divergence

divergence is a skill for Claude Code, Codex from alsk1992/CloddsBot. It costs 17 tokens per session (727 once invoked), scanned A, original, MIT.

A trading tool that compares Binance spot prices with Polymarket’s 15-minute crypto prediction markets. It looks for cases where the prediction market has not yet reflected a spot-price move.

In plain words
What is it for?
Starting and stopping monitoring for selected assets, viewing positions and market data, checking statistics, and configuring trade size, profit targets, loss limits, and detection windows.
Why use it?
It automates monitoring for this specific price delay and starts in dry-run mode, which simulates trades without placing real orders.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/alsk1992/cloddsbot/divergence
Any agent
npx skills add alsk1992/CloddsBot --skill divergence
Clone the repo
git clone --depth 1 https://github.com/alsk1992/CloddsBot

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 divergence

README.md
[![agentmods](https://agentmods.dev/badge/skills/alsk1992/cloddsbot/divergence.svg)](https://agentmods.dev/skills/alsk1992/cloddsbot/divergence)
Your own site
<a href="https://agentmods.dev/skills/alsk1992/cloddsbot/divergence"><img src="https://agentmods.dev/badge/skills/alsk1992/cloddsbot/divergence.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 727 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00727
Opus 5 $0.00009 $0.00364
Sonnet 5 $0.00003 $0.00145
Haiku 4.5 $0.00002 $0.00073

Measured 5d ago against content hash fd14f5b96c02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

divergence 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (index.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/skills/bundled/divergence/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Divergence Trading - Spot vs Poly Price Lag

Detects when Binance spot prices move but Polymarket 15-minute binary markets haven't caught up yet. Buys the lagging side and sells when it corrects.

Strategy tags match the CLAUDE.md encoding: BTC_DOWN_s12-14_w15 (0.12-0.14% move in 15s window).

Starts in dry-run mode by default (no real orders).

Quick Start

/div start                     # Dry-run on BTC,ETH,SOL,XRP
/div start BTC,ETH --size 30   # Specific assets + size
/div status                    # Stats, open positions
/div stop                      # Stop and show summary

Commands

Start / Stop

/div start [ASSETS] [--size N] [--dry-run]
/div stop

Monitor

/div status       Stats + open positions + round info
/div positions    Last 20 closed trades with strategy tags
/div markets      Active 15-min markets from Gamma API

Configure

/div config                           Show current config
/div config --tp 20 --sl 30          Set TP/SL %
/div config --size 50                 Set trade size
/div config --windows 5,10,30         Set detection windows

Detection Algorithm

For each spot tick, across all configured windows (5s, 10s, 15s, 30s, 60s, 90s, 120s):

  1. Look up spot price N seconds ago via binary search
  2. Calculate spotMovePct = (now - then) / then * 100
  3. If move >= threshold AND poly is fresh (< 5s stale):
    • Generate signal with strategy tag: {ASSET}_{DIR}_s{bucket}_w{window}
    • e.g., BTC_DOWN_s12-14_w15 = 0.12-0.14% spot drop over 15s

Threshold Buckets

Bucket Spot Move Range
s08-10 0.08% - 0.10%
s10-12 0.10% - 0.12%
s12-14 0.12% - 0.14%
s14-16 0.14% - 0.16%
s16-20 0.16% - 0.20%
s20+ 0.20%+

Exit Logic

  1. Force exit — < 30s before market expiry
  2. Take profit — PnL >= 15% (configurable)
  3. Stop loss — PnL <= -25% (configurable)
  4. Trailing stop — Activated at +10%, exits if drops 8% from HWM
  5. Time exit — < 2min before expiry

Read the full file on GitHub · 84 lines

Files

What ships with it

1 file 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. 5d ago First seen · 84 lines · 17 tokens per session scan A fd14f5b96c02

Subscribe to this mod's changes

divergence is a skill published in the GitHub repository alsk1992/CloddsBot (869 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 727 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

hive-defi-research

Use this skill when the user asks about DeFi protocol metrics — TVL, fees, revenue, yields, APY, stablecoin supply, bridge volume, or chain-level DeFi totals — or wants protocols compared ("Aave vs Compound", "top protocols by TVL", "best stablecoin yields"). Use it whenever the answer needs current protocol-level…

hive-intel/hive-sdk · 106 tokens

hive-market-research

Use this skill for any live crypto market question — prices, 24h moves, liquidity, exchange/venue data, OHLC candles, order books, tickers, funding rates, derivatives, trading context — even casual asks like "what's BTC at" or "is ETH pumping". Use it whenever the answer needs current market numbers instead of memory.…

hive-intel/hive-sdk · 109 tokens

hive-query

Default entry point for any live crypto question when Hive MCP is connected — prices, wallets, tokens, DeFi, NFTs, Solana, security, markets, DEX, networks, prediction markets. Use it whenever the answer depends on live or on-chain data instead of answering from memory, even if the user never mentions Hive. Routes…

hive-intel/hive-sdk · 119 tokens

hive-token-diligence

Use this skill whenever the user asks whether a specific token is real, legit, liquid, well-held, enriched, investable, or worth researching — "is this token a scam", "run diligence on 0x…", "who holds this", "does it have real liquidity" — even if they never say "diligence". Investigates metadata, market context…

hive-intel/hive-sdk · 147 tokens

hive-wallet-investigation

Use this skill whenever the user wants to look inside a wallet or address — portfolio, holdings, balances, transfers, PnL, NFT exposure, DeFi positions, whale moves, "what does this address hold", "trace this wallet's activity" — even if they just paste an address. Requires wallet address and chain before executing…

hive-intel/hive-sdk · 101 tokens

0xarchive

Query historical and real-time crypto market data from 0xArchive across two top-level venue APIs: Hyperliquid and Lighter.xyz. HIP-3 builder perps live under the Hyperliquid namespace at /v1/hyperliquid/hip3. HIP-4 outcome markets (binary prediction markets like 'Will BTC be >= X by date Y?') live at…

0xArchiveIO/0xarchive-skill · 310 tokens