solidity-agentic-stack: Skill for Claude Code

.claude/skills/foundry-invariants/SKILL.md

foundry-invariants is a skill for Claude Code from Hirama/solidity-agentic-stack. It costs 79 tokens per session (1,420 once invoked), scanned A, original, MIT.

A guide for writing Foundry invariant tests for smart contracts. Foundry is a toolkit for developing Ethereum contracts, and invariant tests check that important rules remain true after many possible sequences of actions.

In plain words
What is it for?
Use it to create or debug invariant test suites, build handler contracts, track cumulative deposits and withdrawals, and verify that balances match contract accounting.
Why use it?
Ordinary tests check selected examples, but invariant tests can expose accounting or state bugs across varied action sequences. The guide provides patterns for actors, input limits, target selection, and tracked totals.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Hirama/solidity-agentic-stack's own configuration. It tells Claude Code how to work on solidity-agentic-stack itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything solidity-agentic-stack configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Hirama/solidity-agentic-stack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Hirama/solidity-agentic-stack/main/.claude/skills/foundry-invariants/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Hirama/solidity-agentic-stack

Made for: Claude Code.

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 foundry-invariants

README.md
[![agentmods](https://agentmods.dev/badge/skills/hirama/solidity-agentic-stack/foundry-invariants/github.svg)](https://agentmods.dev/skills/hirama/solidity-agentic-stack/foundry-invariants)
Your own site
<a href="https://agentmods.dev/skills/hirama/solidity-agentic-stack/foundry-invariants"><img src="https://agentmods.dev/badge/skills/hirama/solidity-agentic-stack/foundry-invariants/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.

agentmods 80×15 button for foundry-invariants

Your own site · 80×15
<a href="https://agentmods.dev/skills/hirama/solidity-agentic-stack/foundry-invariants"><img src="https://agentmods.dev/badge/skills/hirama/solidity-agentic-stack/foundry-invariants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,420 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.01420
Opus 5.5 $0.00032 $0.00568
Sonnet 5.5 $0.00016 $0.00284
Haiku 4.5 $0.00008 $0.00142

Measured 2mo ago against content hash 5f514b066570, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

foundry-invariants 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 2mo 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.

.claude/skills/foundry-invariants/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Foundry Invariants

Invariant tests assert properties that must hold across any sequence of state transitions. They are the protocol's constitution. If an invariant breaks, the protocol is broken — fix the implementation, never weaken the invariant.

When to use this skill

  • Writing a new invariant suite for a fresh protocol
  • Adding an invariant to an existing suite
  • Debugging an invariant break (e.g. INV-1 fails after 1024 calls)
  • Designing a handler to drive multi-actor state
  • Adding ghost variables to track cumulative state
  • Onboarding to this repo's test/invariant/VaultInvariant.t.sol

The contract — INV-1 and INV-2 in this stack

INV-1: address(vault).balance == vault.totalDeposits()
INV-2: ghost_totalDeposited - ghost_totalWithdrawn == vault.totalDeposits()

INV-1 is a balance ↔ accounting invariant — catches donation attacks, force-send drift, missing state updates. INV-2 is a flow conservation invariant — catches accounting bugs by reconciling external observations (ghost vars in the handler) against on-chain state.

Anatomy of an invariant suite

test/
├── handlers/
│   └── VaultHandler.sol      # drives actors through the state machine
└── invariant/
    └── VaultInvariant.t.sol  # the invariant_* functions

Handler — drives randomized actions

contract VaultHandler is Test {
    Vault public vault;
    address[] public actors;

    // Ghost variables — track cumulative state across calls
    uint256 public ghost_totalDeposited;
    uint256 public ghost_totalWithdrawn;

    constructor(Vault _vault) {
        vault = _vault;
        for (uint256 i; i < 5; i++) {
            actors.push(makeAddr(string.concat("actor", vm.toString(i))));
            vm.deal(actors[i], 1_000 ether);
        }
    }

    function deposit(uint256 actorSeed, uint256 amount) public {
        address actor = actors[bound(actorSeed, 0, actors.length - 1)];
        amount = bound(amount, 1, actor.balance);

        vm.prank(actor);
        vault.deposit{value: amount}();

        ghost_totalDeposited += amount;
    }

    function withdraw(uint256 actorSeed, uint256 amount) public {
        address actor = actors[bound(actorSeed, 0, actors.length - 1)];
        uint256 bal = vault.balanceOf(actor);
        if (bal == 0) return;
        amount = bound(amount, 1, bal);

        vm.prank(actor);
        vault.withdraw(amount);

        ghost_totalWithdrawn += amount;
    }
}

Read the full file on GitHub · 184 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. 2mo ago First seen · 184 lines · 79 tokens per session scan A 5f514b066570

Subscribe to this mod's changes

foundry-invariants is a skill published in the GitHub repository Hirama/solidity-agentic-stack (6 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 1,420 once invoked, about $0.0003 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.

Related

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.

wshobson/agents · 46 tokens

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…

pydantic/pydantic-ai · 92 tokens

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…

elvisun/newsjack · 67 tokens

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".

pashov/skills · 60 tokens

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…

stencila/stencila · 82 tokens

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/.

PaulRBerg/foundry-template · 64 tokens