xbird-acp

xbird-acp is a skill for Claude Code from checkra1neth/xbird-skill. It costs 64 tokens per session (1,035 once invoked), scanned A, original, MIT.

A skill for accessing Twitter/X data through Virtuals Protocol, an agent-to-agent marketplace and communication system. It uses encrypted credentials and requires setup details such as API, wallet, and Twitter session credentials.

In plain words
What is it for?
Use it when an agent operating through Virtuals Protocol needs Twitter/X data, encrypted credential exchange, or agent-to-agent commerce.
Why use it?
It keeps the supplied Twitter credentials encrypted during the protocol flow and supports access through the specified marketplace service.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the xbird plugin — 4 skills shipped together

Good fit Use it when an agent operating through Virtuals Protocol needs Twitter/X data, encrypted credential exchange, or agent-to-agent commerce.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/checkra1neth/xbird-skill/xbird-acp
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 checkra1neth/xbird-skill --skill xbird-acp
Clone the repo
git clone --depth 1 https://github.com/checkra1neth/xbird-skill

Made for: Claude Code.

Or install xbird, the plugin that ships this one along with the rest of its 4 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 xbird-acp

README.md
[![agentmods](https://agentmods.dev/badge/skills/checkra1neth/xbird-skill/xbird-acp/github.svg)](https://agentmods.dev/skills/checkra1neth/xbird-skill/xbird-acp)
Your own site
<a href="https://agentmods.dev/skills/checkra1neth/xbird-skill/xbird-acp"><img src="https://agentmods.dev/badge/skills/checkra1neth/xbird-skill/xbird-acp/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 xbird-acp

Your own site · 80×15
<a href="https://agentmods.dev/skills/checkra1neth/xbird-skill/xbird-acp"><img src="https://agentmods.dev/badge/skills/checkra1neth/xbird-skill/xbird-acp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,035 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 $0.00064 $0.01035
Opus 5 $0.00032 $0.00517
Sonnet 5 $0.00013 $0.00207
Haiku 4.5 $0.00006 $0.00103

Measured 10d ago against content hash ce56ae33d56e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

xbird-acp 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 10d 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.

skills/xbird-acp/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

xbird ACP (Agent Commerce Protocol)

Access Twitter/X data through Virtuals Protocol agent-to-agent commerce. Credentials are ECDH-encrypted client-side — even the protocol relay cannot read them.

When to Use

  • Agent operating on Virtuals Protocol marketplace
  • Need E2E encrypted credential protection (ECDH P-256 + AES-256-GCM)
  • Agent-to-agent commerce with on-chain escrow

Don't use when: Running inside Claude Code / Cursor (use MCP instead), or making direct HTTP calls (use REST x402 instead).

Prerequisites

  1. Virtuals Protocol API key (buyer key) — obtain via acp setup or from config.json LITE_AGENT_API_KEY
  2. xbird provider wallet address — the wallet address of the xbird agent on Virtuals marketplace
  3. Twitter credentialsauth_token and ct0 cookies from an authenticated Twitter session

API Endpoints

Endpoint URL
Virtuals REST API https://claw-api.virtuals.io
Virtuals Socket.io https://acpx.virtuals.io
xbird TEE attestation https://xbirdapi.up.railway.app/tee/attestation

How It Works

  1. Fetch server attestation + ECDH key exchange (see encryption-flow.md)
  2. Encrypt credentials with AES-256-GCM using derived shared key
  3. Create ACP job via Virtuals REST API with encryptedCredentials
  4. Poll for results (see polling.md)

Available Offerings

Offering name: twitter_search

Method Params Description
search { query: string, count?: number, cursor?: string } Search tweets. Default count: 20.
getMentions { handle: string, count?: number } Get mentions for a handle.

Complete Example

import {
  generateKeyPair, exportPublicKey, importPublicKey, deriveSharedKey, encrypt,
} from "./acp/tee/crypto.ts";

const SERVER = "https://xbirdapi.up.railway.app";
const ACP_API = "https://claw-api.virtuals.io";

// 1. Attestation + ECDH
const att = await fetch(`${SERVER}/tee/attestation`).then(r => r.json());
const clientKP = await generateKeyPair();
const clientPub = await exportPublicKey(clientKP.publicKey);
const sharedKey = await deriveSharedKey(clientKP.privateKey, await importPublicKey(att.publicKey));
const { iv, ciphertext } = await encrypt(sharedKey, JSON.stringify({ authToken, ct0 }));

// 2. Create job — serviceRequirements MUST be a plain object
const res = await fetch(`${ACP_API}/acp/jobs`, {
  method: "POST",
  headers: { "Content-Type": "application/json", "x-api-key": apiKey },
  body: JSON.stringify({
    providerWalletAddress: providerWallet,
    jobOfferingName: "twitter_search",
    serviceRequirements: {
      method: "search",
      params: { query: "AI agents", count: 20 },
      encryptedCredentials: { ephemeralPublicKey: clientPub, iv, ciphertext },
    },
  }),
});
const jobId = (await res.json())?.data?.jobId;

// 3. Poll (see polling.md for full implementation)

Read the full file on GitHub · 97 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 97 lines · 64 tokens per session scan A ce56ae33d56e

Subscribe to this mod's changes

xbird-acp is a skill published in the GitHub repository checkra1neth/xbird-skill (15 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,035 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

signature-replay

Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.

PurpleAILAB/Decepticon · 31 tokens

official-sui-skills

Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…

MystenLabs/sui · 116 tokens

crypto-market-rank

Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…

tradecatlabs/tradecat-public · 85 tokens

trading-signal

Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…

tradecatlabs/tradecat-public · 64 tokens

bridge

Cross-chain token transfers using Wormhole and CCTP.

alsk1992/CloddsBot · 13 tokens

onchainkit

Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.

alsk1992/CloddsBot · 24 tokens