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 rules/xfuel-lab/xfuel-protocol/cursorrulesgit clone --depth 1 https://github.com/XFuel-Lab/xfuel-protocolWhat 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 | $0.00889 | $0.00889 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
cursorrules 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 yesterday.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XFuel Protocol – Cursor Rules
Based on Whitepaper v1.6 core with expansions to v2.4
Solidity
- Use Solidity ^0.8.22 for all contracts in
contracts/core/and any new audit-scope contracts. - Use Solidity ^0.8.20 for all other contracts (
contracts/circuits/,contracts/mocks/,contracts/legacy/,contracts/interfaces/). - Do NOT use versions below 0.8.20 in any new contract.
- Follow OpenZeppelin patterns for access control, pausability, and safe transfers.
Architecture
- Prioritize modularity per whitepaper Section 2: No shared state between circuits, event-driven interfaces.
- Use SP1 hooks for zkML proofs per Section 7.
- Money + proof home = Base (USDC/x402, ZKVerifierSP1). Theta EdgeCloud = optional GPU provider only (ADR 0002).
Gas Optimization
- Target <300K gas per operation, <500K gas end-to-end per Section 3.5.
Code Comments
- Comment code with whitepaper references (e.g.,
// Per Section 3.2for Hyperlane relay).
Hardhat / Testing
- Use ethers.js v6+ for all RPC interactions.
- NEVER run
npx hardhat testagainst a live Theta RPC. Tests run against Hardhat local (chain 1337) only. - Theta ETH-RPC adaptor does NOT support
evm_snapshot,evm_revert, orevm_mine. Waffle fixtures will fail on-chain. - When writing Theta-live integration tests, replace
revertedWith('custom message')withrevertedWith('evm: execution reverted')— Theta always returns the generic message.
Base Networks (money + proof home — ADR 0002)
- Mainnet: chain ID 8453, RPC
https://mainnet.base.org(or Alchemy/Infura) - Sepolia: chain ID 84532, RPC
https://sepolia.base.org - Hardhat networks:
base,base-sepolia
Theta ETH-RPC (provider / EdgeCloud ops only — not settlement home)
- Mainnet: chain ID 361 (
0x169), RPChttps://eth-rpc-api.thetatoken.org/rpc - Testnet: chain ID 365 (
0x16d), RPChttps://eth-rpc-api-testnet.thetatoken.org/rpc - Privatenet: chain ID 366, RPC
http://localhost:18888/rpc - Subchain Testnet: chain ID 365001; Mainnet: 361001; Privatenet: 360777
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.
- yesterday First seen · 54 lines · 889 tokens per session scan A 0727eb41288c
cursorrules is a cursor rule published in the GitHub repository XFuel-Lab/xfuel-protocol (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 889 tokens to every session, about $0.0044 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 2026-08-31.
Other cursor rules, from other repositories
agoragentic-assure
Prepare and evaluate an autonomous agent transaction without self-granting authority or moving money. Use for bounded authority requests, pre-execution checks, payment and delivery evidence, safe retry decisions, outcome verification, and reconciliation.
agoragentic
Route an Agoragentic task to the smallest applicable skill. Use when the request involves Agoragentic execution, governance, transaction assurance, proof/receipts, deployment, selling, or integration and the correct branch is not yet known.
agoragentic-govern
Apply Agoragentic local governance before an agent performs side effects. Use for policy checks, approval packets, authority boundaries, and no-spend Harness or ECF preparation.
agoragentic-integrate
Connect an external agent host, framework, tool, or specialist engine to Agoragentic governance and receipts. Use for adapters, lifecycle mapping, MCP/tool discovery, and bounded integration design.
agoragentic-prove
Produce or inspect Agoragentic local proof and receipt evidence for an agent run. Use for evidence refs, hashes, run status, policy decisions, approval linkage, and reconciliation.
agoragentic-sell
Prepare an Agoragentic capability for commercial listing or paid routing. Use for listing readiness, pricing/payment metadata checks, seller evidence, and marketplace handoff without publishing or spending automatically.