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/originprotocol/origin-dollar/claude-mdgit clone --depth 1 https://github.com/OriginProtocol/origin-dollarWrote 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/originprotocol/origin-dollar/claude-md)<a href="https://agentmods.dev/instructions/originprotocol/origin-dollar/claude-md"><img src="https://agentmods.dev/badge/instructions/originprotocol/origin-dollar/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 | $0.05142 | $0.05142 |
| Opus 5 | $0.02571 | $0.02571 |
| Sonnet 5 | $0.01028 | $0.01028 |
| Haiku 4.5 | $0.00514 | $0.00514 |
Grade A, and why
origin-dollar 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 today.
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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Origin DeFi's OTokens monorepo containing smart contracts for:
- OUSD (Origin Dollar) - a yield-bearing stablecoin
- OETH (Origin Ether) - an Ethereum liquid staking token
- OS (Origin Sonic) - Sonic chain native token
Deployed on Ethereum Mainnet, Base, Arbitrum, Sonic, Plume, Hoodi, and HyperEVM. All smart contract work happens in the contracts/ directory.
Toolchain
Foundry is the contract toolchain: forge (driven by the Makefile) builds the contracts, runs the contract test suite, executes deployments, and generates the @origin/defi npm ABI package. Hardhat remains only for the ops task CLI (tasks/*.js, wired up in hardhat.config.js). The committed deployments/ descriptors are the address/ABI registry consumed by both toolchains; there are no Hardhat deployment scripts.
Setup
cd contracts
cp dev.env .env # Set MAINNET_PROVIDER_URL to an Alchemy/Infura endpoint
make install # foundryup (v1.8.1), forge soldeer install, install-deps.sh, pnpm i
Key .env variables: MAINNET_PROVIDER_URL (required), BASE_PROVIDER_URL, ARBITRUM_PROVIDER_URL, SONIC_PROVIDER_URL, HYPEREVM_PROVIDER_URL, BEACON_PROVIDER_URL (beacon-proof fork tests), and optional FORK_BLOCK_NUMBER_<CHAIN> pins for Foundry fork tests (unset = latest block; refresh with make update-fork-blocks). The Hardhat task CLI resolves its mainnet RPC from MAINNET_PROVIDER_URL as well (legacy fallback: PROVIDER_URL).
Real deployments additionally need DEPLOYER_ADDRESS and the encrypted deployerKey keystore (cast wallet import deployerKey --interactive).
@oplabs/talos-client (private, optional)
pnpm i deliberately does not install @oplabs/talos-client. It is declared
as an optional peer dependency so that CI and external contributors can install
this repo without GitHub Packages credentials.
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.
- today First seen · 353 lines · 5,142 tokens per session scan A 9964bd5ba712
origin-dollar CLAUDE.md is an instructions file published in the GitHub repository OriginProtocol/origin-dollar (151 stars, last pushed yesterday), licensed MIT. It adds 5,142 tokens to every session, about $0.0257 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 2026-09-04.
Other instructions, from other repositories
WAIaaS CLAUDE.md
Instructions for waiaas/WAIaaS, covering waiaas project rules, language, communication, schema & type system and database.
krait CLAUDE.md
Instructions for ZealynxSecurity/krait, covering claude.md, project shape, common commands, run a single test file or test by name and cli architecture (src/).
ponscli CLAUDE.md
Claude Code instructions for mesutgulecen/ponscli, covering ponscli, the rule that matters most, layout, verifying a change and things that will bite.
coingecko-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/coingecko-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
coingecko-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/coingecko-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
quantum-shield AGENTS.md
AGENTS.md instructions for kota1026/quantum-shield, covering agents.md - quantum shield project, project overview, core components, allowed actions and file operations.