TWZRD buyer-side x402 trust packages: x402 trust gate, elizaOS trust plugin, and the agent-intel client. Vet a counterparty before you pay.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/twzrd-sol/twzrd-trust && cp twzrd-trust/*.md ~/.claude/agents/Subagents overview
# TWZRD
**Don't let your agent sign blind.**
Pre-spend trust for agents that buy: the x402 service they are about to pay (Solana, and Base) and the product listing they are about to buy from.
- **x402 services:** vet the seller **before** USDC leaves the wallet, cap and ledger every spend, and bind each settled payment to the exact offer it paid for (**bind-v1** — verifiable from public chain data). Advisory preflight is free ($0). The paid `quickCheck` is **$0.001** (seller wash risk, tier and score; no receipt). Separately, the gate can issue a portable `twzrd.payment_decision.v1` record from its own decision, signed locally with your own signer.
- **Product listings:** a free check of a store product URL and its asking price against a card TWZRD published from the store's public pages. The card is an observer card, not a merchant attestation, and a match is never permission to spend ([details](#product-listings-check-the-listing-before-you-buy)).
Not a wallet. Not a payment network. Not Catena's Agent Commerce Kit — the walkthrough lives in [docs/COMMERCE-KIT.md](./docs/COMMERCE-KIT.md).
**Canonical skill (always refresh)** • https://intel.twzrd.xyz/skill.md (skill `twzrd-trust`; the live copy carries its version) · [ClawHub `twzrd-trust`](https://clawhub.ai)
**Spend-control SDK (npm)** • [`twzrd-x402-gate@0.11.2`](https://www.npmjs.com/package/twzrd-x402-gate) + seat [`x402-solana@3.0.0`](https://www.npmjs.com/package/x402-solana)
**Live MCP** • https://intel.twzrd.xyz/mcp (streamable HTTP; free tools for x402 service checks and product-listing checks)
**Shopping check** • free `check_listing` on the hosted MCP · report: https://twzrd.xyz/shopping-check/vuori-kore/
**Agent contract** • https://intel.twzrd.xyz/llms.txt · https://intel.twzrd.xyz/.well-known/agent.json
---
## 60-second deterministic free demo
Run this one-line command with **no wallet, no API key, and no configuration**:
```bash
curl -fsS https://intel.twzrd.xyz/v1/intel/demo-gate | jq '{verdict: (.steps[] | select(.name == "block_path") | .verdict), approved: (.steps[] | select(.name == "block_path") | .approved), signerInvocations: (.steps[] | select(.name == "block_path") | .signer_invocations), mode, ok}'
```
Without `jq`, run: `curl -fsS https://intel.twzrd.xyz/v1/intel/demo-gate`
Expected output:
```json
{
"verdict": "block",
"approved": false,
"signerInvocations": 0,
"mode": "no_spend",
"ok": true
}
```
*Blocks happen before your signer is invoked (`signerInvocations: 0`) — zero USDC at risk.*
---
## How the pieces fit
<!-- twzrd:ecosystem:begin (generated by scripts/render-ecosystem.mjs from docs/ecosystem.json; edit that file) -->
**Pre-spend trust for AI agents that buy: check x402 services and product listings before paying.**
| You are | Free | Paid |
|---|---|---|
| an agent about to pay an x402 seller | Readiness card (allow, warn or block), wash flags, seller reputation, offline receipt check. | $0.001 `quickCheck` (seller wash risk, tier and score, no receipt); optional $0.05 trust receipt, a signed V7 receipt when you pay on Solana. |
| an agent about to buy a product from a store | `check_listing(product_url, declared_unit_price)` against a published listing card, and the Agent Shopping Check report. | Optional $0.001 checkout brief for a buyer-approved Shop Pay checkout. |
Each piece below works alone. Plugged into the hosted checks, they form one pre-spend path.
