Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Demerzels-lab/elsamultiskillagent --skill agent-credit-systemgit clone --depth 1 https://github.com/Demerzels-lab/elsamultiskillagentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/agent-credit-system)<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/agent-credit-system"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/agent-credit-system/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/agent-credit-system"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/agent-credit-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.03409 |
| Opus 5 | $0.00020 | $0.01705 |
| Sonnet 5 | $0.00008 | $0.00682 |
| Haiku 4.5 | $0.00004 | $0.00341 |
Grade A, and why
karmabank scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- karmabank — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
Credit Tiers:
- 🥉 Bronze: 1–20 karma → 50 USDC max
- 🥈 Silver: 21–40 karma → 150 USDC max
- 🥇 Gold: 41–60 karma → 300 USDC max
- 💎 Platinum: 61–80 karma → 600 USDC max
- 👑 Diamond: 81–100 karma → 1000 USDC max
Loan Terms: 0% interest, 14-day term
Installation
Option 1: Install from ClawHub
clawhub install karmabank
cd ~/.openclaw/workspace/skills/karmabank
npm install
Option 2: Install from Source
git clone https://github.com/openclaw/agent-credit-system.git
cd agent-credit-system
npm install
npm run build
Create CLI Symlink
npm link
Prerequisites
KarmaBank has two roles:
1. KarmaBank Admin (Lender) - Runs the Service
The admin manages the USDC lending pool and needs:
-
Moltbook API Key (Optional)
- Used to verify agent identities
- Can use mock mode for demo
-
Circle API Key & Entity Secret
- Required for real wallet integration
- Used to create and manage the pool wallet
- Get from https://console.circle.com
- This is needed to fund and manage the lending pool
Note: The pool wallet holds USDC that agents can borrow. The admin funds this wallet with testnet USDC.
2. Agents (Borrowers) - Use the Service
Agents only need:
- Moltbook Account
- Register at https://moltbook.com
- Get your API key from your agent profile
- Active karma determines your credit tier
- No Circle API key needed - you receive borrowed USDC to your own wallet
How it works: Agents borrow USDC from the KarmaBank pool. The admin manages the pool. Agents don't need Circle credentials—they just need a Moltbook account and a wallet address to receive funds.
What ships with it
57 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _meta.json 299 B
- ARCHITECTURE.md 4.2 KB
- data/agents.json 1005 B
- data/config.json 140 B
- data/loans.json 17 B
- DEMO.md 12 KB
- jest.config.cjs 407 B runs code
- package-lock.json 176 KB
- package.json 1.1 KB
- README.md 3.9 KB
- scripts/circle-entity-secret.js 2.8 KB runs code
- scripts/circle-entity-secret.ts 3.0 KB runs code
- scripts/create-wallet-set.js 1.1 KB runs code
- scripts/create-with-ciphertext.js 1.7 KB runs code
- scripts/detailed-test.js 886 B runs code
- scripts/generate-circle-secret.ts 2.8 KB runs code
- scripts/generate-circle.ts 1.5 KB runs code
- scripts/generate-entity.ts 1.6 KB runs code
- scripts/generate-entity2.ts 1.6 KB runs code
- scripts/generate-secret-simple.ts 1.5 KB runs code
- scripts/register-ciphertext.js 1.1 KB runs code
- scripts/register-direct.js 755 B runs code
- scripts/simple-test.js 762 B runs code
- scripts/test-circle-sdk.js 1.6 KB runs code
- scripts/test-sdk-config.js 776 B runs code
- src/adapters/circle.test.ts 4.5 KB runs code
- src/adapters/circle.ts 6.3 KB runs code
- src/adapters/moltbook.test.ts 2.5 KB runs code
- src/adapters/moltbook.ts 6.7 KB runs code
- src/cli-simple.ts 4.3 KB runs code
- src/cli.ts 1.7 KB runs code
- src/cli/adapters/moltbook.ts 2.3 KB runs code
- src/cli/commands/borrow.ts 3.6 KB runs code
- src/cli/commands/check.ts 2.2 KB runs code
- src/cli/commands/history.ts 1.6 KB runs code
- src/cli/commands/list.ts 1.4 KB runs code
- src/cli/commands/register.ts 1.6 KB runs code
- src/cli/commands/repay.ts 3.1 KB runs code
- src/cli/commands/wallet.ts 2.6 KB runs code
- src/cli/help.ts 3.5 KB runs code
- src/cli/main.ts 1.3 KB runs code
- src/cli/services/ledger.ts 4.5 KB runs code
- src/data/mockData.ts 8.2 KB runs code
- src/data/storage.ts 5.8 KB runs code
- src/models/agent.ts 8.7 KB runs code
- src/models/loan.ts 11 KB runs code
- src/scoring.test.ts 19 KB runs code
- src/scoring.ts 15 KB runs code
- src/services/credit.ts 12 KB runs code
- src/services/ledger.ts 13 KB runs code
- src/types.ts 6.5 KB runs code
- SUBMISSION.md 2.4 KB
- test-skill.sh 525 B runs code
- tests/cli.test.ts 1.2 KB runs code
- tests/ledger.test.ts 6.8 KB runs code
- TODO.md 8.8 KB
- tsconfig.json 742 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 571 lines · 40 tokens per session scan A 19ec5b691611
karmabank is a skill published in the GitHub repository Demerzels-lab/elsamultiskillagent (10 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 3,409 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…