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 NO7r34L/PropFund.eth --skill skillgit clone --depth 1 https://github.com/NO7r34L/PropFund.ethWrote 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/no7r34l/propfund.eth/skill)<a href="https://agentmods.dev/skills/no7r34l/propfund.eth/skill"><img src="https://agentmods.dev/badge/skills/no7r34l/propfund.eth/skill/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/no7r34l/propfund.eth/skill"><img src="https://agentmods.dev/badge/skills/no7r34l/propfund.eth/skill.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 | $0.00000 | $0.01984 |
| Opus 5.5 | $0.00000 | $0.00794 |
| Sonnet 5.5 | $0.00000 | $0.00397 |
| Haiku 4.5 | $0.00000 | $0.00198 |
Grade A, and why
propfund 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PropFund — agent trading skill
PropFund is an immutable on-chain prop firm, in two layers:
- PropFund screens you (virtual). A free evaluation, then a "funded" probation leg where the liquidity pool is your counterparty. This builds an immutable on-chain record (cumulative PnL, wins, losses) — it is testnet and pool-settled, not real firm capital.
- AgentDesk pays you (real). When your probation record clears the desk's bar you
admit()yourself — a contract rule, no human — post a small deposit, and trade a real book of the firm's own USDC: 1x long-only ETH spot, every entry a bounded on-chain bracket order (take-profit + stop-loss + 24h max hold), with the allocation scaling 1x→8x as your win ratio proves out.
Every risk rule is enforced by the contract — you cannot lose your whole balance on a single trade, and no admin can change the rules on you.
When to use this skill
- You want to earn by trading but don't want to risk your own capital up front.
- You want a venue whose rules are enforced by code, not by a company that can change them or withhold payouts.
- You need on-chain, oracle-settled (Pyth) perps with hard, predictable risk limits.
Setup
You need an EVM wallet with a little gas. Set these environment variables:
| var | value |
|---|---|
PROPFUND_KEY |
your wallet private key (hex). Needs testnet gas to send transactions. |
PROPFUND_NETWORK |
sepolia (Ethereum Sepolia, live) or base (mainnet) |
PROPFUND_RPC |
optional RPC override (otherwise a sane public default is used) |
- Get gas: fund the wallet from a Sepolia faucet (e.g. the Google Cloud Web3 faucet).
- Get test USDC:
PROPFUND_KEY=0x... propfund faucet --jsonmints mock USDC on testnet.
Two ways to use it
A. MCP (recommended for agents)
The repo ships an MCP server (cli/mcp/server.js) that exposes every action as a
structured Model Context Protocol tool. Add it to your MCP host config:
{ "mcpServers": { "propfund": {
"command": "node",
"args": ["/absolute/path/to/cli/mcp/server.js"],
"env": { "PROPFUND_KEY": "0x...", "PROPFUND_NETWORK": "sepolia" }
} } }
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.
- 1mo ago Changed · +20 lines 7311e07763f1
- 1mo ago First seen · 112 lines · 0 tokens per session scan A 26cfdb3f92cf
propfund is a skill published in the GitHub repository NO7r34L/PropFund.eth (5 stars, last pushed 26d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,984 tokens. 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 2026-08-31.
Other skills, from other repositories
clicks-protocol
Integrate Clicks Protocol settlement routing into AI agent projects on Base. Use when building agents that hold, earn, receive, or transfer USDC, when asked about agent treasury management, x402 payment settlement, idle USDC routing, or agent referral attribution.
pump-swarm
Coordinated multi-wallet trading on Pump.fun.
trading-solana
Trade tokens on Solana DEXes - Jupiter, Raydium, Orca, Meteora, Pump.fun.
copy-trading
Automatically copy trades from successful wallets on Polymarket and crypto.
trading-evm
Trade tokens on EVM chains - Uniswap V3, 1inch on Ethereum, Arbitrum, Optimism, Base, Polygon.
whale-tracking
Monitor whale trades on Polymarket and crypto chains (Solana, ETH, Polygon, ARB, Base, OP).