Expert guide for autonomous Machine-to-Machine (M2M) agent settlement, dual-rail fiat & stablecoin micro-clearing, dynamic budget envelopes, and cryptographic agent invoicing / Panduan ahli settlement otonom antar-agen (M2M), kliring mikro dual-rail fiat & stablecoin, pagu anggaran dinamis, dan penagihan agen kriptografis.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
<a name="english"></a>
Connects and orchestrates with agentic-micro-economy-architect, doku-payment-gateway, doku-mcp-server, payment-gateway-expert, saas-billing, multi-agent-orchestration, formal-spec-z3-verifier, database-orm-expert, and zero-trust-secret-vault.
In multi-agent swarms where sub-agents consume paid third-party APIs, compute clusters, specialized data scraping, or delegated reasoning, agents require an autonomous, real-time clearing and settlement rail. Agentic M2M Settlement establishes production-grade financial rails for autonomous Agent-to-Agent (A2A) and Agent-to-Infrastructure (A2I) transactions. It supports Dual-Rail Clearing:
It enforces strict velocity caps, non-bypassable spending ceilings, cryptographic invoice signing, and milestone-gated critic escrow.
Activate this skill when:
[ Swarm Director Treasury ]
│
┌─────────────────┴─────────────────┐
▼ ▼
[ Fiat Settlement Rail ] [ Stablecoin Micro Rail ]
(DOKU SNAP BI QRIS / VA) (USDC via Base ERC-4337)
│ │
└─────────────────┬─────────────────┘
│
[ Escrow & Verification Vault ]
(Critic Agent + SMT Invariants)
│
▼
[ Target Worker Sub-Agent ]
maxBudget: 25.00 USD). Attempts to spend above this ceiling trigger immediate execution termination.taskId, nonce, callerAgentId, targetAgentId, itemizedCostBreakdown, and timestamp.X-EXTERNAL-ID) in PostgreSQL with unique constraint locks.import { createHmac, randomUUID } from 'node:crypto';
export interface SettlementInvoice {
invoiceId: string;
sourceAgentId: string;
workerAgentId: string;
taskId: string;
amountMinor: bigint; // In smallest currency unit (e.g. cents or IDR rupiah)
currency: 'IDR' | 'USD';
rail: 'DOKU_SNAP_BI' | 'USDC_BASE_SMART_ACCOUNT';
timestamp: string;
signature: string;
}
export interface EscrowContract {
escrowId: string;
invoice: SettlementInvoice;
maxBudgetMinor: bigint;
status: 'PENDING' | 'CRITIC_VERIFIED' | 'RELEASED' | 'REFUNDED';
criticAgentId: string;
}
export class AgentM2MSettlementEngine {
private readonly sharedSecret: string;
private readonly activeEscrows = new Map<string, EscrowContract>();
constructor(sharedSecret: string) {
if (!sharedSecret || sharedSecret.length < 32) {
throw new Error('Settlement Secret must be at least 32 characters for HMAC-SHA512 security.');
}
this.sharedSecret = sharedSecret;
}
// Generate cryptographic invoice from worker agent
public createAgentInvoice(params: {
sourceAgentId: string;
workerAgentId: string;
taskId: string;
amountMinor: bigint;
currency: 'IDR' | 'USD';
rail: 'DOKU_SNAP_BI' | 'USDC_BASE_SMART_ACCOUNT';
}): SettlementInvoice {
const invoiceId = `inv_${randomUUID()}`;
const timestamp = new Date().toISOString();
const payload = `${invoiceId}|${params.sourceAgentId}|${params.workerAgentId}|${params.taskId}|${params.amountMinor.toString()}|${params.currency}|${timestamp}`;
const signature = createHmac('sha512', this.sharedSecret)
.update(payload)
.digest('hex');
return {
invoiceId,
sourceAgentId: params.sourceAgentId,
workerAgentId: params.workerAgentId,
taskId: params.taskId,
amountMinor: params.amountMinor,
currency: params.currency,
rail: params.rail,
timestamp,
signature
};
}
// Open an escrow with strict budget envelope
public openEscrow(invoice: SettlementInvoice, maxBudgetMinor: bigint, criticAgentId: string): EscrowContract {
// 1. Verify invoice cryptographic authenticity
const payload = `${invoice.invoiceId}|${invoice.sourceAgentId}|${invoice.workerAgentId}|${invoice.taskId}|${invoice.amountMinor.toString()}|${invoice.currency}|${invoice.timestamp}`;
const expectedSignature = createHmac('sha512', this.sharedSecret)
.update(payload)
.digest('hex');
if (invoice.signature !== expectedSignature) {
throw new Error('Settlement Rejected: Cryptographic invoice signature tampering detected.');
}
// 2. Enforce strict budget envelope
if (invoice.amountMinor > maxBudgetMinor) {
throw new Error(`FinOps Gate Tripped: Invoice amount ${invoice.amountMinor} exceeds allocated ceiling ${maxBudgetMinor}.`);
}
const escrow: EscrowContract = {
escrowId: `escrow_${randomUUID()}`,
invoice,
maxBudgetMinor,
status: 'PENDING',
criticAgentId
};
