Borrowing it
Nothing to install: this file belongs to rome-protocol/rome-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rome-protocol/rome-cli/main/AGENTS.mdgit clone --depth 1 https://github.com/rome-protocol/rome-cliWrote 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/rome-protocol/rome-cli/agents-md)<a href="https://agentmods.dev/instructions/rome-protocol/rome-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/rome-protocol/rome-cli/agents-md/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/instructions/rome-protocol/rome-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/rome-protocol/rome-cli/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03781 | $0.03781 |
| Opus 5.5 | $0.01512 | $0.01512 |
| Sonnet 5.5 | $0.00756 | $0.00756 |
| Haiku 4.5 | $0.00378 | $0.00378 |
Grade A, and why
rome-cli AGENTS.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 22d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — building on Rome with an AI coding agent
Rome is EVM chains that run natively inside the Solana runtime. Your Solidity/EVM app executes inside a Solana program and can call Solana programs atomically (CPI). Two lanes reach the same chain and the same state: MetaMask/EVM tooling, and a Solana wallet (Solflare, for example).
This file gives you the facts, organized by what you're starting from. Find your starting point, apply the rules that bite on every path, and read the example repo closest to what you're building. Vanilla-EVM habits produce plausible-but-wrong code here — reads (eth_call, balances, logs) are standard; the differences are in writes, gas, tooling, CPI, and architecture.
First, the mental model — three facts everything rests on
- EVM inside Solana. Your Solidity runs inside a Solana program; from Solidity you can invoke any Solana program (SPL Token, Meteora, a program you wrote) atomically, in one transaction, via the CPI precompile.
- One state, two lanes. MetaMask (an EVM key) and a Solana wallet such as Solflare (a Solana key) drive the same contracts and the same state. A Solana user signs with their Solana key — no EVM keypair; Rome derives their EVM address (a synthetic address) from that key. An EVM user's on-chain identity is a Rome-derived PDA (
external_auth). - SPL is ERC-20, automatically. Any SPL token is already an ERC-20 on Rome — the same account, no bridge and no wrapped-asset hop. An LP or position token minted as an SPL mint is spendable as an ERC-20 too, and vice-versa, once the wallet has granted the token's wrapper (rule 4).
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.
- 22d ago Changed · +1 lines · +27 tokens per session d15befe71b3c
- 25d ago Changed · +1 lines · +249 tokens per session 6729e1d852cc
- 26d ago Changed · +5 lines · +496 tokens per session 94c5a5b9ecf4
- 2mo ago First seen · 69 lines · 3,009 tokens per session scan A 39972628be33
rome-cli AGENTS.md is an instructions file published in the GitHub repository rome-protocol/rome-cli (1 stars, last pushed 8d ago), licensed MIT. It adds 3,781 tokens to every session, about $0.0151 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.
rome-cli AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rome-cli AGENTS.mdrome-protocol/rome-cli | Instructions file | 1 | 8d ago | MIT | A | 3,781 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |