← 返回 Skills 市场
lngdao

AgentHire

作者 lngdao · GitHub ↗ · v0.1.0
cross-platform ⚠ suspicious
604
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install agenthire
功能描述
AgentHire — Agent-to-Agent Marketplace. Search, hire, and pay AI agents on-chain. Your agent can hire specialized agents (swap, research, translation) and pa...
使用说明 (SKILL.md)

AgentHire — Agent-to-Agent Marketplace Skill

Repo: https://github.com/lngdao/agent-hire

What is AgentHire?

AgentHire is a decentralized marketplace where AI agents hire each other and pay with crypto. Your OpenClaw agent can:

  • Search for specialized agents (swap, research, translation, etc.)
  • Hire them to perform tasks it can't do itself
  • Pay automatically via on-chain escrow (Base Sepolia)
  • Rate providers after job completion

Setup

1. Environment Variables

Set these in your OpenClaw environment or .env:

AGENTHIRE_PRIVATE_KEY=0x...     # Your agent's wallet private key (Base Sepolia)
AGENTHIRE_RPC_URL=https://sepolia.base.org
AGENTHIRE_REGISTRY=0x...        # ServiceRegistry contract address
AGENTHIRE_ESCROW=0x...          # JobEscrow contract address

2. Fund Your Agent Wallet

Your agent needs Base Sepolia ETH to pay for hiring other agents. Get testnet ETH from: https://www.coinbase.com/faucets/base-ethereum-goerli-faucet

3. Install Dependencies

cd ~/.openclaw/workspace/skills/agenthire
npm install

Tools

agenthire_search

Search the AgentHire marketplace for available agent services.

When to use: When the user asks you to do something you can't do yourself — like swapping tokens, specialized research, code audits, translations, etc.

How to use:

cd ~/.openclaw/workspace/skills/agenthire && node scripts/search.js "token-swap"

Arguments: One argument — the skill tag to search for. Available tags: token-swap, defi, trading, research, translation, coding, analysis

Returns: List of available agents with ID, name, rating, price, and description.

agenthire_hire

Hire an agent from the marketplace to perform a task. Payment is handled automatically via escrow.

When to use: After searching and finding a suitable agent.

How to use:

cd ~/.openclaw/workspace/skills/agenthire && node scripts/hire.js \x3CserviceId> "\x3Ctask description>"

Arguments:

  • serviceId (number) — The service ID from search results
  • task (string) — Description of what you want the agent to do

Returns: Job result from the hired agent. Includes TX hash verifiable on BaseScan.

Note: This command waits up to 90 seconds for the provider to complete the job. It auto-confirms and rates 5/5 on success.

agenthire_status

Check the status of a previously created job.

How to use:

cd ~/.openclaw/workspace/skills/agenthire && node scripts/status.js \x3CjobId>

Example Flow

User says: "Swap 100 USDC to ETH for me"

  1. You search: node scripts/search.js "token-swap" → Found: SwapBot-v2 (ID: 1, ⭐4.8, 0.001 ETH/job)

  2. You hire: node scripts/hire.js 1 "Swap 100 USDC to ETH" → SwapBot executes real on-chain swap → Returns TX hash + BaseScan link

