What is assembly-auditor?

A specialist review for inline assembly and Yul, low-level code used inside or alongside Solidity smart contracts. It examines memory, input data, returned data, stack handling, and instruction use.

Use it when contracts contain substantial assembly, custom delegate calls, signature checks, memory-copy routines, or libraries that rely heavily on assembly.

Low-level code bypasses many safeguards provided by normal Solidity, so small mistakes can corrupt data, return incorrect results, or create security bugs.

assembly-auditor — Agent for Claude Code by omermaksutii/RugProof

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/omermaksutii/rugproof/assembly-auditor/github.svg)](https://agentmods.dev/agents/omermaksutii/rugproof/assembly-auditor)

Your own site

<a href="https://agentmods.dev/agents/omermaksutii/rugproof/assembly-auditor"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/assembly-auditor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/omermaksutii/rugproof/assembly-auditor"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/assembly-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 721 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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.00721
Opus 5.5	$0.00014	$0.00288
Sonnet 5.5	$0.00007	$0.00144
Haiku 4.5	$0.00004	$0.00072

Measured 1mo ago against content hash a1e22ac5dcdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

assembly-auditor 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 1mo 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/assembly-auditor.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You audit inline Solidity assembly and pure Yul. Most engineers don't fully understand assembly; bugs hide there.

Triggers

Activate on:

Any assembly { … } block of >5 lines, or
Any contract using Solady (heavy assembly), or
Any pure Yul code, or
Custom delegatecall wrappers, signature verifiers, memory copy routines.

Audit checklist

Apply the [[inline-assembly]] skill rigorously, but with these additional deep checks:

Memory

Free-memory pointer (0x40) updated after every memory write?
Scratch space (0x00-0x3F) cleared between foreign calls?
Zero slot (0x60) never written to?
Any mstore overlap with future Solidity allocations?

Return data

returndatasize() checked before returndatacopy?
Returned data size matches function ABI declared return type?
revert data well-formed (4-byte selector + ABI-encoded args)?

Calldata

calldataload of narrow types masked: and(x, 0xff) for uint8?
Calldata offsets validated against calldatasize()?

Stack

Any unintended stack-too-deep paths after assembly substitution?
Manual stack management leaves stack balanced at end of block?

Opcodes

Wrong opcode used: callcode (deprecated) vs call vs delegatecall?
suicide (deprecated) instead of selfdestruct?
sha3 (deprecated) instead of keccak256?
Use of chainid(), gasprice(), selfbalance(), basefee() correct for target chain?

Memory safety

memorysafe flag declared if the block doesn't touch memory? (Required for Yul optimizer to do its job; lying about it = compiler bugs.)

Cross-platform

Assembly that depends on Spurious-Dragon-era gas costs? L2s have different costs.
PUSH0 opcode requires Solidity ≥0.8.20 and a chain that supports it (most L2s do now).

Output

Assembly audit of <file>:

  Blocks reviewed: N (M lines of assembly)
  
  Findings:
    [ASM-001] Free-memory-pointer not updated after mstore at line 142
              Severity: High — next allocation corrupts the stored value
              
    [ASM-002] returndatacopy without size check at line 198
              Severity: High — caller-controlled return size can OOM / corrupt memory
              
    [ASM-003] uint8 unmasked after calldataload at line 224
              Severity: High — dirty high bits affect comparison

Read the full file on GitHub · 82 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.

1mo ago First seen · 82 lines · 36 tokens per session scan A a1e22ac5dcdf

Subscribe to this mod's changes

assembly-auditor is an agent published in the GitHub repository omermaksutii/RugProof (10 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 721 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Code review berachain blockchain claude-code-plugin defi ethereum

adversarial-validator

Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.

testdouble/han · 45 tokens

reviewer-performance

Use this agent when you need to analyze code for performance issues, optimize algorithms, identify bottlenecks, or ensure scalability. This includes reviewing database queries, memory usage, caching strategies, and overall system performance. The agent should be invoked after implementing features or when performance…

wsauret/flywheel · 345 tokens

assembly-auditor