What is risk-attestation?

A system for creating or checking signed, short-lived records that show an agent inspected the current Bitcoin and Ethereum market-risk state before moving money.

Use it when capital movement requires proof of diligence, or when verifying a peer agent’s claim that it checked market risk.

It provides independently verifiable evidence of a recent risk check for audits, policies, insurance, or cooperation between agents.

risk-attestation — Skill for Claude Code and Codex by gblinproject

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 risk-attestation

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gblinproject/gblin-treasury-risk-regime/risk-attestation/github.svg)](https://agentmods.dev/skills/gblinproject/gblin-treasury-risk-regime/risk-attestation)

Your own site

<a href="https://agentmods.dev/skills/gblinproject/gblin-treasury-risk-regime/risk-attestation"><img src="https://agentmods.dev/badge/skills/gblinproject/gblin-treasury-risk-regime/risk-attestation/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gblinproject/gblin-treasury-risk-regime/risk-attestation"><img src="https://agentmods.dev/badge/skills/gblinproject/gblin-treasury-risk-regime/risk-attestation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,694 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.

Model	Per session	Once invoked
Fable 5.1	$0.00114	$0.01694
Opus 5	$0.00057	$0.00847
Sonnet 5	$0.00023	$0.00339
Haiku 4.5	$0.00011	$0.00169

Measured 12d ago against content hash f2d0bd73893e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

risk-attestation 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/risk-attestation/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GBLIN Risk Attestation (proof-of-diligence for autonomous agents)

When this skill applies

Trigger when:

An agent is about to move meaningful capital and wants a verifiable record that it checked market risk first (audit trail, operator policy, insurance, compliance).
A workflow, vault, or counterparty requires proof that the agent is not acting into a crashing market.
An agent receives an action from a peer agent that claims "I already checked risk" and needs to verify that claim before trusting it.
You want a risk signal that is independent and cannot be silently faked — anyone can verify it without trusting the agent that produced it.

If you only need the raw signal for your own private decision (no proof needed), use the cheaper get_market_risk_regime tool or the crash-shield-risk-management skill instead.

What a Risk Attestation is

A signed, perishable snapshot of the current market-risk regime derived from GBLIN's on-chain Crash Shield (drawdown-driven weight cuts vs Chainlink-oracle peaks on Base mainnet). Each attestation contains:

regime — calm | elevated | crash
risk_posture — risk_on | reduce | risk_off
severity_bps — how deep the drawdown-driven weight cut is
defensive_cash_bps — the defensive (USDC) allocation
block_number, issued_at, expires_at — a hard 10-minute validity window
basket_hash — binds the attestation to the exact on-chain weights it summarizes
attestation_id — the EIP-712 digest (recomputable by anyone → tamper-evident)
signature + attestor — present when GBLIN's attestor key is configured (one-step ecrecover verification)

Because it expires in 10 minutes, an action gated on a fresh attestation forces a new check every cycle. That is the point: it is a live proof, not a stale rubber stamp.

Minting one (paid, ~$0.003 USDC)

GET https://gblin.digital/api/x402/attestation

This is an x402 endpoint on Base mainnet. Flow:

Call without payment → receive HTTP 402 with payment requirements (USDC on Base, chain id 8453).
Pay via your x402 client (@x402/fetch or @x402/axios).
Retry with the payment header → receive the attestation object.

Read the full file on GitHub · 103 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.

12d ago First seen · 103 lines · 114 tokens per session scan A f2d0bd73893e

Subscribe to this mod's changes

risk-attestation is a skill published in the GitHub repository gblinproject/gblin-treasury-risk-regime (1 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 1,694 once invoked, about $0.0006 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.

Finance and fintech Security ai-agent base-mainnet defi elizaos mcp mcp-server

wealthville

Score Solana and EVM liquidity pools before providing liquidity. Returns a 0-100 pool score, an ENTER/HOLD/EXIT/REDUCE/AVOID verdict with calibrated confidence, and a public miss-inclusive track record. Use when a user asks whether a pool is worth LPing into, which pools currently look best, or how the scores have…

amitesh-m/wealthville-integrations · 77 tokens

risk-attestation

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

GBLIN Risk Attestation (proof-of-diligence for autonomous agents)

When this skill applies

What a Risk Attestation is

Minting one (paid, ~$0.003 USDC)

What this file has done since we first saw it

Other skills, from other repositories

wealthville

pump-swarm

backtest

bridge

hyperliquid

bags