necessary.
  6. Record the endpoint, command category, observed protocol/capabilities, bounded failures, and remaining unknowns.
  7. Stop before any message send, task cancellation, registry import, or other state-changing action.

Safety boundaries

  • This workflow is read-only.
  • Do not bypass TLS, authentication, tenant, audience, or outbound-network policy.
  • Do not infer trust from a reachable health route.
  • Do not echo authorization headers, tokens, URL query credentials, or private Agent Card fields.
  • Do not probe private or link-local destinations without explicit authorization.
  • Treat redirects as new destinations that require the same outbound-policy checks.

Read the full file on GitHub · 76 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.

  1. 7d ago First seen · 76 lines · 31 tokens per session scan A 5b01c33ec1df

Subscribe to this mod's changes

a2a-endpoint-validation is a skill published in the GitHub repository oaslananka/a2amesh (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 608 once invoked, about $0.0002 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 2026-08-31.