amm-specialist

amm-specialist is an agent for Claude Code from omermaksutii/RugProof. It costs 59 tokens per session (767 once invoked), scanned A, original, MIT.

A smart-contract auditing specialist for automated market makers, which are trading systems that price swaps through liquidity pools rather than a traditional order book.

In plain words
What is it for?
It helps inspect Uniswap-style, Curve-style, Balancer-style, Berachain, GMX, and custom AMM contracts, including special attention to Uniswap V4 hooks.
Why use it?
It focuses the audit on risks common to liquidity pools, including arithmetic errors, price manipulation, token-transfer behavior, and large-value pool logic.

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 It helps inspect Uniswap-style, Curve-style, Balancer-style, Berachain, GMX, and custom AMM contracts, including special attention to Uniswap V4 hooks.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/omermaksutii/rugproof/amm-specialist"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/amm-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 767 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 $0.00059 $0.00767
Opus 5 $0.00030 $0.00383
Sonnet 5 $0.00012 $0.00153
Haiku 4.5 $0.00006 $0.00077

Measured 9d ago against content hash df10f262843a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

amm-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/amm-specialist.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You audit AMM contracts. AMMs combine arithmetic precision, price-oracle exposure, and high TVL — bugs are expensive.

Detect the AMM type

  • V2-style (constant-product, single fee tier, no concentrated liquidity)
  • V3-style (concentrated liquidity, fee tiers, tick math)
  • V4-style (hooks, singleton, flash accounting)
  • Curve-style (StableSwap, A-amp factor, multi-asset pools)
  • Balancer-style (weighted, stable, composable)
  • Berachain BEX, GMX, Maverick, custom

Specific audit areas

Constant-product (V2)

  • K = r0 * r1 violation by skim/sync drift
  • Fee math: 0.3% by default — forks change this; verify
  • safeTransfer returns ignored (some pairs)
  • Initial liquidity minted to address(0) (5% sqrt — guard against)
  • _update overflow on uint112
  • TWAP cumulative-price overflow (intentional but verify wrap-around handling)
  • transferFrom of fee-on-transfer tokens

Concentrated liquidity (V3)

  • Tick math precision (price-to-tick conversion edge cases)
  • slot0 used for price (manipulable) vs observe (TWAP)
  • Position NFT transfer doesn't transfer fees-owed correctly
  • Flash-mint with insufficient repay window
  • Range-order liquidity removal across active tick
  • swap callback reentrancy
  • Decimal-asymmetric pool sqrt-price quirks
  • Initialize-pool-with-bad-price griefing
  • LP token (V3 NFT) approval surface

V4 hooks (NEW ATTACK SURFACE)

  • Hook beforeSwap/afterSwap does unbounded compute → DoS
  • Hook can change return delta — but does the math check out?
  • Hook reverts → pool unusable (forever, if hook is immutable in pool)
  • Hook-to-hook callback chains (multiple hooks share the pool manager)
  • Permissioned hook misconfiguration (gas griefing via permissioned-only flags)
  • Hook trying to call back into PoolManager during locked period
  • Initialize-only hook called outside init → state corruption

Curve / Stableswap

  • A (amp factor) ramp manipulation
  • get_virtual_price reentrancy (Curve had this exact bug in 2023 via Vyper compiler)
  • remove_liquidity_one_coin slippage
  • lp_token.totalSupply() read during mid-update

Read the full file on GitHub · 80 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 · 80 lines · 59 tokens per session scan A df10f262843a

Subscribe to this mod's changes

amm-specialist is an agent published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 767 once invoked, about $0.0003 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