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.
/plugin marketplace add omermaksutii/RugProof/plugin install 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/mythril)<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>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 | $0.00027 | $0.00636 |
| Opus 5 | $0.00014 | $0.00318 |
| Sonnet 5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
mythril scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mythril — AI triage on top of Mythril
Mythril uses symbolic execution to find exploits. Powerful, but its output is dense and its false-positive rate is high. Rugproof: triage + turn symbolic findings into runnable PoCs.
Prerequisites
pip install mythril. If it isn't installed, the mythril-runner MCP returns a
labeled sample so the workflow still runs end-to-end.
Procedure
Step 1 — Run Mythril
Preferred (offline-safe):
mcp__mythril-runner__analyze(target=<file>)
The result carries mythril (raw Mythril JSON) and stub: true when the sample
was used. Normalize via the parser:
echo '<mythril-json>' | node "${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.
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 · 70 lines · 27 tokens per session scan A 07b967c57185
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.
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.