Skip to content

armgit / ECC

Public Imported from GitHub
0

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

fix: address all automated review feedback on code example

up2itnow0822e57ad5c33d52
diff --git a/skills/agent-payment-x402/SKILL.md b/skills/agent-payment-x402/SKILL.md
index 0dab98d08..c90d505df 100644
--- a/skills/agent-payment-x402/SKILL.md
+++ b/skills/agent-payment-x402/SKILL.md
@@ -10,9 +10,9 @@ Enable AI agents to make autonomous payments with built-in spending controls. Us
## When to Use
-Use when: your agent needs to pay for an API call, purchase a service, settle with another agent, enforce per-task spending limits, or manage a non-custodial wallet. Pairs naturally with cost-aware-llm-pipeline and mcp-server-patterns skills.
+Use when: your agent needs to pay for an API call, purchase a service, settle with another agent, enforce per-task spending limits, or manage a non-custodial wallet. Pairs naturally with cost-aware-llm-pipeline and security-review skills.
-## Core Concepts
+## How It Works
### x402 Protocol
x402 extends HTTP 402 (Payment Required) into a machine-negotiable flow. When a server returns `402`, the agent's payment tool automatically negotiates price, checks budget, signs a transaction, and retries — no human in the loop.
@@ -25,52 +25,144 @@ Every payment tool call enforces a `SpendingPolicy`:
- **Rate limits** — max transactions per minute/hour
### Non-Custodial Wallets
-Agents hold their own keys via ERC-4337 smart accounts. The orchestrator sets policy; the agent can only spend within bounds. No pooled funds, no custodial risk.
+Agents hold their own keys via ERC-4337 smart accounts. The orchestrator sets policy before delegation; the agent can only spend within bounds. No pooled funds, no custodial risk.
## MCP Integration
-The payment layer exposes standard MCP tools that slot into any Claude Code or agent harness setup:
+The payment layer exposes standard MCP tools that slot into any Claude Code or agent harness setup.
+
+> **Security note**: Always pin the package version. This tool manages private keys — unpinned `npx` installs introduce supply-chain risk.
```json
{
"mcpServers": {
"agentpay": {
"command": "npx",
- "args": ["-y", "agentwallet-sdk"]
+ "args": ["[email protected]"]
}
}
}
```
-### Available Tools
+### Available Tools (agent-callable)
| Tool | Purpose |
|------|---------|
| `get_balance` | Check agent wallet balance |
| `send_payment` | Send payment to address or ENS |
| `check_spending` | Query remaining budget |
-| `set_policy` | Configure spending limits |
| `list_transactions` | Audit trail of all payments |
-## Example: Pay-Per-API-Call Agent
+> **Note**: Spending policy is set by the **orchestrator** before delegating to the agent — not by the agent itself. This prevents agents from escalating their own spending limits. Configure policy via `set_policy` in your orchestration layer or pre-task hook, never as an agent-callable tool.
+
+## Examples
+
+### Budget enforcement in an MCP client
+
+When building an orchestrator that calls the agentpay MCP server, enforce budgets before dispatching paid tool calls.
+
+> **Prerequisites**: Install the package before adding the MCP config — `npx` without `-y` will prompt for confirmation in non-interactive environments, causing the server to hang: `npm install -g [email protected]`
```typescript
-// In your CLAUDE.md or agent config:
-// 1. Add agentpay MCP server (see above)
-// 2. Set spending policy in your skill/hook:
-
-// Hook: pre-tool check
-if (toolName === "web_search" && apiCost > 0) {
- const budget = await mcp.call("agentpay", "check_spending");
- if (budget.remaining < apiCost) {
- return { error: "Budget exceeded for this task" };
+import { Client } from "@modelcontextprotocol/sdk/client/index.js";
