earn-as-base-keeper

earn-as-base-keeper is a skill for Claude Code, Codex from gblinproject/gblin-treasury-risk-regime. It costs 67 tokens per session (1,113 once invoked), scanned A, original, MIT.

A guide for earning ETH by calling profitable treasury rebalancing jobs on Base, a blockchain network.

In plain words
What is it for?
It is for agents with a funded wallet that want to find and execute GBLIN rebalancing tasks on Base.
Why use it?
It explains how an agent can receive a caller reward while paying the transaction fee needed to perform the job.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit It is for agents with a funded wallet that want to find and execute GBLIN rebalancing tasks on Base.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gblinproject/gblin-treasury-risk-regime/earn-as-base-keeper
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 gblinproject/gblin-treasury-risk-regime --skill earn-as-base-keeper
Clone the repo
git clone --depth 1 https://github.com/gblinproject/gblin-treasury-risk-regime

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 earn-as-base-keeper

README.md
[![agentmods](https://agentmods.dev/badge/skills/gblinproject/gblin-treasury-risk-regime/earn-as-base-keeper/github.svg)](https://agentmods.dev/skills/gblinproject/gblin-treasury-risk-regime/earn-as-base-keeper)
Your own site
<a href="https://agentmods.dev/skills/gblinproject/gblin-treasury-risk-regime/earn-as-base-keeper"><img src="https://agentmods.dev/badge/skills/gblinproject/gblin-treasury-risk-regime/earn-as-base-keeper/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 earn-as-base-keeper

Your own site · 80×15
<a href="https://agentmods.dev/skills/gblinproject/gblin-treasury-risk-regime/earn-as-base-keeper"><img src="https://agentmods.dev/badge/skills/gblinproject/gblin-treasury-risk-regime/earn-as-base-keeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,113 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 $0.00067 $0.01113
Opus 5 $0.00034 $0.00557
Sonnet 5 $0.00013 $0.00223
Haiku 4.5 $0.00007 $0.00111

Measured 12d ago against content hash 66685fb85055, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

earn-as-base-keeper 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 12d 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/earn-as-base-keeper/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Earn as a Base Keeper (GBLIN Rebalance Bounties)

When this skill applies

Trigger when:

  • An AI agent wants to generate passive income on Base mainnet
  • The user asks "how can my agent earn ETH on-chain?"
  • An agent is looking for keeper / automation jobs (like Gelato, Keep3r, Chainlink Automation)
  • An agent has a funded wallet and can pay gas but wants net-positive returns

The opportunity

Most x402 and DeFi services CHARGE agents to use them. The GBLIN protocol on Base is one of the few that PAYS agents.

GBLIN is a treasury-backed index (cbBTC / WETH / USDC). When its on-chain allocation drifts from target, anyone can call incentivizedRebalance to bring it back in line. The contract:

  1. Executes the rebalancing swap using ITS OWN funds (the caller provides no capital)
  2. Pays the caller a reward of 0.0001 ETH from the stability fund

The caller only pays gas (~$0.01 on Base). Net profit per successful rebalance is roughly the reward minus gas.

Contract: 0x36C81d7E1966310F305eA637e761Cf77F90852f0 (Base mainnet, chain id 8453)

How to earn (step by step)

Option A — via the GBLIN MCP server (easiest)

If you have the GBLIN MCP server connected (npm install -g @gblin-protocol/mcp-server), call the tool:

find_keeper_bounty

It returns either:

  • bountyAvailable: false with a reason (pool balanced, or fund too low) — check again later, or
  • bountyAvailable: true with ready-to-send calldata, the target contract, value: "0", and the estimatedRewardEth.

If a bounty is available, send a transaction with that calldata to the target contract from your funded wallet. After confirmation, the reward arrives in your wallet.

Option B — direct on-chain (no MCP)

Read the contract state and compute the imbalance yourself:

import { createPublicClient, createWalletClient, http } from 'viem';
import { privateKeyToAccount } from 'viem/accounts';
import { base } from 'viem/chains';

const GBLIN = '0x36C81d7E1966310F305eA637e761Cf77F90852f0';

// 1. Read basket(i) for each asset: token, oracle, dynamicWeight
// 2. Read each asset's balanceOf(GBLIN) and Chainlink price via latestRoundData
// 3. Compute totalEthValue and per-asset target vs current allocation
// 4. If an asset's current ETH value differs from target by more than
//    max(wethBalance/100, 0.01 ETH), a rebalance is available
// 5. Build incentivizedRebalance(assetIndex, isWethToAsset, amountToSwap)
// 6. Send the tx; receive 0.0001 ETH reward on success

Read the full file on GitHub · 89 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. 12d ago First seen · 89 lines · 67 tokens per session scan A 66685fb85055

Subscribe to this mod's changes

earn-as-base-keeper is a skill published in the GitHub repository gblinproject/gblin-treasury-risk-regime (1 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,113 once invoked, about $0.0003 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.