burner-wallet

burner-wallet is a skill for Claude Code, Codex from sepivip/SeekerClaw. It costs 91 tokens per session (2,711 once invoked), scanned A, original, MIT.

A small Solana wallet managed by an app that can sign transactions within spending limits. Its private key stays in Android’s encrypted key storage and is never passed to the Node.js agent.

In plain words
What is it for?
Use it for capped autonomous spending, paid API payments using x402, recurring purchases, and price-triggered orders; use the main wallet for larger or explicitly approved transfers.
Why use it?
It allows approved small or recurring payments without a confirmation popup while keeping larger transfers under the main wallet’s user approval flow.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: positional $N argument; built for openclaw.

Good fit Use it for capped autonomous spending, paid API payments using x402, recurring purchases, and price-triggered orders; use the main wallet for larger or explicitly approved transfers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sepivip/seekerclaw/burner-wallet
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 sepivip/SeekerClaw --skill burner-wallet
Clone the repo
git clone --depth 1 https://github.com/sepivip/SeekerClaw

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 burner-wallet

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sepivip/seekerclaw/burner-wallet"><img src="https://agentmods.dev/badge/skills/sepivip/seekerclaw/burner-wallet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,711 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00091 $0.02711
Opus 5 $0.00046 $0.01355
Sonnet 5 $0.00018 $0.00542
Haiku 4.5 $0.00009 $0.00271

Measured 11d ago against content hash a0e13bc6facd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

burner-wallet 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 11d 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.

app/src/main/assets/default-skills/burner-wallet/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Burner Wallet

The burner wallet is a small, app-managed Solana wallet that lives inside SeekerClaw. Its private key is stored encrypted in Android's KeyVault and never crosses the bridge into the Node.js agent. The agent can ask the bridge to sign transactions on its behalf — but only within caps the user controls.

When to use the burner vs the main wallet

Situation Wallet
Small autonomous spend (<= per-tx cap) Burner — silent, no popup
x402 payment for a paid API Burner — autonomous by design
Recurring DCA inside daily cap Burner
Price-triggered limit order inside cap Burner
Large transfer (> per-tx cap) Main — requires user popup
User says "send from my wallet" / "approve in Phantom" Main
User explicitly opts into popup Main
Burner not configured Main (only choice)

The agent does not decide routing — caps/preflight.js does, based on cap math. The agent's job is to USE the right wallet semantics in conversation:

"I'll send 0.001 SOL from your Burner wallet — that's under your 0.05 per-tx cap, so it goes through silently."

"0.5 SOL is over your burner per-tx cap. I can either raise the cap (let me know your new limit) or send it from your Main wallet (that'll pop your wallet app for approval)."

Never paraphrase as "your wallet" — always say "Burner wallet" or "Main wallet" so the user knows which is signing.

Caps

The burner has four caps, all stored as atomic units (lamports for SOL, microunits for USDC):

  • per_tx_sol: max SOL per single transaction
  • per_tx_usdc: max USDC per single transaction
  • daily_sol: max SOL spent in a 24-hour window (UTC midnight rollover)
  • daily_usdc: max USDC spent in a 24-hour window (UTC midnight rollover)

A transaction must pass BOTH per-tx AND daily checks to route through the burner. Above either cap, the agent gets a "block" decision and must propose either a cap raise or a main-wallet fallback.

Read the full file on GitHub · 158 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. 11d ago First seen · 158 lines · 91 tokens per session scan A a0e13bc6facd

Subscribe to this mod's changes

burner-wallet is a skill published in the GitHub repository sepivip/SeekerClaw (314 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 2,711 once invoked, about $0.0005 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 2026-08-30.