worldcup-linelock

worldcup-linelock is a skill for Claude Code, Codex from edycutjong/linelock. It costs 121 tokens per session (1,250 once invoked), scanned A, original, MIT.

A coding-agent skill for buying World Cup knockout betting picks from LineLock and checking a tipster’s settled record. It uses Injective, a blockchain network, and USDC, a digital dollar token, for payment.

In plain words
What is it for?
Use it to request the next knockout pick, pay per call without an API key, check a USDC balance, and audit a tipster’s public record.
Why use it?
It gives you a way to compare a model’s probability with market odds and verify when a paid pick was issued. It also lets you review losses and results using closing-line value, which compares a tip to the final market price.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to request the next knockout pick, pay per call without an API key, check a USDC balance, and audit a tipster’s public record.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/edycutjong/linelock/worldcup-linelock
Install

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.

Any agent
npx skills add edycutjong/linelock --skill worldcup-linelock
Clone the repo
git clone --depth 1 https://github.com/edycutjong/linelock

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for worldcup-linelock

README.md
[![agentmods](https://agentmods.dev/badge/skills/edycutjong/linelock/worldcup-linelock/github.svg)](https://agentmods.dev/skills/edycutjong/linelock/worldcup-linelock)
Your own site
<a href="https://agentmods.dev/skills/edycutjong/linelock/worldcup-linelock"><img src="https://agentmods.dev/badge/skills/edycutjong/linelock/worldcup-linelock/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.

agentmods 80×15 button for worldcup-linelock

Your own site · 80×15
<a href="https://agentmods.dev/skills/edycutjong/linelock/worldcup-linelock"><img src="https://agentmods.dev/badge/skills/edycutjong/linelock/worldcup-linelock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.01250
Opus 5.5 $0.00048 $0.00500
Sonnet 5.5 $0.00024 $0.00250
Haiku 4.5 $0.00012 $0.00125

Measured 1mo ago against content hash e5164dde3224, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

worldcup-linelock 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 1mo 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.

skills/worldcup-linelock/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

worldcup-linelock

Teach any harness (Claude Code / Cursor / Codex) to be a buyer on LineLock: a pay-per-pick World Cup edge API on Injective EVM where the x402 USDC receipt IS the pick's pre-kickoff timestamp, plus a free public ledger that CLV-scores every settled pick (losses included).

Install:

npx skills add https://github.com/edycutjong/linelock --skill worldcup-linelock

Config: set LINELOCK_API (default https://linelock.edycu.dev) and, to pay, OPS_WALLET_PK (a funded Injective EVM key holding USDC).

When to use

  • "Get me the next World Cup knockout edge / pick."
  • "Is this tipster real? Check their CLV." → read the free ledger, no payment.
  • "Pay for the edge and prove the receipt predates kickoff."

The flow (4 steps)

1. Check USDC balance (Injective MCP server — free, no payment)

Use the Injective MCP server (InjectiveLabs/mcp-server, stdio, INJECTIVE_NETWORK=mainnet):

  • account_balances { address } → confirm ≥ 0.05 USDC on Injective.
  • usdc_native_info → the USDC contract address + decimals used by the quote (do not hardcode from docs; pin from here).
  • If low, fund via CCTP: cctp_supported_chains → burn on Base (domain 6) → cctp_attestation_status → cctp_mint on Injective. address_normalize converts inj1… ↔ 0x… for display.

2. Pay the x402 quote (first-party client — never hand-roll signing)

POST {LINELOCK_API}/api/edge         # no payment header → HTTP 402 + quote

The 402 body (and the PAYMENT-REQUIRED base64 header) is an x402 v2 PaymentRequired: accepts[0] = { network: "eip155:1776", asset: <USDC>, amount: "50000", payTo, scheme: "exact" }. Pay with the shipped client:

import { createInjectiveClient, parsePaymentResponseHeader } from '@injectivelabs/x402/client';
const client = createInjectiveClient({ privateKey: process.env.OPS_WALLET_PK,
  preferredNetworks: ['eip155:1776'], defaultToken: 'USDC' });
const res = await client.fetch(`${API}/api/edge`, { method: 'POST' }); // auto-handles the 402
const receipt = parsePaymentResponseHeader(res); // { success, transaction, network, payer }

receipt.transaction is the on-chain tx — its block time is your pre-kickoff proof (verify on Blockscout: https://blockscout.injective.network/tx/<tx>). The repo's scripts/buyer.ts implements exactly this (run npm run buyer for the free 402-parse path, -- --pay to pay).

Read the full file on GitHub · 97 lines

Changes

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.

  1. 1mo ago First seen · 97 lines · 121 tokens per session scan A e5164dde3224

Subscribe to this mod's changes

worldcup-linelock is a skill published in the GitHub repository edycutjong/linelock (0 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 1,250 once invoked, about $0.0005 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.