lending-specialist

lending-specialist is an agent for Claude Code from omermaksutii/RugProof. It costs 47 tokens per session (761 once invoked), scanned A, original, MIT.

A specialist for auditing lending protocols, where users deposit assets, borrow against collateral, and may be liquidated when their loans become unsafe. It covers Aave, Compound, Morpho, Silo, Euler, and custom lending systems.

In plain words
What is it for?
Use it to review oracle dependencies, decimal handling, health factors, liquidation incentives, interest-rate models, flash-loan manipulation, and lender protection.
Why use it?
It helps find errors in asset pricing, interest calculations, collateral limits, liquidations, and utilization that can cause losses or bad debt.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the rugproof plugin — 35 commands, 23 agents shipped together

Good fit Use it to review oracle dependencies, decimal handling, health factors, liquidation incentives, interest-rate models, flash-loan manipulation, and lender protection.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/omermaksutii/rugproof/lending-specialist
Install

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.

Clone the repo
git clone --depth 1 https://github.com/omermaksutii/RugProof

Made for: Claude Code.

Or install rugproof, the plugin that ships this one along with the rest of its 35 commands, 23 agents.

Wrote 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.

agentmods badge for lending-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/omermaksutii/rugproof/lending-specialist/github.svg)](https://agentmods.dev/agents/omermaksutii/rugproof/lending-specialist)
Your own site
<a href="https://agentmods.dev/agents/omermaksutii/rugproof/lending-specialist"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/lending-specialist/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.

agentmods 80×15 button for lending-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/omermaksutii/rugproof/lending-specialist"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/lending-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 761 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00761
Opus 5 $0.00023 $0.00380
Sonnet 5 $0.00009 $0.00152
Haiku 4.5 $0.00005 $0.00076

Measured 9d ago against content hash 86e2b6fe37aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

lending-specialist 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.

agents/lending-specialist.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You audit lending protocols. Lending is the highest-value target in DeFi; oracle + liquidation + utilization gaming are the canonical attack vectors.

Detect the lending type

  • Aave V3-style pooled lending with eMode
  • Compound V3 / Comet (single-borrow-asset)
  • Morpho Blue (isolated markets)
  • Silo / Euler (per-asset isolation)
  • Custom variable-rate / fixed-rate

Specific audit areas

Oracle dependency

  • Spot vs TWAP — collateral pricing must use TWAP or multi-oracle.
  • Sequencer-uptime check on L2s.
  • Decimal scaling (USDC=6dp, WETH=18dp).
  • Fallback oracle (single point of failure).
  • Oracle admin power: who can switch oracles? Timelock?

Liquidation

  • Health-factor formula precision (under/over-collateralization at edges)
  • Close-factor: full vs partial liquidation
  • Bad-debt accumulation: who absorbs (insurance fund? socialized to lenders?)
  • Liquidation incentive (bonus) — too high griefs borrowers; too low → unliquidated bad debt
  • Self-liquidation prevention
  • Liquidation MEV: front-runnable, sandwich on flash-loan
  • Oracle-flash-crash liquidation cascades

Interest rate model

  • Utilization-rate fn: can be flash-loan-manipulated in one block?
  • Kink point and second-slope cliff
  • Borrow rate compounding precision (ray math, 1e27 scale)
  • Interest accrual timing: every interaction vs once per block

Reserve management

  • Reserve factor (protocol take) — sane bounds?
  • Reserve withdrawal authority — owner only? Timelock?
  • Bridged / wrapped assets — depeg risk handled?

eMode / Correlated assets

  • eMode LTV bypass via assets that drift apart
  • Cross-eMode bridging via flash-borrow

LTV / liquidation thresholds per asset

  • LTV per asset matches actual volatility?
  • Stale params after market crash?
  • Admin can lower LTV → cascading liquidations

Borrow caps / supply caps

  • Per-asset caps enforced?
  • Total-protocol limits?
  • Caps bypassable via cross-market?

Specific attack patterns to scan for

  • Flash-loan + oracle-spot → liquidate-yourself for protocol bad debt absorption.
  • Donation to a pooled vault → manipulate interest-rate utilization across a block.
  • Insolvency via depegged stablecoin used as collateral with stale oracle.
  • "Rounding-up" liquidations that take more than the seize-ratio allows.

Read the full file on GitHub · 94 lines

Changes

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.

  1. 9d ago First seen · 94 lines · 47 tokens per session scan A 86e2b6fe37aa

Subscribe to this mod's changes

lending-specialist is an agent published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 761 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 2026-08-31.

Related

Other agents, from other repositories

chainaware-gamefi-screener

Screens wallets connecting to a Web3 game or P2E (Play-to-Earn) platform using ChainAware's Behavioral Prediction MCP. Detects bot farms, multi-account cheaters, and reward abusers, then classifies legitimate players into experience tiers for matchmaking and calculates their P2E reward eligibility. Use this agent…

ChainAware/behavioral-prediction-mcp · 247 tokens

chainaware-lead-scorer

Scores a wallet as a sales lead using ChainAware's Behavioral Prediction MCP. Returns a lead score (0–100), a lead tier (Hot / Warm / Cold / Dead), a conversion probability, and a recommended outreach angle — so sales and marketing teams know exactly which wallets to prioritise and how to approach them. Use this agent…

ChainAware/behavioral-prediction-mcp · 253 tokens

chainaware-lending-risk-assessor

Assesses borrower risk for DeFi lending by combining fraud probability, on-chain experience, and risk appetite from ChainAware's Behavioral Prediction MCP. Returns a Borrower Risk Grade (A–F), a recommended collateral ratio, and an interest rate tier — so lending protocols can price risk per wallet rather than…

ChainAware/behavioral-prediction-mcp · 249 tokens

chainaware-marketing-director

Full-cycle marketing campaign orchestrator for Web3 platforms. Takes a wallet list (or single wallet), a plain-text platform description, and a campaign goal — then orchestrates ChainAware's specialist subagents to produce a complete Marketing Campaign Brief: segmented audience, prioritized leads, whale roster…

ChainAware/behavioral-prediction-mcp · 244 tokens

chainaware-portfolio-risk-advisor

Assesses the rug pull risk and community health of a token portfolio using ChainAware's Behavioral Prediction MCP. Scans every token in the portfolio through predictiverugpull (works for all contracts on ETH, BNB, BASE, HAQQ), enriches with community rank data from tokenranksingle where available (pre-calculated index…

ChainAware/behavioral-prediction-mcp · 290 tokens

chainaware-rwa-investor-screener

Screens wallets seeking to invest in tokenized Real World Assets (RWA) using ChainAware's Behavioral Prediction MCP. Assesses AML compliance, fraud risk, on-chain experience (proxy for investor sophistication), and risk profile alignment against the RWA's risk tier — then returns an investor Suitability Tier…

ChainAware/behavioral-prediction-mcp · 318 tokens