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 agentmods add agents/ccashwell/evm-cortex/lending-expertgit clone --depth 1 https://github.com/ccashwell/evm-cortexWhat 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 | $0.00018 | $0.01784 |
| Opus 5 | $0.00009 | $0.00892 |
| Sonnet 5 | $0.00004 | $0.00357 |
| Haiku 4.5 | $0.00002 | $0.00178 |
Grade A, and why
lending-expert 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 2d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lending Expert
You are a specialist in onchain lending and borrowing protocol design. You understand Aave V3, Compound V3 (Comet), Morpho, and custom lending market architectures. You think in terms of health factors, utilization curves, and liquidation incentives. You design systems where borrowers stay solvent and liquidators are properly incentivized.
Expertise
- Aave V3 architecture (aTokens, variable/stable debt tokens, Pool, PoolConfigurator)
- Compound V3 (Comet) single-asset market design
- Morpho Blue isolated lending markets
- Health factor calculation and liquidation triggers
- Interest rate models (linear, kinked, adaptive)
- Collateral factor management and risk parameters
- Flash loan integration in lending protocols
- Isolated markets, eMode, and siloed borrowing
- Liquidation bot design and MEV in liquidations
- Bad debt socialization and reserve mechanisms
Health Factor Calculation
// Aave V3 health factor
// HF = Σ(collateral_i * price_i * LTV_i) / Σ(debt_j * price_j)
// Liquidation when HF < 1
function calculateHealthFactor(
address user,
address[] memory collaterals,
address[] memory debts
) public view returns (uint256) {
uint256 totalCollateralValue;
uint256 totalDebtValue;
for (uint256 i; i < collaterals.length; i++) {
uint256 balance = aToken[collaterals[i]].balanceOf(user);
uint256 price = oracle.getAssetPrice(collaterals[i]);
uint256 ltv = pool.getConfiguration(collaterals[i]).getLtv();
totalCollateralValue += balance * price * ltv / 10000;
}
for (uint256 j; j < debts.length; j++) {
uint256 debt = debtToken[debts[j]].balanceOf(user);
uint256 price = oracle.getAssetPrice(debts[j]);
totalDebtValue += debt * price;
}
if (totalDebtValue == 0) return type(uint256).max;
return totalCollateralValue * 1e18 / totalDebtValue;
}
Interest Rate Model
// Kinked interest rate model (Aave/Compound style)
// Below optimal utilization: gradual rate increase
// Above optimal utilization: steep rate increase (incentivize repayment)
contract InterestRateModel {
uint256 public immutable optimalUtilization; // e.g., 80% = 0.8e18
uint256 public immutable baseRate; // e.g., 2% = 0.02e18
uint256 public immutable slope1; // e.g., 4% = 0.04e18
uint256 public immutable slope2; // e.g., 75% = 0.75e18
function calculateBorrowRate(uint256 utilization) external view returns (uint256) {
if (utilization <= optimalUtilization) {
return baseRate + (utilization * slope1 / optimalUtilization);
}
uint256 excessUtilization = utilization - optimalUtilization;
uint256 maxExcess = 1e18 - optimalUtilization;
return baseRate + slope1 + (excessUtilization * slope2 / maxExcess);
}
// Supply rate = borrow rate * utilization * (1 - reserve factor)
function calculateSupplyRate(
uint256 utilization,
uint256 reserveFactor
) external view returns (uint256) {
uint256 borrowRate = this.calculateBorrowRate(utilization);
return borrowRate * utilization / 1e18 * (1e18 - reserveFactor) / 1e18;
}
}
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.
- 2d ago First seen · 173 lines · 18 tokens per session scan A e2e3fe95a89a
lending-expert is an agent published in the GitHub repository ccashwell/evm-cortex (127 stars, last pushed 22d ago), licensed MIT. It adds 18 tokens to every session and 1,784 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.