| Piece | On its own | Plugged in | Install |
|---|---|---|---|
| [Hosted checks](https://intel.twzrd.xyz/llms.txt) | Free checks with nothing to install: is this x402 seller safe to pay, and does this store listing match a published card. | The pieces below that screen a payment call it; it is where the decisions and the signed receipts come from. The receipt verifier needs no server. | Add `https://intel.twzrd.xyz/mcp` to an MCP client |
| [`twzrd-x402-gate`](https://www.npmjs.com/package/twzrd-x402-gate) | Wraps an x402 client's pay path: asks the hosted checks about the seller before your signer runs, refuses a block (the signer is never invoked), enforces a spend cap, and can issue a `twzrd.payment_decision.v1` record from its decision, signed with your own signer. | Decisions come from the hosted checks; pairs with `x402-solana` or `@x402/fetch` as the payer. | `npm install twzrd-x402-gate` |
| [`twzrd-preflight`](https://github.com/twzrd-sol/twzrd-preflight) | OpenClaw plugin: assign its wrapped fetch to the client and every 402 that passes through it is checked before a signer can attach payment (enforce and fail-closed by default). | Matches the gate's wrapper and adds OpenClaw tool-call gating, against the hosted checks. Payments outside the wrapped fetch (a ClawRouter proxy, unparsed exec or curl) are not covered. | `npm install twzrd-preflight` |
| [`twzrd-receipt-verifier`](https://github.com/twzrd-sol/twzrd-receipt-verifier) | Verifies a TWZRD receipt offline against a published Ed25519 key: no wallet, no API key, no trust in TWZRD's server. | Checks the signed receipts that the hosted checks issue. | `npx twzrd-receipt-verifier` or `pip install twzrd-receipt-verifier` |
| [`twzrd-mcp-server`](https://www.npmjs.com/package/twzrd-mcp-server) / [`twzrd-mcp`](https://pypi.org/project/twzrd-mcp/) | A local MCP client with 6 tools that pays the $0.001 and $0.05 calls itself under a spend cap (a wallet only if you enable paid calls). | Calls the hosted checks; use the hosted MCP directly for the free checks. | `npx -y twzrd-mcp-server` or `pip install twzrd-mcp` |
| [`@wzrd_sol/plugin-trustgate`](https://www.npmjs.com/package/@wzrd_sol/plugin-trustgate), [`@wzrd_sol/eliza-plugin`](https://www.npmjs.com/package/@wzrd_sol/eliza-plugin) | Framework seats: a settle hook for facilitators (see [docs](https://github.com/twzrd-sol/twzrd-trust/blob/main/docs/facilitator-trust-in-3-lines.md)), a Faremeter payer chooser, and elizaOS actions. | Each seat calls the hosted checks from inside its framework. | `npm install @wzrd_sol/plugin-trustgate` |
| [`twzrd-agent-intel`](https://pypi.org/project/twzrd-agent-intel/) | The server package behind the hosted checks. Run it yourself behind a firewall; a local run serves a small static snapshot, not live data. | Point a self-hosted instance at live data with its environment variables. | `pip install twzrd-agent-intel`, then `twzrd-agent-intel-mcp` |
| Seller starters: [`x402-solana-starter`](https://github.com/twzrd-sol/x402-solana-starter), [`x402-seller-starter`](https://github.com/twzrd-sol/x402-seller-starter) | Cloudflare Worker templates for selling a paid API to agents over x402: `x402-solana-starter` is the production-style Solana storefront (x402 v2), `x402-seller-starter` a minimal wedge. | Both default to the TWZRD facilitator. `x402-solana-starter` also runs a settle guard, advisory and fail-open, that screens payers through the hosted checks. | Deploy button in each repo |
**Put them together**
- **Refuse before signing:** gate (or preflight) + hosted checks. A blocked seller never reaches your signer. Prove it with no wallet and no spend: `curl -fsS https://intel.twzrd.xyz/v1/intel/demo-gate`.
- **Keep proof of what you paid for:** paid trust receipt + receipt verifier. A signed receipt you or anyone else can verify offline.
- **Check a listing before you buy:** `check_listing` + your human approval step. A price above the card is refused; a price below it, or a card with no price, asks a human. Optionally add the paid checkout brief.
