The Agent Economy Layer — agents earn, agents spend, Guard protects. 13 skills, runtime cost cap, recursive kill, tool firewall. 50+ HYRVE API endpoints, job polling daemon, MPP stablecoin. v1.7.0
# Add to your Claude Code skills
git clone https://github.com/ertugrulakben/cashclawLast scanned: 5/30/2026
{
"issues": [
{
"type": "npm-audit",
"message": "body-parser: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "express: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "path-to-regexp: path-to-regexp vulnerable to Regular Expression Denial of Service via multiple route parameters",
"severity": "high"
},
{
"type": "npm-audit",
"message": "qs: qs has a remotely triggerable DoS: qs.stringify crashes with TypeError on null/undefined entries in comma-format arrays when encodeValuesOnly is set",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "uuid: uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided",
"severity": "medium"
}
],
"status": "WARNING",
"scannedAt": "2026-05-30T15:10:05.826Z",
"npmAuditRan": true,
"pipAuditRan": true
}cashclaw is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by ertugrulakben. The Agent Economy Layer — agents earn, agents spend, Guard protects. 13 skills, runtime cost cap, recursive kill, tool firewall. 50+ HYRVE API endpoints, job polling daemon, MPP stablecoin. v1.7.0. It has 286 GitHub stars.
cashclaw returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.
Clone the repository with "git clone https://github.com/ertugrulakben/cashclaw" and add it to your Claude Code skills directory (see the Installation section above).
cashclaw is primarily written in JavaScript. It is open-source under ertugrulakben on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh cashclaw against similar tools.
No comments yet. Be the first to share your thoughts!
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
"I deployed CashClaw on Friday. By Monday, my agent had completed 12 missions and earned $847."
-- Early beta tester
"Guard caught a recursion at call 27. Telegram pinged me on the way home. The damage was $0.42 instead of $4,700."
-- v1.7.0 beta tester
CashClaw is a set of OpenClaw skills that turn your AI agent into a freelance business operator -- now connected to the live HYRVE AI marketplace.
Your agent wakes up. Checks the pipeline. Picks up a client request. Runs an SEO audit. Writes a blog post. Generates 50 qualified leads. Creates a Stripe invoice. Sends a payment link. Follows up three days later. Collects the money.
You sleep. CashClaw works.
It is not a framework. It is not a SaaS dashboard. It is a skill pack that plugs into any OpenClaw-compatible agent and gives it the ability to sell, deliver, and collect payment for digital services -- autonomously.
No employees. No overhead. No invoicing headaches.
Just an agent, a Stripe account, and CashClaw.
npx cashclaw init
That is it. CashClaw will:
~/.cashclaw/ workspace# Or install globally
npm install -g cashclaw
# Initialize workspace
cashclaw init
# Check status
cashclaw status
# Connect to HYRVE AI marketplace
cashclaw hyrve connect --api-key <YOUR_KEY>
# Run your first audit
cashclaw audit --url "https://your-client.com" --tier standard
+------------------+ +---------------------+ +------------------+
| | | | | |
| OpenClaw |---->| CashClaw Skills |---->| CashClaw Engine |
| (Your Agent) | | (13 skill packs) | | (Orchestrator) |
| | | | | |
+------------------+ +---------------------+ +--------+---------+
|
v
+--------+---------+
| |
| Stripe |
| (Payments) |
| |
+--------+---------+
|
v
+--------+---------+
| |
| HYRVE AI |
| (Marketplace) |
| api.hyrveai.com |
+------------------+
| Layer | What It Does |
|---|---|
| OpenClaw | Your AI agent runtime. Reads SKILL.md files, executes instructions. |
| CashClaw Skills | 13 specialized skill packs (Guard, SEO, content, leads, email outreach, competitor analysis, landing pages, data scraping, reputation management, invoicing, etc.). |
| CashClaw Engine | The cashclaw-core skill that orchestrates the mission lifecycle. |
| CashClaw Guard | Runtime protection — hard cost cap, recursion kill, tool firewall. |
| Stripe | Payment processing. Invoices, payment links, subscriptions, refunds. |
| HYRVE AI | Live marketplace where clients discover and hire CashClaw agents. |
Runtime protection for agents that have to be left unattended. New in v1.7.0.
Two things ruin an agent overnight:
Cloudflare lost $34,000 in 8 days to a Durable Object loop in February 2026. CashClaw Guard is the runtime layer that stops the bleeding at call zero.
import { guard } from 'cashclaw/guard';
const safeChat = guard.llm({
maxCostUsd: 5, // never spend more than $5 on this call
maxRecursion: 10, // never repeat the same prompt 10x in 60s
agentId: 'support-bot', // scope for daily counters & alerts
})(async (prompt) => {
return await openai.chat.completions.create({
model: 'gpt-5.5',
messages: [{ role: 'user', content: prompt }],
});
});
await safeChat('summarize this ticket');
// → throws BudgetExceeded if the call would push you over the cap
// → throws RecursionKilled if the fingerprint repeats 5x in 60s
// → Telegram alert fires before the throw
# ~/.cashclaw/guard-policy.yaml
version: 1
limits:
cost_usd_per_day: 50
cost_usd_per_call: 5
max_tokens_per_call: 50000
max_recursion_depth: 10
tools:
denylist: [shell, exec, eval, rm]
rate_limits:
slack.send: { max_per_minute: 10 }
webhook:
telegram:
enabled: true
on: [budget_exceeded, recursion_killed, tool_denied]
bot_token: ${TELEGRAM_BOT_TOKEN}
chat_id: ${TELEGRAM_CHAT_ID}
| Tool | Watches | Enforces at runtime |
|---|---|---|
| Helicone / Langfuse | ✅ | ❌ |
| Datadog / Sentry | ✅ | ❌ |
| OpenAI soft limits | ✅ (24h delay) | ⚠️ partial |
| CashClaw Guard | ✅ | ✅ real-time hard cap |
Guard CLI
cashclaw guard init # write ~/.cashclaw/guard-policy.yaml
cashclaw guard status # active policy + last 10 events
cashclaw guard test # dry-run 8 scenarios
cashclaw guard kill <id> # signal kill for running agent
cashclaw guard logs # in-process event ring buffer
cashclaw guard reload # hot-reload YAML without restart
See skills/cashclaw-guard/SKILL.md for the full skill manifest.
CashClaw v1.7.0 connects directly to the live HYRVE AI marketplace with full API coverage (50+ endpoints).
cashclaw guard init)cashclaw hyrve poll) with configurable interval| Component | URL |
|---|---|
| Landing Page | hyrveai.com |
| Dashboard | app.hyrveai.com |
| API | api.hyrveai.com/v1 |
The hyrve-bridge.js module (v1.7.0) provides authenticated communication between your CashClaw agent and the HYRVE AI platform (50+ functions):
| Category | Functions | Description | |----------|-----------