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/up2itnow0822/agentpay-mcp/cursorrulesgit clone --depth 1 https://github.com/up2itnow0822/agentpay-mcpWhat 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 | $0.00593 | $0.00593 |
| Opus 5 | $0.00296 | $0.00296 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00059 | $0.00059 |
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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentPay MCP — Cursor Rules (ClawPowers enabled)
Project Context
This is agentpay-mcp — an MCP (Model Context Protocol) server that wraps agentwallet-sdk to give AI agents financial capabilities. Any MCP-compatible client (Claude Desktop, Cursor, Windsurf, etc.) can use it.
Current State
- v3.1.0 on npm, 11 MCP tools
- Dependencies: @modelcontextprotocol/sdk, [email protected], viem, zod
- TypeScript, vitest for tests, stdio transport
Upgrade Task: v4.0.0
Add new MCP tools exposing agentwallet-sdk v6.0.0 features:
New Tools to Build
send_token— Send any ERC-20 token (uses TokenRegistry + agentTransferToken)get_balances— Multi-token, multi-chain balance queryswap_tokens— Uniswap V3 swap via SwapModulebridge_usdc— CCTP V2 cross-chain bridgelookup_token— TokenRegistry lookup by symbol + chainadd_custom_token— Register custom tokenset_spend_policy— Configure spending limitscheck_budget— Query remaining budgetverify_agent_identity— ERC-8004 identity verificationget_reputation— Agent reputation scorecreate_escrow— Mutual stake escrow
Code Patterns
Follow existing tool patterns in src/tools/:
- Each tool file exports:
toolDefinition,handleFunction,ZodSchema - Zod schemas for input validation
- All handlers return
{ content: [{ type: "text", text: JSON.stringify(result) }] } - Register in
src/index.tsALL_TOOLS array and CallToolRequest handler
Quality Gates
- All existing 107 tests must still pass
- New tools need tests in
tests/ npm run build(tsc) must pass with 0 errors- Follow existing code style (no semicolons, single quotes)
SDK Reference
agentwallet-sdk v6.0.0 exports:
- TokenRegistry:
getGlobalRegistry(),.getToken(symbol, chainId),.listTokens(chainId),.addToken() - Transfers:
agentTransferToken(),encodeERC20Transfer() - Decimals:
toRaw(),toHuman(),formatBalance() - Swap:
SwapModule,attachSwap() - Bridge:
BridgeClient - Identity:
IdentityClient,ReputationClient,ValidationClient - Escrow:
MutualStakeEscrow - x402: multi-asset resolution
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.
- 2d ago First seen · 50 lines · 593 tokens per session scan A c6b0d9932f65
cursorrules is a cursor rule published in the GitHub repository up2itnow0822/agentpay-mcp (5 stars, last pushed 3d ago), licensed MIT. It adds 593 tokens to every session, about $0.0030 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
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-deploy
Prepare a bounded Agoragentic deployment handoff or preview. Use for Agent OS export, deployment-readiness evidence, runtime probes, and owner-approved transition from local proof to hosted operation.
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.
spend-lanes
Spend lanes — Cursor for review/specs, Claude Code for all implementation. Stops frontier token burn on multi-file code work in Cursor.
design-system
The model in one line: share VALUES by copy-in (design-tokens/tokens.css, pure CSS variables only), own COMPONENTS per-app (shadcn in components/ui/), and never ship a shared UI/token package again — @t2000/ui was removed 2026-07-01 because it bundled a marketing global stylesheet and packaged primitives a consumer's…
sui-platform
Sui platform patterns — Address Balances (SIP-58) make one address concurrent, gasless stablecoin transfers remove the SUI-for-gas wall, plus the eligibility gotchas that cause misleading failures. Full detail in .claude/skills/t2000-sui-platform/.