Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Agent Inference Capacity Marketplace

ASecurity

Enables AI agents to interact with AISP (Agent Inference Sharing Protocol) for renting or providing DIEM API capacity. Use when working with diem-marketplace, Venice API keys, USDC escrow, listings, rentals, or when the user wants to rent inference capacity or list API keys.

19 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentstypescriptgoapibackendsecurity

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill agent-inference-capacity-marketplace --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agent Inference Capacity Marketplace?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Agent Inference Capacity Marketplace
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-agent-inference-capacity-marketplace/badge)](https://www.skillsdirectory.com/skills/rondoflow-agent-inference-capacity-marketplace)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: agent-inference-capacity-marketplace
description: "Enables AI agents to interact with AISP (Agent Inference Sharing Protocol) for renting or providing DIEM API capacity. Use when working with diem-marketplace, Venice API keys, USDC escrow, listings, rentals, or when the user wants to rent inference capacity or list API keys."
category: "AI & Agents"
author: community
version: "1.0.2"
icon: bot
---

# AISP Agent Skill

Agent Inference Sharing Protocol (AISP) lets agents rent idle DIEM/Venice API capacity via USDC escrow. Providers list capped API keys; agents fund and receive keys automatically.

## Architecture

```
Agent: fund() → Backend sees Funded event → Key released → Agent uses Venice API
Provider: list() → Agent funds → Term expires → settle() → Provider paid (99%, 1% fee)
```

## Agent Workflow (Renting)

1. **Listings** from backend: `GET /api/listings`
2. **Approve USDC** if needed (contract spends on `fund`)
3. **Fund** on-chain: `contract.fund(listingId, termDays, diemAmount)` → returns `rentalId`
4. **Get key**: `POST /api/key/{rentalId}` with signed message `diem-marketplace:get-key:{rentalId}:{timestamp}`
5. Use `apiKey` with Venice API until `expiresAt` (Unix timestamp)

### SDK (Agent)

```typescript
import { DiemAgent } from "diem-marketplace-sdk";

const agent = new DiemAgent({
  signer: wallet,
  contractAddress: "0x...",
  backendUrl: "https://diem-marketplace-backend.fly.dev",
  usdcAddress: "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
});

const listings = await agent.getListings();
const { apiKey, expiresAt } = await agent.rent(
  listings[0].listingId,
  termDays,
  ethers.parseUnits(diemAmount, 6)
);
```

## Provider Workflow (Listing)

1. **Create listing** on-chain: `contract.list(pricePerDay, termDays, diemMin, diemMax)` → `listingId`
2. **Store key** on backend: `POST /api/keys` with `{ listingId, apiKey, signature, timestamp }`
   - Message: `diem-marketplace:store-key:{listingId}:{timestamp}`
3. **Settle** when rental expires: `contract.settle(rentalId)` → provider receives 99% (1% protocol fee)

### SDK (Provider)

```typescript
import { DiemProvider } from "diem-marketplace-sdk";

const provider = new DiemProvider({
  signer: wallet,
  contractAddress: "0x...",
  backendUrl: "https://diem-marketplace-backend.fly.dev",
  usdcAddress: "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
});

const listingId = await provider.createListing({
  pricePerDay: ethers.parseUnits("0.80", 6),
  termDays: 30,
  diemMin: ethers.parseUnits("1000", 6),
  diemMax: ethers.parseUnits("4000", 6),
  apiKey: "vn-scoped-...",
});
```

## Key Paths

| Path | Purpose |
|------|---------|
| `sdk/src/agent.ts` | DiemAgent: getListings, rent, getKey, getMyRentals |
| `sdk/src/provider.ts` | DiemProvider: createListing, settle, revokeAndRefund |
| `backend/src/routes.ts` | API routes: /api/listings, /api/keys, /api/key/:id |
| `contracts/DiemMarketplace.sol` | On-chain escrow, 1% fee |

## Backend API

| Endpoint | Method | Purpose |
|----------|--------|---------|
| `/api/listings` | GET | List rentable listings |
| `/api/listings/:id` | GET | Single listing |
| `/api/keys` | POST | Provider stores API key |
| `/api/key/:rentalId` | POST | Agent retrieves key (signature required) |
| `/api/balance` | POST | Check DIEM balance for API key |
| `/api/requests` | POST | Create rental request |

## Signatures

All backend requests requiring auth use EIP-191 signing:
- `getKey`: `diem-marketplace:get-key:{rentalId}:{timestamp}`
- `storeKey`: `diem-marketplace:store-key:{listingId}:{timestamp}`
- `balance`: `apiKey` in body (no signature)

## Contract (Base)

- **Chain**: Base (8453)
- **Mainnet**: `0xeeDa7657f2018b3b71B444b7ca2D8dE91b3B08f3`
- **USDC**: `0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913`

## Security & Signing

- Use an external signer or hardware wallet; never paste raw private keys.
- Require explicit user confirmation before fund transfers or credential usage.
- Venice API keys must be scoped (inference-only), revocable, and minimal for escrow.

## Notes

- Venice API keys must be **inference-only** (not admin)
- 1% protocol fee deducted at settlement

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →