crash-shield-risk-management

crash-shield-risk-management is a skill for Claude Code, Codex from gblinproject/gblin-treasury-risk-regime. It costs 54 tokens per session (1,105 once invoked), scanned A, original, MIT.

A guide to using GBLIN's Crash Shield, an on-chain signal that tracks large price drops in certain crypto assets.

In plain words
What is it for?
Use it when protecting or hedging capital, reading the Crash Shield status, identifying affected assets, and choosing between normal, cautious, or risk-off actions.
Why use it?
It gives an agent a defined market signal for reacting conservatively to sharp declines instead of relying only on opinions or general sentiment.

Skill for Claude CodeCodex

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

Good fit Use it when protecting or hedging capital, reading the Crash Shield status, identifying affected assets, and choosing between normal, cautious, or risk-off actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gblinproject/gblin-treasury-risk-regime/crash-shield-risk-management
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 crash-shield-risk-management
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 crash-shield-risk-management

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gblinproject/gblin-treasury-risk-regime/crash-shield-risk-management"><img src="https://agentmods.dev/badge/skills/gblinproject/gblin-treasury-risk-regime/crash-shield-risk-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,105 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 $0.00054 $0.01105
Opus 5 $0.00027 $0.00553
Sonnet 5 $0.00011 $0.00221
Haiku 4.5 $0.00005 $0.00111

Measured 12d ago against content hash 81149992a25c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

crash-shield-risk-management 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/crash-shield-risk-management/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crash Shield Risk Management

When this skill applies

Trigger when:

  • The user wants the agent to defend capital during market crashes
  • The agent is leveraging or hedging positions
  • The user asks "how do I make my agent crash-resistant?"
  • The user wants a market sentiment signal that's algorithmic, not opinion-based

What Crash Shield is

GBLIN's Crash Shield is an on-chain algorithmic indicator. The protocol tracks the peak price of each basket asset (cbBTC, WETH) over time. When the current Chainlink-reported price draws down past the adaptive threshold (from ~15%, scaling with volatility and decaying peaks in V6), the Crash Shield activates and rebalances allocations toward USDC.

This means: crashShieldActive: true is a high-confidence on-chain signal that significant market drawdown has occurred. It's not opinion-based, not lagging like sentiment indexes, and not subject to manipulation (the underlying data is Chainlink oracles).

How to read it

async function getMarketRiskSignal(): Promise<{
  shieldActive: boolean;
  affectedAssets: string[];
  signal: 'normal' | 'caution' | 'risk-off';
}> {
  const response = await fetch('https://gblin.digital/api/x402/treasury-state');
  const state = await response.json();
  // Note: treasury-state is x402-paywalled at $0.001
  // For free polling, parse the llms.txt at /api/x402/llms.txt

  const affected = state.basket
    .filter((a: any) => a.dynamicWeight < a.weight)
    .map((a: any) => a.token);

  return {
    shieldActive: state.crashShieldActive,
    affectedAssets: affected,
    signal: state.crashShieldActive ? 'risk-off' : 'normal',
  };
}

Risk-off actions for autonomous agents

When crashShieldActive: true:

  1. Pause new leveraged positions. Do not open new long positions on volatile assets.

  2. Tighten stop losses on existing positions. Reduce stop loss distance by 50%.

  3. Increase USDC allocation. Shift 20-30% of any productive treasury (Morpho lending in cbBTC, etc.) back to USDC.

Read the full file on GitHub · 109 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 · 109 lines · 54 tokens per session scan A 81149992a25c

Subscribe to this mod's changes

crash-shield-risk-management is a skill published in the GitHub repository gblinproject/gblin-treasury-risk-regime (1 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 1,105 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.