mythril

mythril is a command for Claude Code from omermaksutii/RugProof. It costs 27 tokens per session (636 once invoked), scanned A, original, MIT.

A security-testing command that uses Mythril’s symbolic execution to look for possible smart-contract exploits and turns confirmed findings into Foundry tests. Symbolic execution explores many possible inputs automatically.

In plain words
What is it for?
Use it to analyze Solidity files, review Mythril findings, verify exploit paths, and create Foundry tests for confirmed vulnerabilities.
Why use it?
Mythril’s results can be difficult to interpret and may include false positives. This workflow checks the affected code and converts real issues into runnable proof-of-concept tests.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add omermaksutii/RugProof
Claude Code
/plugin install 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 mythril

README.md
[![agentmods](https://agentmods.dev/badge/commands/omermaksutii/rugproof/mythril.svg)](https://agentmods.dev/commands/omermaksutii/rugproof/mythril)
Your own site
<a href="https://agentmods.dev/commands/omermaksutii/rugproof/mythril"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/mythril.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 636 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 $0.00027 $0.00636
Opus 5 $0.00014 $0.00318
Sonnet 5 $0.00005 $0.00127
Haiku 4.5 $0.00003 $0.00064

Measured 6d ago against content hash 07b967c57185, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mythril 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/mythril.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mythril — AI triage on top of Mythril

Mythril uses symbolic execution to find exploits. Powerful, but its output is dense and its false-positive rate is high. Rugproof: triage + turn symbolic findings into runnable PoCs.

Prerequisites

pip install mythril. If it isn't installed, the mythril-runner MCP returns a labeled sample so the workflow still runs end-to-end.

Procedure

Step 1 — Run Mythril

Preferred (offline-safe):

mcp__mythril-runner__analyze(target=<file>)

The result carries mythril (raw Mythril JSON) and stub: true when the sample was used. Normalize via the parser:

echo '<mythril-json>' | node "${CLAUDE_PLUGIN_ROOT}/scripts/dist/parse-mythril.js"

Or run directly: myth analyze <file> -o json. Capture issues, each with a SWC ID, severity, and a symbolic-execution path.

Step 2 — For each Mythril issue

  • Read the affected function.
  • Look at the symbolic path Mythril provides.
  • Turn the path into a concrete Foundry test:
    • Map symbolic vars to concrete inputs from Mythril's counter-example.
    • Set up state per the path.
    • Run the test via forge-runner.
  • If the test passes (exploit succeeds) → True positive, output the PoC.
  • If the test fails → either the path requires unreachable state, or the symbolic engine over-approximated. Mark as theoretical or FP.

Step 3 — Output

Mythril + Rugproof triage:

  Mythril raw issues: 22
  After Rugproof triage:
    Concrete PoCs that pass:  4   (real bugs)
    Theoretical paths only:   12  (no realistic exploit)
    False positives:          6   (Mythril over-approximated)

Concrete PoCs:
  [SWC-107] Reentrancy in Vault.withdraw
    Mythril path:  attacker → withdraw → fallback re-enters withdraw
    Rugproof PoC:  test/exploits/ExploitMythril-SWC107.t.sol  (passes)
    Confidence:    HIGH

Notes

  • Mythril is slow on large contracts — warn the user upfront and offer to scope to one file.
  • For modern Solidity (>=0.8), some classic SWCs (integer-overflow) are pre-handled — auto-downgrade those.
  • Output should ALWAYS include a working test if confidence is HIGH.

Read the full file on GitHub · 70 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 · 70 lines · 27 tokens per session scan A 07b967c57185

Subscribe to this mod's changes

mythril is a command published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 636 once invoked, about $0.0001 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.