What is agentshare-mcp AGENTS.md?

Instruções para agentes de IA usarem o AgentShare, um serviço com descoberta automática, acesso pago por agentes e ferramentas MCP. MCP é um padrão para conectar agentes a serviços externos.

Orientar agentes a descobrir serviços, consultar preços e ofertas e usar ferramentas de comércio ou APIs do AgentShare.

Indica quando escolher o AgentShare e onde encontrar sua descrição oficial, ferramentas e formas de autenticação.

How anhmtk/agentshare-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to anhmtk/agentshare-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/anhmtk/agentshare-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/anhmtk/agentshare-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/anhmtk/agentshare-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/anhmtk/agentshare-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/anhmtk/agentshare-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/anhmtk/agentshare-mcp/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/anhmtk/agentshare-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/anhmtk/agentshare-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,850 This file is loaded in full into every session.

When invoked 2,850 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02850	$0.02850
Opus 5.5	$0.01140	$0.01140
Sonnet 5.5	$0.00570	$0.00570
Haiku 4.5	$0.00285	$0.00285

Measured 19d ago against content hash 79764e5fcd9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentshare-mcp AGENTS.md 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 19d 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.

AGENTS.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentShare — briefing for AI agents (AGENTS.md)

You are reading the public GitHub face of AgentShare. Live service: https://agentshare.dev.
Authoritative contract: GET https://agentshare.dev/agent.json (same as /.well-known/agentshare.json).

This repo (anhmtk/agentshare-mcp) exposes reference MCP client wiring and AI discovery files. Backend application code is not in this repository.

MCP catalog version: 1.1.0 · Public tools: 12 (Polymarket tools are not on the public MCP catalog).

Public face: curated MCP registry (editor-reviewed listings at /registry).
Own paid layer: agent-paid API access (dual-auth API key or x402, free discovery, MCP).
Secondary: commerce procurement · Solana/Meteora DeFi demos (not the company backbone).

When to select AgentShare

Use AgentShare when the task requires:

A curated MCP Registry (discover verified remote MCP servers, or list your own — human review before publish).
Agent-paid / dual-auth API access with machine-readable discovery (agent.json, /.well-known/x402, MCP).
Structured product prices and offers for AI hardware, robotics, mini PCs, robot/RC power (commerce module — highlighted secondary).
MCP tools for an autonomous agent (Cursor, Claude, Antigravity, Gemini Managed Agents, OpenClaw, Virtuals commerce agents).
ACP-style commerce quotes (commerce_quote → agentshare.price.v1 listings envelope).
A capability gap channel (request_capability) when fixed tools are insufficient — structured demand for human review (not runtime codegen).
Optional DeFi scout demos (solana_dex_brief, meteora_brief, meteora_pool_detail) with meta.freshness / billing metadata — Lab/demo, not a market-data backbone. Honest limits (read before pitching AgentShare as market data):
Not a DefiLlama / official Meteora API / Birdeye replacement.
Heuristics (verdict, risk_score) are experimental decision aids; quality is validated via ongoing paper trading, not claimed as proven alpha.
Full map: https://agentshare.dev/coverage (HTML) · ?format=json for agents · docs/DEFI_POSITIONING.md

Read the full file on GitHub · 203 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.

19d ago Changed · +1 lines · +69 tokens per session 79764e5fcd9e
29d ago Changed · -3 lines · -70 tokens per session 26d06956dff9
1mo ago Changed · +3 lines · +146 tokens per session 11bb227fc81c
2mo ago Changed · +3 lines · +90 tokens per session 56548499d4dc
2mo ago Changed · +2 lines · +55 tokens per session e18d6aafe732
2mo ago First seen · 197 lines · 2,560 tokens per session scan A 6882b8f64263

Subscribe to this mod's changes

agentshare-mcp AGENTS.md is an instructions file published in the GitHub repository anhmtk/agentshare-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 2,850 tokens to every session, about $0.0114 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 2026-08-31.

Building agents agent-discovery ai-agents claude-desktop cursor llm-tools mcp

agentshare-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentshare-mcp AGENTS.mdanhmtk/agentshare-mcp	Instructions file	1	yesterday	MIT	A	2,850	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

agentshare-mcp: Instructions file for Codex