- **Screen every settlement you broker:** plugin-trustgate settle hook + hosted checks. A facilitator aborts a settle to a blocked seller before the transfer.
**What TWZRD does not claim**
- TWZRD scores observed wallet and payment behavior. It does not prove a person, company, or agent identity.
- A listing card is an observer card, not a merchant attestation. Advertised means a captured page said it; purchase completion and delivery are not verified.
- `authorizes_spend` is always false: a check is evidence for your own spend policy, never permission to spend.
- Not a wallet. Not a payment network.
<!-- twzrd:ecosystem:end -->
More: [docs/ECOSYSTEM.md](./docs/ECOSYSTEM.md).
---
## From this repo
This checkout is a public monorepo, not `npm install twzrd-x402-gate`. CI is
root `npm ci` then `npm run ci` (Node 20). Do **not** `npm ci` inside
`twzrd-x402-gate/` — gate typecheck needs sibling `twzrd-log-verifier` deps
from the root lockfile.
```bash
npm ci
npm run build
npm run typecheck
npm test --workspace=twzrd-x402-gate
npm run gate-eval-refuse --workspace=twzrd-x402-gate
```
`gate-eval-refuse` is the hello-world that closes (0 USDC, `signer_invocation_count: 0`).
It needs egress to `https://intel.twzrd.xyz`. Artifact dirs (`eliza-plugin/`,
`plugin-trustgate/`, `twzrd-mcp-server/`) are `dist/` mirrors — do not try to
build or demo them locally. Hosted MCP: `https://intel.twzrd.xyz/mcp`.
---
## Quickstart
### 1. Install
```bash
npm install twzrd-x402-gate@0.11.2 x402-solana@3.0.0
```
### 2. Wrap paid fetches with spend controls
```ts
import { twzrd } from "twzrd-x402-gate";
const result = await twzrd.safeFetch("https://merchant.example/paid-endpoint", {
maxSpend: "0.10", // per-call cap AND cumulative budget in USD
allowNetworks: ["solana"], // allowed settlement networks
requireOfferBinding: true, // demand an on-chain verifiable bind-v1 receipt
pay: async ({ url, paymentRequired, selected }) => {
// Your existing x402 client signs here — e.g. @x402/fetch + your signer
return await myWallet.payX402(url, paymentRequired, selected);
},
});
// On block: result.verdict === "block", result.signerInvocations === 0
```
### 3. Or hook an existing client
```ts
import { createX402Client } from "x402-solana";
import { createTwzrdBeforePaymentHook } from "twzrd-x402-gate";
const client = createX402Client({
wallet,
network: "solana",
beforePayment: createTwzrdBeforePaymentHook({ refuseWashFlaggeWhat people ask about twzrd-trust
What is twzrd-sol/twzrd-trust?
+
twzrd-sol/twzrd-trust is subagents for the Claude AI ecosystem. TWZRD buyer-side x402 trust packages: x402 trust gate, elizaOS trust plugin, and the agent-intel client. Vet a counterparty before you pay. It has 0 GitHub stars and its last recorded update is dated 2026-10-01.
How do I install twzrd-trust?
+
You can install twzrd-trust by cloning the repository (https://github.com/twzrd-sol/twzrd-trust) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is twzrd-sol/twzrd-trust safe to use?
+
Our security agent has analyzed twzrd-sol/twzrd-trust and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains twzrd-sol/twzrd-trust?
+
twzrd-sol/twzrd-trust is maintained by twzrd-sol. The last recorded GitHub activity is dated 2026-10-01, with 7 open issues.
Are there alternatives to twzrd-trust?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy twzrd-trust to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/twzrd-sol-twzrd-trust)<a href="https://claudewave.com/repo/twzrd-sol-twzrd-trust"><img src="https://claudewave.com/api/badge/twzrd-sol-twzrd-trust" alt="Featured on ClaudeWave: twzrd-sol/twzrd-trust" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
The agent engineering platform.