this.activeEscrows.set(escrow.escrowId, escrow);
return escrow;
}
// Critic subagent verifies work quality and releases payment
public releaseSettlement(escrowId: string, criticSignature: string, qualityScore: number): { success: boolean; txHash: string } {
const escrow = this.activeEscrows.get(escrowId);
if (!escrow) {
throw new Error(`Escrow ${escrowId} not found in settlement vault.`);
}
if (escrow.status !== 'PENDING') {
throw new Error(`Escrow ${escrowId} is already in ${escrow.status} state. Double-spend prevention active.`);
}
if (qualityScore < 0.85) {
escrow.status = 'REFUNDED';
throw new Error(`Settlement Rejected: Critic evaluation score (${qualityScore}) below quality threshold 0.85. Funds refunded.`);
}
// In production, dispatch DOKU SNAP BI transfer or execute Base USDC transfer
escrow.status = 'RELEASED';
const txHash = `settlement_tx_${randomUUID().replace(/-/g, '')}`;
return { success: true, txHash };
}
}
<a name="bahasa-indonesia"></a>
Terhubung dan mengorkestrasi bersama agentic-micro-economy-architect, doku-payment-gateway, doku-mcp-server, payment-gateway-expert, saas-billing, multi-agent-orchestration, formal-spec-z3-verifier, database-orm-expert, dan zero-trust-secret-vault.
Dalam swarm multi-agen skala produksi di mana sub-agen mengonsumsi API pihak ketiga berbayar, komputasi GPU, scraping web berbayar, atau inferensi penalaran terdelegasi, agen memerlukan rel kliring dan settlement pembayaran otomatis secara real-time. Agentic M2M Settlement menyediakan infrastruktur finansial tangguh untuk transaksi Mesin-ke-Mesin (Agent-to-Agent / A2A) dan Agen-ke-Infrastruktur (A2I). Protokol ini mendukung Kliring Dual-Rail:
Protokol ini menerapkan batas kecepatan belanja (velocity caps), pagu anggaran mutlak tanpa toleransi (hard budget ceiling), penagihan kriptografis antar-agen, dan escrow berkala dengan gerbang validasi agen penilai (Critic Agent).
Aktifkan skill ini ketika:
maxBudget: Rp250.000). Upaya transaksi di atas pagu ini otomatis memicu terminasi eksekusi.taskId, nonce, callerAgentId, targetAgentId, dan rincian biaya.X-EXTERNAL-ID) pada database PostgreSQL dengan kunci pengaman atomik.まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Expert guide for automated and manual Web Accessibility (a11y) testing — axe-core, Pa11y, Playwright a11y, screen reader testing, and WCAG 2.2 Level AA/AAA compliance / Panduan ahli pengujian aksesibilitas web.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guide for intelligent model cascading and routing — complexity-scored task routing from Flash/Haiku to Sonnet/Opus/Astra, dynamic escalation with quality gates, 40-60% token cost reduction while maintaining output quality / Panduan ahli untuk kaskade dan routing model cerdas — routing tugas berbasis skor kompleksitas dari Flash/Haiku ke Sonnet/Opus/Astra, eskalasi dinamis dengan gerbang kualitas, pengurangan biaya token 40-60% dengan kualitas output terjaga.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guide for Affective Computing, emotional AI, and real-time sentiment analysis through native multimodal tokens (voice intonation and facial micro-expressions) / Panduan ahli komputasi afektif, AI emosional, dan analisis sentimen real-time melalui token multimodal native.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guide for AI-assisted coding workflows — agentic code generation, multi-agent code swarms, self-healing CI/CD, automated PR review, spec-to-code pipelines, codebase knowledge graphs, and human-in-the-loop approval gates / Panduan ahli untuk workflow pengkodean berbasis AI — generasi kode agentic, code swarm multi-agen, CI/CD self-healing, review PR otomatis, pipeline spec-to-code, knowledge graph codebase, dan gate persetujuan human-in-the-loop.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guide for long-term episodic memory integration (Mem0 v2, Letta/MemGPT, Zep v2), memory tier architecture, pgvector HNSW storage, and unified context management for autonomous AI agents / Panduan ahli untuk integrasi memori episodik jangka panjang (Mem0 v2, Letta/MemGPT, Zep v2), arsitektur tier memori, penyimpanan pgvector HNSW, dan manajemen konteks terpadu untuk agen AI otonom.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guide for designing Machine-to-Machine (M2M) micro-economies, autonomous agent wallets, and swarm budget allocation / Panduan ahli merancang ekonomi mikro antar-agen (M2M), dompet agen otonom, dan alokasi anggaran swarm.
日本語の概要は準備中です。原文の説明を表示しています。