aa

aa is a skill for Claude Code from ChainGPT-org/chaingpt-claude-skill. It costs 96 tokens per session (1,614 once invoked), scanned A, original, MIT.

A collection of tools for ERC-4337 account abstraction, a way for smart-contract wallets to send blockchain transactions through bundlers. It calculates operation hashes, formats operations, estimates gas, and checks receipts without handling wallet keys.

In plain words
What is it for?
Use it to prepare UserOperations, calculate the hash a wallet must sign, estimate their gas, and check whether they were included on-chain.
Why use it?
It removes repeated low-level formatting and bundler-connection work while keeping signing outside the tool.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the chaingpt plugin — 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server shipped together

Good fit Use it to prepare UserOperations, calculate the hash a wallet must sign, estimate their gas, and check whether they were included on-chain.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chaingpt-org/chaingpt-claude-skill/aa
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.

Any agent
npx skills add ChainGPT-org/chaingpt-claude-skill --skill aa
Clone the repo
git clone --depth 1 https://github.com/ChainGPT-org/chaingpt-claude-skill

Made for: Claude Code.

Or install chaingpt, the plugin that ships this one along with the rest of its 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/aa.svg)](https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/aa)
Your own site
<a href="https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/aa"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/aa.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,614 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 81
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 83
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00096 $0.01614
Opus 5 $0.00048 $0.00807
Sonnet 5 $0.00019 $0.00323
Haiku 4.5 $0.00010 $0.00161

Measured 8d ago against content hash 7c354de5ad09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aa 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 8d 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.

skills/aa/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ERC-4337 (Account Abstraction) skill

This skill exposes the shared primitives every ERC-4337 v0.7 smart-contract wallet needs:

Tool Purpose
chaingpt_aa_userop_hash Compute the v0.7 userOpHash the signer signs.
chaingpt_aa_pack_userop Pack a UserOp into the EntryPoint wire-format PackedUserOperation + emit the bundler-RPC JSON shape.
chaingpt_aa_estimate_userop Proxy eth_estimateUserOperationGas to an admin-supplied bundler URL.
chaingpt_aa_userop_receipt Proxy eth_getUserOperationReceipt to check if a userop was bundled and what the on-chain receipt looks like.

Custody-free invariant

The plugin never signs a UserOp and never sees a smart-account owner key or session key. The hash returned by chaingpt_aa_userop_hash is the input to the user's wallet (MetaMask, hardware wallet, viem signer, SCW session-key module). The user signs externally and places the signature into the UserOp's signature field before submitting via the bundler.

A unit test asserts the surface contract: no tool input schema may contain a parameter that matches /privatekey|ownerkey|sessionkey|mnemonic|seedphrase|signer/. Future additions that try to accept a secret will fail the build.

Foundation vs. session-key flow

ERC-4337 session keys live inside the smart-contract wallet's validator module. Every major SCW provider has its own validator with its own session-key ABI:

Provider Validator Session-key issuance
Safe + Zodiac safe-protocol-kit modules enableModule + setSessionKey
Kernel (ZeroDev) EIP-7579 modular validators installValidator
Biconomy K1Validator + sponsorship issueSessionKey
Alchemy Smart Wallet Modular Account v2 installPlugin
SimpleAccount (canonical reference) single owner — no session keys natively (none — add a session-key validator)

Picking one provider here would lock the plugin into that vendor's surface. Instead, this skill ships the shared primitives (packing, hashing, bundler-rpc) that every v0.7 SCW needs, and per-provider session-key issuance / use is queued as follow-up PRs:

Read the full file on GitHub · 108 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. 8d ago First seen · 108 lines · 0 tokens per session scan A 7c354de5ad09

Subscribe to this mod's changes

aa is a skill published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (16 stars, last pushed 9d ago), licensed MIT. It adds 96 tokens to every session and 1,614 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

analyzing-ethereum-smart-contract-vulnerabilities

Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.

mukul975/Anthropic-Cybersecurity-Skills · 49 tokens

analyzing-ethereum-smart-contract-vulnerabilities

Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.

xalgorix/xalgorix · 49 tokens

talos-action-development

Develop, modify, review, and maintain standalone Talos actions in contracts/tasks/actions, including chain guardrails, contract bindings, transaction safety, schedules, action catalogues, and Talos documentation. Use when adding an action, changing an action’s behavior or parameters, updating a Talos schedule, or…

OriginProtocol/origin-dollar · 70 tokens

web3-bug-classes

Complete reference for all 10 DeFi smart contract bug classes. Use this when hunting for specific vulnerability types, need attack patterns for accounting desync, access control, incomplete path, off-by-one, oracle manipulation, ERC4626 vaults, reentrancy, flash loans, signature replay, or proxy/upgrade bugs.

Awarexone/web3-bug-bounty-hunting-ai-skills · 72 tokens

web3-methodology-research

External research synthesis from Trail of Bits, SlowMist, ConsenSys, Immunefi, and Cyfrin. Use this for advanced audit methodology, Echidna/Medusa fuzzing setup, Slither custom detector writing, attack pattern deep dives, or the 4-phase learning roadmap.

Awarexone/web3-bug-bounty-hunting-ai-skills · 66 tokens

web3-poc-foundry

Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for learning.

Awarexone/web3-bug-bounty-hunting-ai-skills · 59 tokens