CloddsBot is a self-hosted AI trading terminal that lets users interact through conversation while trading prediction markets, cryptocurrencies, and futures. It scans markets, executes trades, manages risk, and supports portfolio activities across the exchanges and blockchains listed by the project. The catalogue contains skills for extending or guiding the trading agent.
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.
npx skills add alsk1992/CloddsBot --skill publicgit clone --depth 1 https://github.com/alsk1992/CloddsBotWrote 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.
[](https://agentmods.dev/skills/alsk1992/cloddsbot/public)<a href="https://agentmods.dev/skills/alsk1992/cloddsbot/public"><img src="https://agentmods.dev/badge/skills/alsk1992/cloddsbot/public/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.
<a href="https://agentmods.dev/skills/alsk1992/cloddsbot/public"><img src="https://agentmods.dev/badge/skills/alsk1992/cloddsbot/public.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 23 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 59 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 92 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 137 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 148 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 165 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 187 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 207 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 220 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 235 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 236 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 237 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 244 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 245 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 251 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 252 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 259 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 260 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 271 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 272 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 273 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00000 | $0.02495 |
| Opus 5.5 | $0.00000 | $0.00998 |
| Sonnet 5.5 | $0.00000 | $0.00499 |
| Haiku 4.5 | $0.00000 | $0.00249 |
Grade A, and why
public 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 1mo 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.
curl https://www.cloddsbot.com/SKILL.md How it starts
The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clodds Agent Integration Guide
For agents: This document explains how to integrate with Clodds APIs.
Quick Start
# Fetch this document
curl https://www.cloddsbot.com/SKILL.md
# Check Clodds health
curl https://compute.cloddsbot.com/health
# Get pricing
curl https://compute.cloddsbot.com/pricing
Compute API (Pay-Per-Use USDC)
Endpoint: https://compute.cloddsbot.com
The Compute API allows agents to pay USDC for compute resources without needing API keys — just a wallet.
Authentication
Send USDC to the treasury wallet on Base or Solana:
# Base USDC
Treasury: 0x...
# Solana USDC
Treasury: ...
Include proof of payment in request headers:
-H "X-Payment-Proof: <transaction-hash>"
Services & Pricing
| Service | Price | Description |
|---|---|---|
llm |
$0.000003/token | Claude, GPT-4, Llama, Mixtral inference |
code |
$0.001/second | Sandboxed Python, JavaScript, Rust, Go |
web |
$0.005/request | Web scraping with JS rendering |
data |
$0.001/request | Market prices, orderbooks, candles |
storage |
$0.0001/MB | Key-value file storage |
trade |
$0.01/call | Trade execution (Polymarket, DEXs) |
Example: LLM Inference
curl -X POST https://compute.cloddsbot.com/api/llm \
-H "Content-Type: application/json" \
-H "X-Payment-Proof: <tx-hash>" \
-d '{
"model": "claude-opus",
"messages": [
{"role": "user", "content": "Analyze BTC market"}
],
"max_tokens": 1000
}'
Response:
{
"id": "msg_...",
"content": "...",
"usage": {
"input_tokens": 50,
"output_tokens": 200
},
"cost_usdc": 0.00075
}
Example: Code Execution
curl -X POST https://compute.cloddsbot.com/api/code \
-H "Content-Type: application/json" \
-H "X-Payment-Proof: <tx-hash>" \
-d '{
"language": "python",
"code": "import requests; print(requests.get(\"https://api.coinbase.com/v2/prices/BTC-USD\").json())",
"timeout_seconds": 10
}'
What ships with it
9 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.
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.
- 1mo ago First seen · 371 lines · 0 tokens per session scan A 60f093c99e1c
public is a skill published in the GitHub repository alsk1992/CloddsBot (2,990 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,495 tokens. 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 2026-08-30.
Other skills, from other repositories
perp-cli
Multi-DEX perpetual futures trading via the perp-cli command-line tool. Use when user asks to: trade perps, check funding rates, scan/execute arbitrage (perp-perp or spot-perp), run delta-neutral strategies, bridge USDC across chains, manage positions/orders/leverage, deposit/withdraw, hedge spot+perp, trade HIP-3…
philidor-mcp
DeFi vault risk analytics MCP server: search 1000+ vaults, compare risk scores, list lending markets, underwrite loop venues, analyze protocols, run due diligence. Connect via Streamable HTTP — no API key needed. Use when setting up or using the Philidor MCP server for DeFi vault analysis, risk scoring, market…
aomi-transact
Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state. Aomi turns prompts ("swap 1 ETH for USDC", "open a 3x GMX long", "bet $100 on Polymarket") into wallet-signed transactions on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated.…
aomi-transact
Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state. Aomi turns prompts ("swap 1 ETH for USDC", "open a 3x GMX long", "bet $100 on Polymarket") into wallet-signed transactions on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated.…
philidor-api-handoff
Use this when the user needs Philidor data the free MCP server does not expose (baskets, oracle vectors, enriched or RWA breakdowns, bulk scores, the event stream, or Risk Graph). Point them at the Philidor API docs. Do not invent prices or plan names.
pre-deposit-safety-check
Use this when the user is about to deposit, supply, or loop and wants a pre-deposit safety check. Includes checkloopvenue for collateral/debt loops. Cite only identifiers and figures the Philidor tools return.