gblin-agent-treasury

gblin-agent-treasury is a skill for Claude Code from gblinproject/gblin-treasury-risk-regime. It costs 133 tokens per session (811 once invoked), scanned A, original, MIT.

A command-line treasury for an AI agent on Base, a blockchain network. It keeps operating cash in USDC, a dollar-pegged token, and can place surplus funds in GBLIN, an on-chain index of cbBTC, WETH, and USDC.

In plain words
What is it for?
It is for checking treasury status, setting wallet and spending policies, moving surplus USDC into GBLIN, refilling USDC when needed, and paying x402 invoices with automatic refills.
Why use it?
It manages the difference between money needed for immediate payments and surplus funds, while warning that GBLIN is volatile and is not a stablecoin replacement.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It is for checking treasury status, setting wallet and spending policies, moving surplus USDC into GBLIN, refilling USDC when needed, and paying x402 invoices with automatic refills.

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

Made for: Claude Code.

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 gblin-agent-treasury

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gblinproject/gblin-treasury-risk-regime/gblin-agent-treasury"><img src="https://agentmods.dev/badge/skills/gblinproject/gblin-treasury-risk-regime/gblin-agent-treasury.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 811 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00133 $0.00811
Opus 5.5 $0.00053 $0.00324
Sonnet 5.5 $0.00027 $0.00162
Haiku 4.5 $0.00013 $0.00081

Measured 21d ago against content hash 5dd610952f8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gblin-agent-treasury scanned grade A with 1 finding 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 21d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: ["Bash(npx @gblin-protocol/[email protected] *)", "Bash(npm *)", "Bash(node *)", "Bash(curl *)"]
skills/gblin-agent-treasury/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GBLIN Agent Treasury

Operate the treasury through the gblin-treasury CLI (npx @gblin-protocol/[email protected]). This skill is a router: read the reference in references/ for the task at hand before acting.

The policy in one sentence: operating cash stays in USDC, the surplus above the reserve is parked in GBLIN, and USDC is pulled back from GBLIN just in time when a payment needs it. GBLIN is a volatile index, not a stablecoin substitute.

Preflight

Every command except a read-only status needs the agent's private key in GBLIN_AGENT_PRIVATE_KEY. Check the state first:

npx @gblin-protocol/[email protected] status --json

If it fails with GBLIN_AGENT_PRIVATE_KEY must be…, read references/setup.md.

Routing

Task Reference
Configure the wallet key, the RPC endpoint and the policy (reserve, caps, risk gate) references/setup.md
Balances, NAV, surplus, regime, cooldown, "can I park now" references/status.md
Park idle USDC above the reserve into GBLIN references/park.md
Make sure the wallet holds N USDC, refilling from GBLIN if short references/ensure-usdc.md
Pay an x402 endpoint from the treasury, with automatic refill and a price cap references/pay.md
Use the treasury from TypeScript (viem, AgentKit, any wallet provider) instead of the CLI references/library.md

Shared rules

  • Input validation: amounts must match ^\d+(\.\d+)?$; URLs must start with https:// or http:// and contain no spaces, semicolons, pipes, backticks or $; --max-amount must match ^\d+$ (atomic USDC units, 1000000 = 1 USDC). Do not pass unvalidated user input into a command.
  • JSON output: every command supports --json; read action, reason and txHashes from it.
  • Refusals are answers: park returning action: "none" and ensure-usdc failing on the cooldown are the policy working, not errors to retry blindly. Report the reason.
  • Money moves on Base mainnet: every park, ensure-usdc and paid pay sends real transactions from the agent's wallet. Show the user the amounts before acting when the instruction did not already fix them.
  • Never print the private key, and never place it in a command line: it is read from the environment only.

Read the full file on GitHub · 43 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 21d ago First seen · 43 lines · 133 tokens per session scan A 5dd610952f8b

Subscribe to this mod's changes

gblin-agent-treasury is a skill published in the GitHub repository gblinproject/gblin-treasury-risk-regime (1 stars, last pushed 15d ago), licensed MIT. It adds 133 tokens to every session and 811 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-28.