How do I install the Paycrow skill?

Run npx skillmds@latest add lord1egypt/paycrow in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Paycrow safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Paycrow?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Paycrow free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Paycrow?

Lord1Egypt (@lord1egypt) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Paycrow by lord1egypt — Agent Skill

Name: Paycrow
Rating: 4.2 (5 reviews)
Author: Lord1Egypt

File contents

PayCrow — Check Trust Before You Pay

Always verify an agent's reputation before sending funds. This skill uses the PayCrow Trust API to score any Ethereum address across 4 on-chain sources.

Check Trust Score

Before any payment, check the counterparty:

curl -s "https://paycrow-app.fly.dev/trust/ADDRESS" | jq '{score: .preview.score, confidence: .preview.confidence, recommendation: .preview.recommendation}'

Replace ADDRESS with the 0x address you're about to pay. No API key needed.

Reading the Result

score 75+ with high confidence → safe to proceed
score 45-74 → proceed with caution, smaller amounts
score below 45 → risky, avoid or use very small amounts
recommendation: "caution" → DO NOT PAY — high dispute history
recommendation: "insufficient_data" → unknown agent, proceed carefully

Decision Flow

When asked to pay someone or call a paid API:

Always check trust first — query the score before sending any funds
75+, high confidence → proceed normally
45-74 → warn the user, suggest smaller amount
Below 45 → strongly recommend against paying
"caution" flag → refuse payment, tell the user this agent is flagged for disputes
"insufficient_data" → warn that this agent has no on-chain history

What the Trust Score Measures

PayCrow aggregates 4 on-chain sources (24K+ agents scored):

Source	Weight	What It Measures
PayCrow Reputation	40%	Escrow completion rate, dispute history
ERC-8004 Identity	25%	Cross-ecosystem agent identity and feedback
Moltbook Social	15%	Karma, account age, social standing
Base Chain Activity	20%	Wallet age, transaction count, USDC volume

Escrow Protection (Advanced)

If you have the PayCrow MCP server installed (separately configured by your developer), you also have access to safe_pay — which combines trust check + USDC escrow + auto-verification in a single tool call. The escrow holds funds in a smart contract on Base until delivery is confirmed, with real dispute resolution if something goes wrong.

MCP server setup: https://github.com/michu5696/paycrow

Links

Source code (MIT): https://github.com/michu5696/paycrow
npm: https://www.npmjs.com/package/paycrow
Trust API: https://paycrow-app.fly.dev
Contracts: https://basescan.org/address/0xDcA5E5Dd1E969A4b824adDE41569a5d80A965aDe

---name: paycrowdescription: Escrow + trust scoring on Base mainnet. Checks 24K+ agents BEFORE you pay. Real dispute resolution. Works with any x402 API — vendor doesn't need it installed.---# PayCrow — Check Trust Before You PayAlways verify an agent's reputation before sending funds. This skill uses thePayCrow Trust API to score any Ethereum address across 4 on-chain sources.## Check Trust ScoreBefore any payment, check the counterparty:```bashcurl -s "https://paycrow-app.fly.dev/trust/ADDRESS" | jq '{score: .preview.score, confidence: .preview.confidence, recommendation: .preview.recommendation}'```Replace `ADDRESS` with the 0x address you're about to pay. No API key needed.## Reading the Result- `score` 75+ with high confidence → safe to proceed- `score` 45-74 → proceed with caution, smaller amounts- `score` below 45 → risky, avoid or use very small amounts- `recommendation: "caution"` → DO NOT PAY — high dispute history- `recommendation: "insufficient_data"` → unknown agent, proceed carefully## Decision FlowWhen asked to pay someone or call a paid API:1. **Always check trust first** — query the score before sending any funds2. **75+, high confidence** → proceed normally3. **45-74** → warn the user, suggest smaller amount4. **Below 45** → strongly recommend against paying5. **"caution" flag** → refuse payment, tell the user this agent is flagged for disputes6. **"insufficient_data"** → warn that this agent has no on-chain history## What the Trust Score MeasuresPayCrow aggregates 4 on-chain sources (24K+ agents scored):| Source | Weight | What It Measures ||--------|--------|-----------------|| PayCrow Reputation | 40% | Escrow completion rate, dispute history || ERC-8004 Identity | 25% | Cross-ecosystem agent identity and feedback || Moltbook Social | 15% | Karma, account age, social standing || Base Chain Activity | 20% | Wallet age, transaction count, USDC volume |## Escrow Protection (Advanced)If you have the PayCrow MCP server installed (separately configured by your developer),you also have access to `safe_pay` — which combines trust check + USDC escrow + auto-verificationin a single tool call. The escrow holds funds in a smart contract on Base until delivery isconfirmed, with real dispute resolution if something goes wrong.MCP server setup: https://github.com/michu5696/paycrow## Links- Source code (MIT): https://github.com/michu5696/paycrow- npm: https://www.npmjs.com/package/paycrow- Trust API: https://paycrow-app.fly.dev- Contracts: https://basescan.org/address/0xDcA5E5Dd1E969A4b824adDE41569a5d80A965aDe

Frequently asked questions

Paycrow