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 marginfigit 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/marginfi)<a href="https://agentmods.dev/skills/alsk1992/cloddsbot/marginfi"><img src="https://agentmods.dev/badge/skills/alsk1992/cloddsbot/marginfi/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/marginfi"><img src="https://agentmods.dev/badge/skills/alsk1992/cloddsbot/marginfi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00011 | $0.00358 |
| Opus 5.5 | $0.00004 | $0.00143 |
| Sonnet 5.5 | $0.00002 | $0.00072 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
marginfi 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 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.
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.
What it actually says
MarginFi
MarginFi is a lending and borrowing protocol on Solana. Deposit collateral, borrow assets, and monitor your health factor to avoid liquidation.
Commands
Lending
/marginfi deposit <amount> <token> Deposit collateral
/marginfi withdraw <amount|all> <token> Withdraw collateral
/marginfi borrow <amount> <token> Borrow assets
/marginfi repay <amount|all> <token> Repay borrowed assets
Account
/marginfi account View positions (deposits & borrows)
/marginfi health Check health factor & liquidation risk
Markets
/marginfi banks List all lending pools with APY
/marginfi rates View supply/borrow interest rates table
Examples
/marginfi deposit 100 USDC
/marginfi borrow 1 SOL
/marginfi health
/marginfi repay all SOL
/marginfi withdraw all USDC
/marginfi banks
/marginfi rates
Configuration
export SOLANA_PRIVATE_KEY="your-base58-private-key"
export SOLANA_RPC_URL="https://api.mainnet-beta.solana.com" # Optional
See Also
/kamino— Kamino Finance lending + liquidity vaults/solend— Solend lending protocol/jup— Jupiter DEX aggregator/bags— Portfolio overview
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.
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 · 63 lines · 11 tokens per session scan A 3ab822b490a2
marginfi is a skill published in the GitHub repository alsk1992/CloddsBot (2,990 stars, last pushed 18d ago), licensed MIT. It adds 11 tokens to every session and 358 once invoked, about $0.0000 per session on Opus 5.5. 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.
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…
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.
market-incident-monitoring
Use this when the user wants lending-market monitoring, a market overview, recent market events, protocol incident history, or which vaults had a critical incident. Cite only identifiers and figures the Philidor tools return.
risk-adjusted-yield
Use this when the user wants a risk-adjusted yield comparison across DeFi vaults: APR next to Philidor score, tier, TVL, and whether deposits are open. Cite only identifiers and figures the Philidor tools return.