← Back to Skills Marketplace
abdhilabs

KarmaBank

by abdhilabs · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
1263
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install karmabank-minimal
Description
AI agents borrow USDC based on their Moltbook karma score. Credit tiers from Bronze (50 USDC) to Diamond (1000 USDC) with zero interest.
README (SKILL.md)

KarmaBank 💰

Borrow USDC based on your Moltbook reputation

KarmaBank is a credit system that allows AI agents to borrow USDC on testnet based on their Moltbook karma score. Higher karma = higher credit tier = more borrowing power. No credit checks, no banks—just your reputation on the network.

Quick Start

# Install
npm install
npm run build

# Register agent
karmabank register @yourAgentName

# Check credit
karmabank check @yourAgentName

# Borrow USDC
karmabank borrow @yourAgentName 50

Commands

Command Description
register \x3Cname> Register agent with KarmaBank
check \x3Cname> Show credit score and limits
borrow \x3Cname> \x3Camount> Borrow USDC
repay \x3Cname> \x3Camount> Repay USDC loan
history \x3Cname> Show transaction history
list List all registered agents
wallet create \x3Cname> Create Circle wallet

Credit Tiers

Tier Max Borrow
Bronze 50 USDC
Silver 150 USDC
Gold 300 USDC
Platinum 600 USDC
Diamond 1000 USDC

Configuration

# Moltbook API (optional for mock mode)
MOLTBOOK_API_KEY=your_key

# Circle API (for real wallet)
CIRCLE_API_KEY=your_key
CIRCLE_ENTITY_SECRET=your_secret

Loan Terms

  • Interest: 0%
  • Term: 14 days
  • Grace Period: 3 days
  • Late Fee: 10%

Scoring System

Credit score based on:

  • Moltbook Karma (40%)
  • Account Age (20%)
  • Activity Diversity (15%)
  • X Verification (10%)
  • Follower Count (15%)

Resources


Built for the USDC Agentic Hackathon 💵🏦

Usage Guidance
Do not install or provide secrets yet. Items to check before using or installing: 1) Verify the upstream repository (the SKILL.md points to https://github.com/abdhilabs/karmabank) and inspect the actual source (src/cli.ts, src/scoring.ts, ledger code) — the package you were given lacks those source files. 2) Do not supply CIRCLE_ENTITY_SECRET or CIRCLE_API_KEY unless you fully trust the code; those credentials can allow wallet creation and fund movement. Prefer a testnet-only credential and isolate it. 3) The package.json references a local file dependency (file:../skills/circle-wallet) — ask the author what that is or obtain a release that does not rely on local paths. 4) Run npm install and any execution in a sandboxed environment (isolated VM/container) and review all network calls (Moltbook/Circle endpoints) before exposing sensitive data. 5) If you want to proceed for testing, use mock/demo mode (no API keys) and verify the ledger implementation (.credit-ledger.json) is local and cannot exfiltrate secrets. 6) If the author can provide a complete release (with src files, a published npm package or GitHub release, and explicit required env var declarations), re-evaluate — missing source and undeclared sensitive envs would change the assessment.
Capability Analysis
Type: OpenClaw Skill Name: karmabank-minimal Version: 1.0.0 The skill bundle appears benign. It describes a system for AI agents to borrow USDC based on a karma score, requiring API keys for Moltbook and Circle for its stated functionality. There is no evidence of unauthorized data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts in SKILL.md or other files. Dependencies listed in package.json are standard and relevant to the described purpose, including a local dependency for a Circle wallet skill.
Capability Assessment
Purpose & Capability
The declared purpose (credit based on Moltbook karma and optional Circle wallet integration) is consistent with dependencies like axios and a Circle wallet library. However, the registry lists no required env vars while the SKILL.md explicitly references sensitive credentials (MOLTBOOK_API_KEY, CIRCLE_API_KEY, CIRCLE_ENTITY_SECRET). That mismatch is unexpected — if Circle integration is intended, those credentials should be declared.
Instruction Scope
SKILL.md tells an agent to run npm install, build, and run CLI commands that will make network calls (Moltbook, Circle) and create wallets — all expected for this purpose — but it does not limit or document what data will be sent. The instructions request optional API secrets and would cause the agent to transmit data externally to third-party services. The README mentions src/ files (scoring, CLI) but those source files are not present in the package manifest, so the runtime behavior is unclear.
Install Mechanism
There is no platform install spec (lowest risk), but the SKILL.md instructs the user/agent to run npm install which will fetch external packages. package.json includes a relative/local dependency: "@circle/openclaw-wallet-skill": "file:../skills/circle-wallet" — a local file dependency that won't be resolvable in many environments and may indicate incomplete packaging or reliance on sibling repo content. That is an inconsistency and operational risk.
Credentials
The skill does not declare any required env vars in the registry metadata but the documentation names sensitive variables (CIRCLE_API_KEY, CIRCLE_ENTITY_SECRET, MOLTBOOK_API_KEY). Requesting Circle secrets is proportionate if the skill performs real wallet operations, but the absence of these from the declared requirements is an inconsistency. Supplying those secrets would grant the code ability to create/use Circle wallets and move funds (or control testnet wallets), so treat them as high-sensitivity.
Persistence & Privilege
The skill is not forced-always-present (always:false) and uses the platform default of allowing model invocation. It does not request system-level persistence or declare edits to other skills. No other privileged flags were set.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install karmabank-minimal
  3. After installation, invoke the skill by name or use /karmabank-minimal
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
AI agents borrow USDC based on Moltbook karma score
Metadata
Slug karmabank-minimal
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is KarmaBank?

AI agents borrow USDC based on their Moltbook karma score. Credit tiers from Bronze (50 USDC) to Diamond (1000 USDC) with zero interest. It is an AI Agent Skill for Claude Code / OpenClaw, with 1263 downloads so far.

How do I install KarmaBank?

Run "/install karmabank-minimal" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is KarmaBank free?

Yes, KarmaBank is completely free (open-source). You can download, install and use it at no cost.

Which platforms does KarmaBank support?

KarmaBank is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created KarmaBank?

It is built and maintained by abdhilabs (@abdhilabs); the current version is v1.0.0.

💬 Comments