crypto-risk

crypto-risk is a skill for Claude Code, Codex from zubair-trabzada/ai-crypto-claude. It costs 50 tokens per session (7,929 once invoked), scanned A, original, MIT.

A cryptocurrency risk-analysis workflow that examines a token’s market, technical, legal, concentration, and supply-release risks.

In plain words
What is it for?
Assessing volatility, drawdowns, liquidity, smart contracts, regulation, whale ownership, token unlocks, and risk-aware investment amounts for a specified token.
Why use it?
It organizes several sources of crypto risk in one assessment and helps relate them to possible position sizes. It is for research, not financial advice.

Skill for Claude CodeCodex

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

Good fit Assessing volatility, drawdowns, liquidity, smart contracts, regulation, whale ownership, token unlocks, and risk-aware investment amounts for a specified token.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zubair-trabzada/ai-crypto-claude/crypto-risk
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 zubair-trabzada/ai-crypto-claude --skill crypto-risk
Clone the repo
git clone --depth 1 https://github.com/zubair-trabzada/ai-crypto-claude

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 crypto-risk

README.md
[![agentmods](https://agentmods.dev/badge/skills/zubair-trabzada/ai-crypto-claude/crypto-risk/github.svg)](https://agentmods.dev/skills/zubair-trabzada/ai-crypto-claude/crypto-risk)
Your own site
<a href="https://agentmods.dev/skills/zubair-trabzada/ai-crypto-claude/crypto-risk"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-crypto-claude/crypto-risk/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 crypto-risk

Your own site · 80×15
<a href="https://agentmods.dev/skills/zubair-trabzada/ai-crypto-claude/crypto-risk"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-crypto-claude/crypto-risk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,929 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 $0.00050 $0.07929
Opus 5 $0.00025 $0.03964
Sonnet 5 $0.00010 $0.01586
Haiku 4.5 $0.00005 $0.00793

Measured 12d ago against content hash e41d28577e75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

crypto-risk 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/crypto-risk/SKILL.md · 715 lines

How it starts

The opening of the file, as written. The whole thing — 715 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Risk Assessment & Position Sizing

You are the Risk Assessment agent for the AI Crypto Analyst system. When invoked via /crypto risk <token>, you produce a comprehensive risk analysis covering historical volatility, drawdown scenarios, correlation dynamics, liquidity risk, smart contract risk, regulatory exposure, whale concentration, and token unlock schedules — plus crypto-specific position sizing calculators.

DISCLAIMER: For educational/research purposes only. Not financial advice. Cryptocurrency is highly volatile. Always DYOR.

Trigger

This skill activates when the user runs:

  • /crypto risk <token> (e.g., /crypto risk ETH, /crypto risk AVAX)
  • Also invoked as a subagent during /crypto analyze <token>

Input Processing

  1. Parse the token ticker from the command
  2. Normalize the ticker (e.g., "ethereum" -> "ETH", "sol" -> "SOL")
  3. Detect the token category (L1, L2, DeFi, Meme, AI/DePIN, RWA, etc.)
  4. Determine risk context:
    • Blue-chip crypto (BTC, ETH) -> Lower baseline risk, still volatile vs traditional assets
    • Large-cap alt (SOL, AVAX, ADA, DOT) -> Moderate baseline risk
    • Mid-cap ($500M-$5B mcap) -> Higher baseline risk, thinner liquidity
    • Small-cap ($50M-$500M mcap) -> High risk, potential for large drawdowns
    • Micro-cap (<$50M mcap) -> Very high risk, extreme volatility, low liquidity
    • Meme token -> Maximum risk category regardless of market cap

Data Collection

Phase 1: Risk Data Gathering

Use WebSearch and WebFetch to collect data from these sources:

PRIORITY DATA SOURCES:
1. CoinGecko/CoinMarketCap — Price history, volatility data, market cap, volume
2. Coinglass — Liquidation data, funding rates, open interest, long/short ratios
3. DeFiLlama — TVL, protocol revenue (for DeFi risk assessment)
4. Token Unlocks (token.unlocks.app) — Upcoming vesting schedules, cliff dates
5. Arkham Intelligence / Nansen summaries — Whale wallet concentrations
6. DefiSafety / audit databases — Smart contract audit status
7. Rekt.news — Historical exploit and hack records
8. Exchange listings pages — Which exchanges list the token
9. CryptoQuant / Glassnode summaries — Exchange flows, whale behavior
10. Regulatory news sources — SEC filings, regulatory actions, compliance status

Read the full file on GitHub · 715 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 · 715 lines · 50 tokens per session scan A e41d28577e75

Subscribe to this mod's changes

crypto-risk is a skill published in the GitHub repository zubair-trabzada/ai-crypto-claude (48 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 7,929 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 2026-08-30.