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.
npx agentmods add instructions/protokol/solidity-typescript-hardhat-template/claude-mdgit clone --depth 1 https://github.com/protokol/solidity-typescript-hardhat-templateWrote 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/instructions/protokol/solidity-typescript-hardhat-template/claude-md)<a href="https://agentmods.dev/instructions/protokol/solidity-typescript-hardhat-template/claude-md"><img src="https://agentmods.dev/badge/instructions/protokol/solidity-typescript-hardhat-template/claude-md.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 | $0.00782 | $0.00782 |
| Opus 5 | $0.00391 | $0.00391 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
solidity-typescript-hardhat-template CLAUDE.md 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Project Instructions
Project Overview
Solidity/TypeScript Hardhat v3 template with ERC20, ERC721, and ERC1155 token contracts using OpenZeppelin v5 patterns.
Key Commands
npm run compile # Compile Solidity contracts
npm run test # Run Mocha/Chai test suite
npm run coverage # Run tests with coverage report
npm run format:write # Format TypeScript/config files with Prettier
npm run sol:format:write # Format Solidity files with Prettier
npm run lint:fix # Fix ESLint issues
npm run solhint # Lint Solidity with Solhint
Solidity Conventions
- Solidity version:
pragma solidity 0.8.28;— use this exact version, not a range - OpenZeppelin v5: Import from
@openzeppelin/contracts/(v5.6.1) - Contract patterns: Ownable + Pausable for access control; pass
initialOwnerto Ownable constructor - Naming: PascalCase for contracts (e.g.,
BasicERC20), use SPDX license identifierMIT - Override pattern: When inheriting multiple contracts with shared functions, use
override(Contract1, Contract2)and callsuper
Test Conventions
- Framework: Mocha + Chai with
expectstyle assertions - Fixture pattern: Each test file defines a
setupFixtureasync function, used vialoadFixture(setupFixture) - Hardhat setup: Use top-level
await hre.network.connect()to getethersandnetworkHelpers - Test structure:
describeblock per contract, nesteddescribefor functionality groups - Assertions: Use
revertedWithCustomErrorfor access control checks (OpenZeppelin v5 custom errors) - File naming: Test file matches contract name (e.g.,
BasicERC721.tstestsBasicERC721.sol)
Task Conventions
- Located in
tasks/organized by token type (e.g.,tasks/erc20/,tasks/erc721/) - Use Hardhat v3 task API:
task().addOption().setInlineAction().build() - Export named const (e.g.,
erc20MintTask) and register inhardhat.config.ts - Include usage example in JSDoc comment above the task
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.
- 4d ago First seen · 69 lines · 782 tokens per session scan A f3047fe62b2f
solidity-typescript-hardhat-template CLAUDE.md is an instructions file published in the GitHub repository protokol/solidity-typescript-hardhat-template (48 stars, last pushed yesterday), licensed MIT. It adds 782 tokens to every session, about $0.0039 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.
Other instructions, from other repositories
tevm CLAUDE.md
Claude Code instructions for evmts/tevm, covering tevm monorepo commands and style guide, project overview, forking implementation, json-rpc support and commands.
foundry-template CLAUDE.md
Instructions for PaulRBerg/foundry-template, a project described as: Foundry-based template for developing Solidity smart contracts.
aptos-ts-sdk AGENTS.md
AGENTS.md instructions for aptos-labs/aptos-ts-sdk, covering agents.md, project overview, runtime compatibility, requirements and repo layout.
starknet-agentic CLAUDE.md
Instructions for keep-starknet-strange/starknet-agentic, covering starknet agentic -- development context, cairo, typescript, skills and git.
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
web3gpt AGENTS.md
Instructions for Markeljan/web3gpt, covering agents.md, stack, common commands, environment and project map.