Agent skill

OmniRoute A2A Agents

by diegosouzapw in diegosouzapw/OmniRoute

Explains how to call OmniRoute over JSON-RPC 2.0 using the agent-to-agent protocol, including its Agent Card, built-in skills, call shape and error codes.

MITAuto-check passedAI & LLM Engineering

Install OmniRoute A2A Agents

skills CLI
$ npx skills add diegosouzapw/OmniRoute --skill omni-agents-a2a -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install diegosouzapw/OmniRoute omni-agents-a2a --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/diegosouzapw/OmniRoute.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/omni-agents-a2a .claude/skills/omni-agents-a2a && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
omni-agents-a2a
GitHub stars
74k
Token cost
~794 tokens
SKILL.md length
181 words
Files
1
Skills in repo
50
Repo updated
First seen
Licence
MIT

At a glance

Explains how to call OmniRoute over JSON-RPC 2.0 using the agent-to-agent protocol, including its Agent Card, built-in skills, call shape and error codes.

  • Asking OmniRoute which provider and model suit a given prompt
  • SKILL.md covers Overview, Authentication, Endpoints and Payloads, plus 6 more sections
  • Calls curl; needs OMNIROUTE_KEY and REQUIRE_API_KEY
  • Checking quota balance or system health through the A2A endpoint

What it does

OmniRoute publishes an Agent Card at /.well-known/agent.json that lists its skills, endpoints and auth scheme, and accepts JSON-RPC 2.0 calls at /a2a with a Bearer key. The listed skills are smart-routing, which recommends a provider and model for a prompt, quota-management for quota balance, provider-discovery for finding providers by capabilities such as vision, JSON mode, tools and maximum context, cost-analysis for estimating a request's cost, and health-report for circuit states, latencies and errors. The description also names list-capabilities.

Requests need OMNIROUTE_URL and OMNIROUTE_KEY, or a session cookie, with a token obtained from POST /api/auth/login or REQUIRE_API_KEY set to false for local development. Error codes are -32600 for a bad JSON-RPC envelope, -32601 for an unknown method, -32602 for invalid params such as a skillId missing from the Agent Card, and 401 for a missing or invalid key. The full API schema is served at /api/openapi/spec.

When your agent uses it

  • Asking OmniRoute which provider and model suit a given prompt
  • Checking quota balance or system health through the A2A endpoint
  • Estimating the cost of a request shape before sending it
  • Debugging a failing JSON-RPC call to OmniRoute

Example prompts

  • “Fetch the OmniRoute Agent Card and list the skills it offers.”
  • “Call the smart-routing skill with a long coding prompt and tell me which model it recommends.”
  • “My A2A call returns -32602, so check the skillId against the Agent Card.”

Requirements

  • A running OmniRoute server with OMNIROUTE_URL and OMNIROUTE_KEY set

What it can do on your machine

Read from SKILL.md and the folder at commit 4ea24a2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OMNIROUTE_KEY
    • REQUIRE_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

OmniRoute A2A Agents loads about 794 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 181 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~794

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from diegosouzapw/OmniRoute at commit 4ea24a2, republished under its MIT licence (© diegosouzapw). 181 words, ~794 tokens.

Download SKILL.mdSave it as .claude/skills/omni-agents-a2a/SKILL.md (or your agent's skills folder).
name
omni-agents-a2a
description
Interact with OmniRoute via JSON-RPC 2.0 agent-to-agent protocol. 6 built-in A2A skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities.
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->

Overview

Interact with OmniRoute via JSON-RPC 2.0 agent-to-agent protocol. 6 built-in A2A skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities.

Authentication

All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.

Endpoints

No endpoints mapped for this area yet.

Payloads

See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.

<!-- skill:custom-start -->
<!-- Migrated from skills/omniroute-a2a/SKILL.md (preserved curated content) -->

OmniRoute — A2A Protocol

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

OmniRoute publishes an Agent Card at /.well-known/agent.json and accepts JSON-RPC 2.0 calls at /a2a.

Discovery

bash
curl $OMNIROUTE_URL/.well-known/agent.json

Returns Agent Card with skills, endpoints, auth scheme.

