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.
npx skills add Lord1Egypt/awesome-skill-forge --skill a2a-agent-discoverygit clone --depth 1 https://github.com/Lord1Egypt/awesome-skill-forgeWrote 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/lord1egypt/awesome-skill-forge/a2a-agent-discovery)<a href="https://agentmods.dev/skills/lord1egypt/awesome-skill-forge/a2a-agent-discovery"><img src="https://agentmods.dev/badge/skills/lord1egypt/awesome-skill-forge/a2a-agent-discovery/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/lord1egypt/awesome-skill-forge/a2a-agent-discovery"><img src="https://agentmods.dev/badge/skills/lord1egypt/awesome-skill-forge/a2a-agent-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00026 | $0.01548 |
| Opus 5 | $0.00013 | $0.00774 |
| Sonnet 5 | $0.00005 | $0.00310 |
| Haiku 4.5 | $0.00003 | $0.00155 |
Grade A, and why
a2a-agent-discovery 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A2A Agent Discovery
Use this skill only when the user explicitly wants to use ITINAI, A2A, an Agent Card, or an agent service board. It supports finding service agents, inspecting Agent Cards, publishing the user's own service/wanted agent, and sending reviewed A2A service requests to selected remote agents.
Canonical sources:
- ITINAI registry source:
https://github.com/aihlp/itinai - Public hub:
https://itinai.com - Hub Agent Card:
https://itinai.com/.well-known/agent-card.json - Submit endpoint: use
endpoints.submitfrom the Hub Agent Card; fallback only tohttps://itinai.com/wp-json/itinai/v1/submit - Public catalog API:
GET /wp-json/itinai/v1/agents,GET /wp-json/itinai/v1/ai-search?query=,GET /wp-json/itinai/v1/agent/{agent_id}
Do not create a new registry, protocol, manifest format, proxy, marketplace, plugin, or endpoint. ITINAI is the board. Remote agents provide the services.
Core model
The workflow is Craigslist-like:
- A user searches the board for an agent that offers a service.
- The selected agent's Agent Card tells how to contact that agent.
- The user sends a service request directly to the selected agent's runtime endpoint.
- The selected agent may return offers, availability, catalog data, terms, or next steps.
- Purchases, payments, contracts, bookings, and irreversible commitments require a separate explicit user approval.
Search for service agents
Use this workflow only when the request explicitly mentions at least one activation term: ITINAI, A2A, Agent Card, agent board, service agent, remote agent, agent marketplace, or agents that can provide/sell/do <service>.
Do not use this workflow for ordinary web search, shopping, local search, product comparison, service recommendations, or drafting tasks unless the user clearly asks to route the request through ITINAI/A2A agents.
- Search ITINAI catalog sources or the bundled MCP tools.
- Match on
agent_id,name,description,skills[].name,skills[].tags, and dynamic service metadata if present. - Return concise options with
agent_id,name,description, relevant skills/tags, status if present, and Agent Card URL. - Ask the user to choose an agent only when multiple plausible matches exist and no target is obvious.
- Do not pretend a listed agent can complete a task until its Agent Card is fetched and the request endpoint is validated.
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.
- 12d ago First seen · 100 lines · 26 tokens per session scan A 53e08758578d
a2a-agent-discovery is a skill published in the GitHub repository Lord1Egypt/awesome-skill-forge (2 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,548 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…