+import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
+
+async function main() {
+ // 1. Validate credentials before constructing the transport.
+ // A missing key must fail immediately — never let the subprocess start without auth.
+ const walletKey = process.env.WALLET_PRIVATE_KEY;
+ if (!walletKey) {
+ throw new Error("WALLET_PRIVATE_KEY is not set — refusing to start payment server");
}
+
+ // Connect to the agentpay MCP server via stdio transport.
+ // Whitelist only the env vars the server needs — never forward all of process.env
+ // to a third-party subprocess that manages private keys.
+ const transport = new StdioClientTransport({
+ command: "npx",
+ args: ["[email protected]"],
+ env: {
+ PATH: process.env.PATH ?? "",
+ NODE_ENV: process.env.NODE_ENV ?? "production",
+ WALLET_PRIVATE_KEY: walletKey,
+ },
+ });
+ const agentpay = new Client({ name: "orchestrator", version: "1.0.0" });
+ await agentpay.connect(transport);
+
+ // 2. Set spending policy before delegating to the agent.
+ // Always verify success — a silent failure means no controls are active.
+ const policyResult = await agentpay.callTool({
+ name: "set_policy",
+ arguments: {
+ per_task_budget: 0.50,
+ per_session_budget: 5.00,
+ allowlisted_recipients: ["api.example.com"],
+ },
+ });
+ if (policyResult.isError) {
+ throw new Error(
+ `Failed to set spending policy — do not delegate: ${JSON.stringify(policyResult.content)}`
+ );
+ }
+
+ // 3. Use preToolCheck before any paid action
+ await preToolCheck(agentpay, 0.01);
}
+
+// Pre-tool hook: fail-closed budget enforcement with four distinct error paths.
+async function preToolCheck(agentpay: Client, apiCost: number): Promise<void> {
+ // Path 1: Reject invalid input (NaN/Infinity bypass the < comparison)
+ if (!Number.isFinite(apiCost) || apiCost < 0) {
+ throw new Error(`Invalid apiCost: ${apiCost} — action blocked`);
+ }
+
+ // Path 2: Transport/connectivity failure
+ let result;
+ try {
+ result = await agentpay.callTool({ name: "check_spending" });
+ } catch (err) {
+ throw new Error(`Payment service unreachable — action blocked: ${err}`);
+ }
+
+ // Path 3: Tool returned an error (e.g., auth failure, wallet not initialised)
+ if (result.isError) {
+ throw new Error(
+ `check_spending failed — action blocked: ${JSON.stringify(result.content)}`
+ );
+ }
+
+ // Path 4: Parse and validate the response shape
+ let remaining: number;
+ try {
+ const parsed = JSON.parse(
+ (result.content as Array<{ text: string }>)[0].text
+ );
+ if (!Number.isFinite(parsed?.remaining)) {
+ throw new TypeError("missing or non-finite 'remaining' field");
+ }
+ remaining = parsed.remaining;
+ } catch (err) {
+ throw new Error(
+ `check_spending returned unexpected format — action blocked: ${err}`
+ );
+ }
+
+ // Path 5: Budget exceeded
+ if (remaining < apiCost) {
+ throw new Error(
+ `Budget exceeded: need $${apiCost} but only $${remaining} remaining`
+ );
+ }
+}
+
+main().catch(console.error);
```
## Best Practices
-- **Set budgets before delegation**: When spawning sub-agents, attach a SpendingPolicy. Never give an agent unlimited spend.
+- **Set budgets before delegation**: When spawning sub-agents, attach a SpendingPolicy via your orchestration layer. Never give an agent unlimited spend.
+- **Pin your dependencies**: Always specify an exact version in your MCP config (e.g., `[email protected]`). Verify package integrity before deploying to production.
- **Audit trails**: Use `list_transactions` in post-task hooks to log what was spent and why.
- **Fail closed**: If the payment tool is unreachable, block the paid action — don't fall back to unmetered access.
- **Pair with security-review**: Payment tools are high-privilege. Apply the same scrutiny as shell access.