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.
npx agentmods add commands/omermaksutii/rugproof/audit-multi-chaingit clone --depth 1 https://github.com/omermaksutii/RugProofWrote 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.
[](https://agentmods.dev/commands/omermaksutii/rugproof/audit-multi-chain)<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- 6d ago First seen · 66 lines · 37 tokens per session scan A 7aea3df9ec00
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.
Other commands, from other repositories
krait-fuzz
Run an invariant-based fuzzing campaign: Understand → Extract Invariants → Generate Foundry Tests → Run & Fix Iteratively → Report.
krait-poc
Write and run a valid Foundry proof-of-concept that proves (or disproves) a Solidity exploit by asserting the actual harm on a forked chain or against local source.
krait-quick
Run a streamlined audit: Recon → Detection → Verification → Report. Skips state inconsistency analysis and cross-feed iteration for speed.
verify-e2e-flow
Verify that the E2E scripts for the specified chain follow the documented transaction flow.
watch-wallet
Watch Wallet operates online and manages public keys only. It creates unsigned transactions, sends signed transactions, and monitors transaction status.
keygen-wallet
Keygen Wallet operates offline as a cold wallet. It generates keys, creates multisig addresses, and provides the first signature for multisig transactions.