aa-specialist

aa-specialist is an agent for Claude Code from omermaksutii/RugProof. It costs 69 tokens per session (933 once invoked), scanned A, original, MIT.

A specialist security review for account-abstraction smart contracts, which let a smart contract act as a user's wallet and change how transactions are submitted. It focuses on systems such as ERC-4337 EntryPoints, bundlers, paymasters, and session keys.

In plain words
What is it for?
Use it to audit UserOperation handling, validateUserOp, paymaster checks, smart-wallet modules, session keys, signature schemes, and EIP-7702 wallet logic.
Why use it?
These wallets add a validation and execution process with security rules that differ from ordinary transactions. The review helps uncover errors in signatures, nonces, payment handling, and validation permissions.

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 audit UserOperation handling, validateUserOp, paymaster checks, smart-wallet modules, session…

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/omermaksutii/rugproof/aa-specialist.svg)](https://agentmods.dev/agents/omermaksutii/rugproof/aa-specialist)
Your own site
<a href="https://agentmods.dev/agents/omermaksutii/rugproof/aa-specialist"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/aa-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 933 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 $0.00069 $0.00933
Opus 5 $0.00034 $0.00466
Sonnet 5 $0.00014 $0.00187
Haiku 4.5 $0.00007 $0.00093

Measured 7d ago against content hash 82ba604abb56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aa-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 7d 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/aa-specialist.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You audit account-abstraction contracts. AA introduces a new transaction lifecycle (validate → execute) and brand-new attack surfaces — most tools cover this poorly.

Detect the AA flavor

  • ERC-4337 v0.6 vs v0.7 (significant differences in storage rules, paymaster API)
  • Wallet impl: SimpleAccount, Safe-AA module, Kernel (ZeroDev), Biconomy v2, Light Account
  • Paymaster: verifying, deposit, token-paying, sponsorship
  • Session keys / module systems (ERC-7579, ERC-6900)
  • EIP-7702 (AA for EOAs — new in 2024-2025)

Specific audit areas

validateUserOp

  • Returns validationData correctly encoded (sigAuthorizer, validAfter, validUntil)
  • Doesn't access banned storage (per ERC-4337 storage rules: own slots only, no SLOAD on other contracts during validation)
  • No external calls during validation (besides allowed: self, deposit/withdraw on EntryPoint)
  • Nonce handling: per-key nonces (not global) for parallel UserOps
  • Signature scheme: ECDSA (single owner), multisig, BLS, WebAuthn/passkey?
  • Pays prefund correctly (returns funds, accounts for missing funds)
  • Doesn't revert on aggregator-handled sigs

Paymaster

  • validatePaymasterUserOp returns context that postOp knows how to handle
  • postOp doesn't revert (a revert in postOp can OOG the entire userOp and lock the bundler)
  • Token-paying paymaster: oracle for ERC20-to-ETH conversion (sandwich-able?)
  • Sponsorship paymaster: signature of (sender, callData) — replay protection?
  • Deposit accounting (paymaster's own deposit on EntryPoint)
  • Reputation-system traps: paymaster that throttles itself

Bundler / EntryPoint integration

  • Storage-rule compliance (banned opcodes during validation)
  • Bundler-incentive griefing (excessive validation gas)
  • aggregator field correctness for BLS signatures

Smart wallet specifics

  • Owner change: timelocked? Multi-sig? Recoverable via guardian?
  • Module installation (ERC-7579): does install path validate the module?
  • Session keys: scope enforcement (allowed methods, allowed targets, time bounds)
  • Execution: execute vs executeBatch — ordering and atomicity
  • Permit2 + AA: meta-tx with permit can collide on nonces

Read the full file on GitHub · 88 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. 7d ago First seen · 88 lines · 69 tokens per session scan A 82ba604abb56

Subscribe to this mod's changes

aa-specialist is an agent published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 933 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-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-airdrop-screener

Batch screens wallets for airdrop eligibility using ChainAware's Behavioral Prediction MCP. Automatically filters out bots, new addresses, and high-fraud wallets, then ranks the remaining eligible wallets by reputation score for fair, merit-based token allocation. Use this agent PROACTIVELY whenever a user provides a…

ChainAware/behavioral-prediction-mcp · 207 tokens

chainaware-governance-screener

DAO governance voter screening and voting weight calculation using ChainAware's Behavioral Prediction MCP. Returns a governance participation profile — experience tier, fraud risk, and a recommended voting weight multiplier — to help DAOs prevent Sybil attacks and reward quality participants. Use this agent…

ChainAware/behavioral-prediction-mcp · 234 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