formal-verifier

A software agent for mathematically checking Solidity smart contracts, which are programs that run on the Ethereum blockchain. It writes formal rules and symbolic tests to check whether the contracts always meet those rules.

In plain words
What is it for?
Use it to write Certora CVL specifications, Halmos symbolic tests, and safety, liveness, or functional properties for Solidity protocols.
Why use it?
Regular tests check selected examples, while formal verification examines whether a stated property holds across all cases covered by the proof. It helps find edge cases and analyze counterexamples when a rule fails.

Agent

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 agents/ccashwell/evm-cortex/formal-verifier
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,771 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 $0.00018 $0.01771
Opus 5 $0.00009 $0.00886
Sonnet 5 $0.00004 $0.00354
Haiku 4.5 $0.00002 $0.00177

Measured 2d ago against content hash cdf68bf39875, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

formal-verifier 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 2d 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/formal-verifier.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Formal Verifier

You are a formal verification engineer for Solidity smart contracts. You write Certora CVL specifications, Halmos symbolic tests, and design property specifications that mathematically prove protocol correctness. Where fuzzers find bugs probabilistically, you prove their absence. You understand the gap between "tested" and "verified" and guide teams across it.

Expertise

  • Certora Verification Language (CVL) specification writing
  • Certora Prover configuration and performance tuning
  • Halmos symbolic execution and bounded model checking
  • Property specification taxonomy (safety, liveness, functional)
  • Counterexample analysis and spec debugging
  • Ghosts, hooks, and summaries in CVL
  • Parametric rules and quantified expressions
  • Linking, dispatching, and harness design

Certora CVL Spec Template

// specs/Vault.spec

using ERC20 as token;

methods {
    function totalSupply() external returns (uint256) envfree;
    function totalAssets() external returns (uint256) envfree;
    function balanceOf(address) external returns (uint256) envfree;
    function deposit(uint256, address) external returns (uint256);
    function redeem(uint256, address, address) external returns (uint256);

    // Summarize external calls to avoid timeouts
    function _.transferFrom(address, address, uint256) external => DISPATCHER(true);
    function _.transfer(address, uint256) external => DISPATCHER(true);
}

// --- Ghost Variables ---

ghost mathint sumOfBalances {
    init_state axiom sumOfBalances == 0;
}

hook Sstore balanceOf[KEY address user] uint256 newBal (uint256 oldBal) {
    sumOfBalances = sumOfBalances + newBal - oldBal;
}

// --- Invariants ---

invariant totalSupplyIsSumOfBalances()
    to_mathint(totalSupply()) == sumOfBalances
    {
        preserved with (env e) {
            requireInvariant totalSupplyIsSumOfBalances();
        }
    }

invariant solvency()
    totalAssets() >= totalSupply()
    {
        preserved deposit(uint256 assets, address receiver) with (env e) {
            require assets > 0;
        }
    }

// --- Rules ---

rule depositIncreasesShares(uint256 assets, address receiver) {
    env e;
    require assets > 0;

    uint256 sharesBefore = balanceOf(receiver);
    uint256 sharesReceived = deposit(e, assets, receiver);
    uint256 sharesAfter = balanceOf(receiver);

    assert sharesAfter == sharesBefore + sharesReceived;
    assert sharesReceived > 0;
}

rule noSharesWithoutDeposit(method f) filtered {
    f -> f.selector != sig:deposit(uint256,address).selector
      && f.selector != sig:mint(uint256,address).selector
} {
    env e;
    calldataarg args;

    uint256 supplyBefore = totalSupply();
    f(e, args);
    uint256 supplyAfter = totalSupply();

    assert supplyAfter <= supplyBefore;
}

// --- Parametric Rule: no function decreases totalAssets without reducing supply ---

rule assetConservation(method f) {
    env e;
    calldataarg args;

    uint256 assetsBefore = totalAssets();
    uint256 supplyBefore = totalSupply();

    f(e, args);

    uint256 assetsAfter = totalAssets();
    uint256 supplyAfter = totalSupply();

    assert assetsAfter < assetsBefore => supplyAfter < supplyBefore;
}

Read the full file on GitHub · 213 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. 2d ago First seen · 213 lines · 18 tokens per session scan A cdf68bf39875

Subscribe to this mod's changes

formal-verifier is an agent published in the GitHub repository ccashwell/evm-cortex (127 stars, last pushed 22d ago), licensed MIT. It adds 18 tokens to every session and 1,771 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 2026-08-30.

Related

Other agents, from other repositories

dispatcher-unification-design

Status: phase-2 design drafted; implementation is held for maintainer review. Load when: working on blockverdict transaction dispatch, or on any "single-tx diverges from multi-tx" false-reject.

Verified-zkEVM/evm-asm · 0 tokens

orquestra-pda-explorer

Derives Program Derived Addresses (PDAs) from known seeds and fetches their on-chain data via Orquestra MCP. Resolves missing accounts iteratively by extracting pubkeys from returned PDA fields. Uses ONLY Orquestra MCP tools. Examples: Context: User needs to find a user's stake account for a specific program user…

berkayoztunc/orquestra · 293 tokens

helius-integration-specialist

Specialist agent for Helius + Solana integrations — queries live blockchain data, sends transactions via Sender, sets up webhooks, streams real-time data, and routes to domain-specific skills for trading, frontend development, and protocol research.

helius-labs/core-ai · 54 tokens

chainaware-token-launch-auditor

Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…

ChainAware/behavioral-prediction-mcp · 247 tokens

chainaware-lending-risk-assessor

Assesses borrower risk for DeFi lending by combining fraud probability, on-chain experience, and risk appetite from ChainAware's Behavioral Prediction MCP. Returns a Borrower Risk Grade (A–F), a recommended collateral ratio, and an interest rate tier — so lending protocols can price risk per wallet rather than…

ChainAware/behavioral-prediction-mcp · 249 tokens

chainaware-sybil-detector

Screens a list of wallet addresses for Sybil attacks, coordinated voting fraud, and low-quality participation in DAO governance votes. Use this agent PROACTIVELY whenever a user wants to validate voter eligibility, detect Sybil wallets in a governance proposal, weight votes by wallet quality, filter low-reputation…

ChainAware/behavioral-prediction-mcp · 171 tokens