audit-multi-chain

audit-multi-chain is a command for Claude Code from omermaksutii/RugProof. It costs 37 tokens per session (856 once invoked), scanned A, original, MIT.

A command that compares the live settings of one blockchain contract deployed on several networks, such as Ethereum, Arbitrum, or Base. It checks values such as owners, oracles, fees, delays, pause status, and proxy implementations.

In plain words
What is it for?
Use it to compare a contract across multiple chains and identify which network has a mismatched owner, oracle, fee, timelock, pause setting, or proxy implementation.
Why use it?
It finds configuration drift, where one deployment has different or unsafe settings from the others.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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

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.

agentmods
npx agentmods add commands/omermaksutii/rugproof/audit-multi-chain
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 audit-multi-chain

README.md
[![agentmods](https://agentmods.dev/badge/commands/omermaksutii/rugproof/audit-multi-chain.svg)](https://agentmods.dev/commands/omermaksutii/rugproof/audit-multi-chain)
Your own site
<a href="https://agentmods.dev/commands/omermaksutii/rugproof/audit-multi-chain"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/audit-multi-chain.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 856 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.00856
Opus 5 $0.00018 $0.00428
Sonnet 5 $0.00007 $0.00171
Haiku 4.5 $0.00004 $0.00086

Measured 6d ago against content hash 7aea3df9ec00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-multi-chain 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 6d 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.

commands/audit-multi-chain.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit-multi-chain — find the chain that's misconfigured

Protocols deploy the same contract to Ethereum, Arbitrum, Base, Optimism… and one chain ends up with the wrong oracle, a forgotten EOA owner, or a paused-forever flag. Configuration drift across chains is a classic, high-severity bug class. This command forks each chain and diffs the live config side by side.

Procedure

Step 1 — Parse arguments

$ARGUMENTS is <address> <chain1,chain2,...>. Split the chain list on commas. Validate each chain has an RPC / explorer entry available.

Step 2 — Pull source + config per chain

For each chain, fetch verified source and read the live state:

mcp__block-explorer__get_source(chain=<chain>, address=<address>)
mcp__anvil__fork(chain=<chain>, address=<address>)

Then read each governance-relevant parameter from the forked state (via anvil eth_call):

  • owner() / admin() / getRoleMember(DEFAULT_ADMIN_ROLE, 0)
  • oracle address (priceFeed(), oracle())
  • fee tiers (feeBps(), protocolFee())
  • timelock duration (delay(), minDelay())
  • pause state (paused())
  • proxy implementation slot (eip1967.proxy.implementation = 0x360894...bbc)
  • token allowlist membership for known tokens

Step 3 — Diff the matrix

Build a parameter × chain matrix. For each parameter, compute the modal (most common) value across chains and flag any chain that deviates. An EOA owner where other chains use a multisig, or a stale oracle, is a drift finding. Dispatch a defender review on each flagged divergence to judge whether it is intentional or a misconfiguration.

Step 4 — Output

Multi-chain config drift: 0xVault... across [ethereum, arbitrum, base]

  Parameter            ethereum          arbitrum          base              Drift
  ─────────────────────────────────────────────────────────────────────────────────
  owner                0xSafe…ab (multisig) 0xSafe…ab        0xEOA…f9 (EOA)    ⚠ base
  oracle               0xChainlink…01    0xChainlink…01    0xChainlink…01    ✓
  feeBps               30                30                50                ⚠ base
  timelock delay       172800            172800            0                 ⚠ base
  paused               false             false             true              ⚠ base
  impl (proxy)         0xImplV2…         0xImplV2…         0xImplV1…         ⚠ base (stale)

Verdict: HIGH RISK — base is misconfigured on 5/6 parameters.
  • owner is an EOA, not the multisig used elsewhere → single-key rug surface
  • timelock delay 0 → admin changes are instant
  • impl is V1 while other chains run V2 → unpatched bug may be live on base

Read the full file on GitHub · 66 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. 6d ago First seen · 66 lines · 37 tokens per session scan A 7aea3df9ec00

Subscribe to this mod's changes

audit-multi-chain is a command published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 856 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.