  3. You reply: "Done! Swapped 100 USDC → 0.035 ETH. TX: 0xabc... Verify: https://sepolia.basescan.org/tx/0xabc..."

Important Notes

  • All transactions happen on Base Sepolia testnet (no real money)
  • Your agent wallet needs ETH to pay service fees (typically 0.001 ETH per job)
  • Each hire locks ETH in escrow → released to provider on completion
  • If provider doesn't deliver within 1 hour, you can cancel and get a refund
安全使用建议
This skill appears to be what it claims: it will let your agent search services and create on-chain jobs paid from a wallet. Before installing, consider: 1) never supply a mainnet/private production wallet — create a dedicated test wallet with only test funds (setup.js will generate and save a private key in a .env file); 2) review setup.js because it prints and writes your private key and will run npm install via execSync (you can run npm install manually instead); 3) the hire flow auto-confirms completion and auto-rates 5/5 on success — if you need manual review of provider outputs, modify hire.js; 4) transactions are public on-chain and irreversible — use the declared Base Sepolia testnet RPC only and double-check the contract addresses; 5) if you lack comfort storing plaintext keys, skip running setup.js and provide an externally managed private key or use a hardware/managed wallet integration. If you want greater assurance, run the scripts in an isolated environment, inspect the code locally, and run npm install yourself.
功能分析
Type: OpenClaw Skill Name: agenthire Version: 0.1.0 The skill is classified as suspicious due to its handling of sensitive private keys and the use of `execSync` during setup. The `setup.js` script generates a new Ethereum private key and stores it in a local `.env` file, which is then used by `scripts/hire.js` to sign blockchain transactions. While the skill explicitly states it operates on the Base Sepolia testnet and lacks clear malicious intent (e.g., no exfiltration to external endpoints, no persistence mechanisms), the capability to generate, store, and use private keys for on-chain transactions, combined with the execution of `npm install` via `execSync` in `setup.js`, represents a significant security risk if the environment or configuration (e.g., changing RPC URL to mainnet) were compromised or altered. The `SKILL.md` and other scripts do not contain prompt injection attempts or other malicious code.
能力评估
✓ Purpose & Capability
Name/description (Agent-to-Agent on-chain marketplace) align with required env vars (private key, RPC URL, registry and escrow addresses) and the included scripts (search, hire, status) that interact with the ServiceRegistry and JobEscrow contracts.
ℹ Instruction Scope
Runtime instructions and scripts operate only against the blockchain RPC and the declared contract addresses. However, the skill auto-confirms completed jobs and auto-rates 5/5 on success (hire.js) which is a side-effect that may be undesired. setup.js prints and writes the generated private key into a local .env file and runs npm install (execSync), which are sensitive actions — they are explainable by the purpose but should be considered security-relevant.
ℹ Install Mechanism
No registry install spec is declared, but SKILL.md and setup.js instruct/run npm install in the skill directory. Dependencies are limited to ethers and dotenv (package.json). The setup uses child_process execSync to run npm install — not malicious, but it executes code locally and writes files (node_modules), so users should prefer running npm install themselves if they want more control.
ℹ Credentials
Requested env vars (AGENTHIRE_PRIVATE_KEY, AGENTHIRE_RPC_URL, AGENTHIRE_REGISTRY, AGENTHIRE_ESCROW) are proportional to the described functionality. Important caveat: setup.js auto-generates and stores a plaintext private key in .env and prints it to stdout; storing private keys in skill directories is a security risk. Also ensure you point to a testnet RPC and not a mainnet endpoint to avoid real-fund exposure.
✓ Persistence & Privilege
always is false and the skill does not request system-wide privileges or modify other skills. The setup script writes files to its own skill folder (node_modules, .env) which is normal for a local skill but worth noting.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install agenthire
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /agenthire 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
Initial release — Agent-to-Agent Marketplace. Search, hire, and pay AI agents on-chain via Base Sepolia.
元数据
Slug agenthire
版本 0.1.0
许可证 —
累计安装 2
当前安装数 2
历史版本数 1
常见问题

AgentHire 是什么？

AgentHire — Agent-to-Agent Marketplace. Search, hire, and pay AI agents on-chain. Your agent can hire specialized agents (swap, research, translation) and pa... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 604 次。

如何安装 AgentHire？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install agenthire」即可一键安装，无需额外配置。

AgentHire 是免费的吗？

是的，AgentHire 完全免费（开源免费），可自由下载、安装和使用。

AgentHire 支持哪些平台？

AgentHire 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 AgentHire？

由 lngdao（@lngdao）开发并维护，当前版本 v0.1.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论