crestapps-core-a2a

crestapps-core-a2a is a skill for Claude Code from CrestApps/CrestApps.AgentSkills. It costs 182 tokens per session (2,158 once invoked), scanned A, original, MIT.

A development skill for connecting one AI agent to another through the Agent-to-Agent protocol, which lets independent agents discover and use each other's abilities.

In plain words
What is it for?
Use it to add an A2A client, discover remote agent descriptions, invoke their skills, and configure authentication and host endpoints.
Why use it?
It helps distinguish agent-to-agent connections from MCP connections, which usually expose tools or data rather than a reasoning agent.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the crestapps-core plugin — 47 skills shipped together

Good fit Use it to add an A2A client, discover remote agent descriptions, invoke their skills, and configure authentication and host endpoints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/crestapps/crestapps.agentskills/crestapps-core-a2a
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 CrestApps/CrestApps.AgentSkills --skill crestapps-core-a2a
Clone the repo
git clone --depth 1 https://github.com/CrestApps/CrestApps.AgentSkills

Made for: Claude Code.

Or install crestapps-core, the plugin that ships this one along with the rest of its 47 skills.

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 crestapps-core-a2a

README.md
[![agentmods](https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-a2a/github.svg)](https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-a2a)
Your own site
<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-a2a"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-a2a/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.

agentmods 80×15 button for crestapps-core-a2a

Your own site · 80×15
<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-a2a"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-a2a.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 182 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,158 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00182 $0.02158
Opus 5.5 $0.00073 $0.00863
Sonnet 5.5 $0.00036 $0.00432
Haiku 4.5 $0.00018 $0.00216

Measured yesterday against content hash 430bdf58096f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crestapps-core-a2a 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 yesterday.

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.

plugins/crestapps-core/skills/crestapps-core-a2a/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CrestApps.Core A2A

Use A2A when the remote system is an agent that reasons on its own (its own model, tools and context). Use MCP (crestapps-core-mcp) when the remote system exposes tools or resources. CrestApps.Core.AI.A2A ships the client; hosting is application code built on the A2A and A2A.AspNetCore 1.0 SDK packages, using A2AHostOptions from the framework.

Client

builder.Services.AddCrestAppsCore(crestApps => crestApps
    .AddAISuite(ai => ai
        .AddOpenAI()
        .AddA2AClient(a2a => a2a
            .AddEntityCoreStores()))   // or .AddYesSqlStores(); registers ICatalog<A2AConnection>
    .AddEntityCoreSqliteDataStore("Data Source=app.db"));

AddCoreAIA2AClient() registers a resilient named HttpClient, IMemoryCache, A2AAICompletionContextBuilderHandler, A2AToolRegistryProvider, IA2AAgentCardCacheService (15-minute cache), IA2AConnectionAuthService, and the system tools listAvailableAgents, findAgentForTask and findToolsForTask.

Connections

using CrestApps.Core;
using CrestApps.Core.AI.A2A;
using CrestApps.Core.AI.A2A.Models;
using CrestApps.Core.AI.Models;

var protector = dataProtectionProvider.CreateProtector(A2AConstants.DataProtectionPurpose); // "A2AClientConnection"

var connection = new A2AConnection
{
    DisplayText = "Legal Review Agent",
    Endpoint = "https://agents.example.com/",
};

connection.Put(new A2AConnectionMetadata
{
    AuthenticationType = ClientAuthenticationType.ApiKey,
    ApiKeyHeaderName = "Authorization",
    ApiKeyPrefix = "Bearer",
    ApiKey = protector.Protect(apiKey),
});

await connectionCatalog.CreateAsync(connection);

profile.Put(new AIProfileA2AMetadata { ConnectionIds = [connection.ItemId] });
  • Authentication types are Anonymous, ApiKey, Basic, OAuth2ClientCredentials, OAuth2PrivateKeyJwt, OAuth2Mtls and CustomHeaders. Protect every secret with the A2AClientConnection purpose.
  • The card is fetched with A2ACardResolver from connection.Endpoint (the SDK reads /.well-known/agent-card.json under it) and each skill becomes a tool a2a:{connectionId}:{skillId} whose name keeps only letters, digits and _.
  • A2AAgentProxyTool sends a 1.0 SendMessageRequest with a Message (Role.User, Part.FromText, ContextId, metadata agentName) to connection.Endpoint, not to the URL in the card's supportedInterfaces. Set Endpoint to the address that accepts JSON-RPC messages and also serves the card.
  • A2ACardResolver returns a single AgentCard. A host that publishes an array of cards (one per agent) is best consumed in skill mode (ExposeAgentsAsSkill = true).
  • Replace IA2AAgentCardCacheService for a distributed cache, or IA2AConnectionAuthService for a custom auth scheme.

Read the full file on GitHub · 178 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. yesterday Changed · +125 lines · +152 tokens per session 430bdf58096f
  2. 1mo ago First seen · 53 lines · 30 tokens per session scan A 0dff2c169d5e

Subscribe to this mod's changes

crestapps-core-a2a is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed yesterday), licensed MIT. It adds 182 tokens to every session and 2,158 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-30.

Related

Other skills, from other repositories

powerpoint-cli

Discover and use the PowerPoint CLI plugin to automate a live PowerPoint desktop session. Use for terminal, PowerShell, batch, and coding-agent tasks; not general presentation design. Triggers: pptcli, PowerPoint command line, presentation automation script.

sbroenne/mcp-server-powerpoint · 55 tokens

powerpoint-deck-design

Plan or improve the visual design of a PowerPoint presentation: layout, typography, color, hierarchy, accessibility, and consistency. Use when the user asks to create, redesign, or review how a deck looks; not for general PowerPoint automation or content-only edits.

sbroenne/mcp-server-powerpoint · 59 tokens

home-memory-documentation

Do not load unless the request or established context explicitly identifies Home Memory (HM) and requires a documentation decision about record boundaries, relationships or information placement. If the product is ambiguous, ask whether the user means Home Memory or Smartconstruct and load neither product skill first.…

impactjo/home-memory · 112 tokens

dotnet-debugging

Debug .NET applications using debug-mcp MCP tools — launch processes, set breakpoints, step through code, inspect variables, evaluate expressions, and analyze exceptions. Use this skill when debugging .NET/C# applications, investigating runtime behavior, diagnosing exceptions, inspecting object state, or performing…

jkolo/debug-mcp · 70 tokens

sast-missingauth

Detect missing authentication and broken function-level authorization vulnerabilities in a codebase using a three-phase approach: recon (map endpoints and the role/permission system), batched verify (check auth/authz in parallel subagents, 3 endpoints each), and merge (consolidate batch results). Covers…

capture0x/YeepForge · 121 tokens

sast-analysis

Perform codebase analysis and architecture mapping as the first phase of a security assessment. Explores the tech stack, frameworks, entry points, data flows, and trust boundaries. Outputs sast/architecture.md. Run this before any vulnerability detection skill. Use when asked to analyze a codebase for security or when…

capture0x/YeepForge · 73 tokens