Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ccashwell/evm-cortexnpx agentmods add skills/ccashwell/evm-cortex/formal-verificationWrote 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/skills/ccashwell/evm-cortex/formal-verification)<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/formal-verification"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/formal-verification/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.
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/formal-verification"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/formal-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.01403 |
| Opus 5.5 | $0.00016 | $0.00561 |
| Sonnet 5.5 | $0.00008 | $0.00281 |
| Haiku 4.5 | $0.00004 | $0.00140 |
Grade A, and why
formal-verification 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.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Formal Verification for Solidity
Tools
| Tool | Approach | Strengths |
|---|---|---|
| Certora Prover | CVL specs + SMT solving | Industry standard, deep analysis |
| Halmos | Symbolic Foundry tests | Familiar Foundry interface, open source |
| KEVM | K Framework semantics | EVM bytecode level verification |
Certora CVL Specification Template
// spec/Vault.spec
using ERC20 as token;
methods {
function deposit(uint256) external returns (uint256);
function withdraw(uint256, address, address) external returns (uint256);
function totalAssets() external returns (uint256) envfree;
function totalSupply() external returns (uint256) envfree;
function balanceOf(address) external returns (uint256) envfree;
function asset() external returns (address) envfree;
// Summarize external calls
function _.transfer(address, uint256) external => DISPATCHER(true);
function _.transferFrom(address, address, uint256) external => DISPATCHER(true);
function _.balanceOf(address) external => DISPATCHER(true);
}
Rule Types
Parametric Rules
Verify properties for all possible inputs:
// Depositing should increase total supply
rule depositIncreasesSupply(uint256 assets) {
env e;
uint256 supplyBefore = totalSupply();
deposit(e, assets);
uint256 supplyAfter = totalSupply();
assert supplyAfter >= supplyBefore, "supply must not decrease on deposit";
}
Invariant Rules
Properties that must hold in every reachable state:
// Solvency: vault always has enough assets to back shares
invariant solvency()
totalSupply() == 0 || totalAssets() > 0
{
preserved deposit(uint256 assets) with (env e) {
require assets > 0;
}
}
Relational Rules
Compare two executions:
// Monotonicity: depositing more gives more shares
rule depositMonotonicity(uint256 assets1, uint256 assets2) {
env e;
require assets1 < assets2;
storage init = lastStorage;
uint256 shares1 = deposit(e, assets1);
uint256 shares2 = deposit(e, assets2) at init;
assert shares2 >= shares1, "more assets should give more shares";
}
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 · 220 lines · 40 tokens per session scan A 397af5aeed50
formal-verification is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 17d ago), licensed MIT. It adds 40 tokens to every session and 1,403 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
web3-testing
Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, attach a workspace, defer capability…
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…
fizz
Generate Echidna/Medusa-compatible Solidity fuzz suites from Foundry or Hardhat projects. Trigger on "fizz", "generate fuzz suite", "build fuzz harness", "stateful fuzzing", "fuzzing harness", "property testing", and "invariant suite".
foundry-testing
Write and debug Foundry tests and Solidity scripts. Use when writing unit, fuzz, fork, or invariant tests, writing bulloak BTT .tree specs (Branching Tree Technique), using cheatcodes, benchmarking gas, measuring coverage, writing deploy scripts, or working in tests/ or script/.
software-test-creation
Write failing tests for a TDD slice based on acceptance criteria and codebase conventions. Use when the "red" phase of red-green-refactor requires tests that define expected behavior before implementation exists. Discovers codebase test conventions first, writes test files that compile or parse but fail because the…