Available skills

SkillPurpose
smart-routingGiven a prompt, recommends best provider/model combo
quota-managementReports quota balance for given provider/account
provider-discoveryLists providers matching capability filters (vision, JSON mode, tools, max-context)
cost-analysisEstimates cost for a given request shape
health-reportReturns system health (circuit states, latencies, errors)

Call example (JSON-RPC 2.0)

bash
curl -X POST $OMNIROUTE_URL/a2a \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tasks/send",
    "params": {
      "skillId": "smart-routing",
      "input": { "prompt_length": 4000, "tools": true, "vision": false }
    },
    "id": 1
  }'

Response shape

json
{
  "jsonrpc": "2.0",
  "result": {
    "taskId": "...",
    "status": "completed",
    "output": { "recommended_combo": "...", "reasoning": "..." }
  },
  "id": 1
}

Errors

  • -32600 → invalid request (bad JSON-RPC envelope)
  • -32601 → method not found (check method field)
  • -32602 → invalid params (check skillId against Agent Card)
  • 401 → missing/invalid OMNIROUTE_KEY

Reference

Full docs: https://github.com/diegosouzapw/OmniRoute/blob/main/docs/frameworks/A2A-SERVER.md

<!-- skill:custom-end -->

© diegosouzapw, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/omni-agents-a2a of diegosouzapw/OmniRoute.

Open the folder on GitHubat commit 4ea24a2

Compare with similar skills

OmniRoute A2A Agents next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

OmniRoute A2A Agents compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
OmniRoute A2A Agents this skilldiegosouzapw/OmniRoute74k—~794Automated safety check: PassMIT
Openrouterdavidondrej/skills4.1k—~1.3kAutomated safety check: PassMIT
Embeddings via 9Routerdecolua/9router30k—~604Automated safety check: PassMIT
FreeRide Free Model ManagerShaivpidadi/FreeRide2372 repos~1.1kAutomated safety check: PassNone
Tavily Search API Integrationandrewyng/context-hub14k—~1.1kAutomated safety check: PassMIT
Pixiu LLM Gatewayapache/dubbo-go-pixiu568—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Openrouter

    davidondrej/skills

    Design, build, debug, and optimize OpenRouter API integrations.

    4.1k GitHub stars~1.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Embeddings via 9Router

    decolua/9router

    Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

    30k GitHub stars~604 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • FreeRide Free Model Manager

    Shaivpidadi/FreeRide

    Configures OpenClaw to use free OpenRouter models, setting the best one as primary and adding ranked fallbacks so rate limits do not interrupt work.

    237 GitHub starsUsed in 2 repos~1.1k tokens
    AI & LLM EngineeringAuto-check passed
  • Tavily Search API Integration

    andrewyng/context-hub

    Guides building Tavily integrations for web search, URL extraction, site crawling and AI-assisted research in Python or JavaScript agent and RAG projects.

    14k GitHub stars~1.1k tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check passed
  • Pixiu LLM Gateway

    apache/dubbo-go-pixiu

    Creates and validates dubbo-go-pixiu LLM gateway conf.yaml. An agent skill from apache/dubbo-go-pixiu.

    568 GitHub stars~2.5k tokensUpdated 6 days ago
    AI & LLM EngineeringAuto-check passed
  • Using Ccproxy API

    starbaser/ccproxy

    Guides users through ccproxy as an OpenAI-compatible and Anthropic-compatible LLM API server with SDK integration, OAuth authentication, sentinel key substitution, model routing, and troubleshooting.

    350 GitHub stars~4k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

More from diegosouzapw/OmniRoute

All 50 skills in this repo
  • OmniRoute Backup and Sync CLI

    diegosouzapw/OmniRoute

    Backup and restore OmniRoute data from the CLI. Trigger incremental snapshots, sync to cloud storage, manage backup schedules, and restore from archive files.

    74k GitHub stars~948 tokensUpdated today
    Auto-check passed
  • Quality Scan

    diegosouzapw/OmniRoute

    Runs a scoped, read-only quality scan on a repository candidate and reports exact evidence, failures and frozen debt, without treating a static scan as release acceptance.

    74k GitHub stars~748 tokensUpdated today
    Auto-check passed
  • OmniRoute Provider Management

    diegosouzapw/OmniRoute

    Manages AI provider connections, API keys, OAuth flows and connection tests through OmniRoute's REST API across its 327-provider catalog.

    74k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • OmniRoute Settings API

    diegosouzapw/OmniRoute

    Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration.

    74k GitHub stars~3.6k tokensUpdated today
    Auto-check passed
  • OmniRoute Database Backups

    diegosouzapw/OmniRoute

    Trigger system backups, restore from backup files, and manage the SQLite database lifecycle. Supports export, import, and incremental snapshot strategies.

    74k GitHub stars~395 tokensUpdated today
    Auto-check passed
  • OmniRoute Batch CLI

    diegosouzapw/OmniRoute

    Submit and monitor batch inference jobs from the CLI. Upload and manage files for batch processing, retrieve results, and integrate batch pipelines with CI/CD…

    74k GitHub stars~565 tokensUpdated today
    Auto-check passed

Questions about OmniRoute A2A Agents

What does OmniRoute A2A Agents do?

Explains how to call OmniRoute over JSON-RPC 2.0 using the agent-to-agent protocol, including its Agent Card, built-in skills, call shape and error codes. 0 calls at /a2a with a Bearer key. The listed skills are smart-routing, which recommends a provider and model for a prompt, quota-management for quota balance, provider-discovery for finding providers by capabilities such as vision, JSON mode, tools and maximum context, cost-analysis for estimating a request's cost, and health-report for circuit states, latencies and errors.

When should I use OmniRoute A2A Agents?

OmniRoute A2A Agents fits situations like: asking OmniRoute which provider and model suit a given prompt; checking quota balance or system health through the A2A endpoint; estimating the cost of a request shape before sending it; debugging a failing JSON-RPC call to OmniRoute.

How do I install OmniRoute A2A Agents in Claude Code?

Run `npx skills add diegosouzapw/OmniRoute --skill omni-agents-a2a -a claude-code`. Or copy the skill folder (skills/omni-agents-a2a in diegosouzapw/OmniRoute) into .claude/skills/omni-agents-a2a in your project. Claude Code loads it when a task matches its description.

How do I install OmniRoute A2A Agents in Codex?

Run `npx skills add diegosouzapw/OmniRoute --skill omni-agents-a2a -a codex`. Or copy the skill folder (skills/omni-agents-a2a in diegosouzapw/OmniRoute) into .agents/skills/omni-agents-a2a in your project. Codex loads it when a task matches its description.

Can I use OmniRoute A2A Agents in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add diegosouzapw/OmniRoute --skill omni-agents-a2a -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/omni-agents-a2a, .gemini/skills/omni-agents-a2a, .github/skills/omni-agents-a2a and .opencode/skills/omni-agents-a2a in your project.

What does OmniRoute A2A Agents need to run?

Going by SKILL.md and its folder, OmniRoute A2A Agents needs the command-line tools its instructions call (curl) and credentials named OMNIROUTE_KEY and REQUIRE_API_KEY. Our summary lists: A running OmniRoute server with OMNIROUTE_URL and OMNIROUTE_KEY set.

Does OmniRoute A2A Agents access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is OmniRoute A2A Agents safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does OmniRoute A2A Agents use?

OmniRoute A2A Agents is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does OmniRoute A2A Agents use?

About 794 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to OmniRoute A2A Agents?

Skills that share tags, products or a category with OmniRoute A2A Agents: Openrouter (davidondrej/skills, 4.1k stars), Embeddings via 9Router (decolua/9router, 30k stars), FreeRide Free Model Manager (Shaivpidadi/FreeRide, 237 stars) and Tavily Search API Integration (andrewyng/context-hub, 14k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains OmniRoute A2A Agents?

diegosouzapw (a GitHub user) maintains it in diegosouzapw/OmniRoute, which has 74,424 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 8, 2026.

Source: diegosouzapw/OmniRoute on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.