Skip to main content
ClaudeWave
SubagentsRegistry oficial0 estrellas0 forksJavaScriptActualizado today
Install as a Claude Code subagent
Method: Clone
Terminal
git clone https://github.com/seekdaseek/agentfeed && cp agentfeed/*.md ~/.claude/agents/
1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
2. Start a new Claude Code session to load the agents.
3. Delegate work to them with the Task/Agent tool or by name.
Casos de uso

Resumen de Subagents

<!-- mcp-name: io.github.seekdaseek/agentfeed -->
# AgentFeed

**Crypto liquidations, cascade detection, positioning and market data for AI agents. Pay per call in USDC. No API keys, no accounts, no subscriptions.**

AgentFeed sells live trading data through the [x402 payment protocol](https://solana.com/x402) on Solana and Base. An agent hits an endpoint, gets a `402 Payment Required` with the price, pays a fraction of a cent in USDC from its own wallet, and receives the data — in about two seconds, gas sponsored by the facilitator.

Two rails, same data:

| Rail | Endpoint | For |
|------|----------|-----|
| **MCP** (Streamable HTTP) | `https://x402.ochinimus.app/mcp` | Claude, Cursor, MCP-native frameworks |
| **HTTP** (x402) | `https://x402.ochinimus.app/api/*` | Anything that speaks HTTP |

---

## What makes this different: the liquidation tape

We run our own liquidation collector across **Bybit, OKX and Binance** — every USDT-margined
perpetual on all three, roughly **600 symbols**, recorded continuously since 2026-07-08.

**This data cannot be bought.** Not from us, not from anyone:

- **Binance deleted their liquidation archive.** `liquidationSnapshot` no longer exists on
  `data.binance.vision` — the directory is an empty shell. Verified 2026-07-12.
- **Bybit has never published historical liquidation data.**
- **OKX offers a 7-day rolling REST window and nothing more.**

There is no public historical liquidation dataset for any major venue, at any price. The only
way to hold this data is to have been recording it.

### And here is exactly where our data is weak

Being straight about this matters more than the marketing:

| Venue | Feed | Complete? |
|---|---|---|
| **Bybit** | `allLiquidation` | ✅ **Yes.** Every liquidation, 500ms cadence. The only complete, unthrottled public liquidation stream among the major perp venues. |
| **Binance** | `!forceOrder@arr` | ❌ **No.** Snapshot only — max one order per symbol per 1000ms, per Binance's own docs. `allForceOrders` REST is unmaintained. |
| **OKX** | `liquidation-orders` | ❌ **No.** Max one update per second per contract. |
| **Hyperliquid** | — | ⛔ **Not included.** Hyperliquid exposes *no public liquidation stream*. `WsTrade` carries no liquidation marker; the data lives only in user-scoped streams. Capturing it requires running a node. |

**Binance and OKX rows are a structural undercount, and the undercount is worst during
cascades — exactly when the data matters most.** This is true of every liquidation dataset on
the market, including the well-known ones. Most don't say so.

**Bybit rows are the highest-integrity part of the dataset.** Weight accordingly.

### The `side` field, which most datasets get wrong

Three exchanges, three conventions. We normalize all of them:

- **Bybit** `S` is already the *position* side (`Buy` = a long was liquidated). Passed through.
- **Binance** `S` is the *order* side — a `SELL` order is what closes a long. **Flipped.**
- **OKX** exposes `posSide` explicitly. Mapped.

**In our output: `Buy` = a LONG was liquidated. `Sell` = a SHORT was liquidated.** Invert this
and every long/short ratio you compute is backwards for some venues.

Notional uses `filled_qty × avg_fill_price` — what actually executed — not `limit_price × requested_size`.

---

## Tools

| Tool | Price | Description |
| --- | --- | --- |
| get_sol_price | $0.001 | SOL spot price via Pyth |
| get_btc_price | $0.001 | BTC spot price via Pyth |
| get_funding_rate | $0.002 | SOL+BTC perp funding rates |
| get_market_snapshot | $0.003 | Full market snapshot in one call |
| get_wallet_holdings | $0.008 | Solana wallet holdings via Helius DAS |
| get_token_metadata | $0.005 | SPL token metadata via Helius DAS |
| get_recent_liquidations | $0.003 | Recent liquidations across ~600 USDT perps |
| get_cascade_alert | $0.01 | Live liquidation cascade detector for the 5 majors |
| get_cascade_scan | $0.05 | Full-universe cascade scan across ~600 USDT perps |
| get_liquidation_leaders | $0.02 | Top symbols by liquidation USD right now |
| get_liquidation_stats | $0.004 | 1h/24h liquidation totals, long/short split |
| get_positioning | $0.004 | SOL+BTC long/short ratio + open interest |
| get_trade_context | $0.01 | Full market state in one call |
| get_token_risk | $0.01 | SPL token rug-risk signals |
| get_sharp_move | $0.02 | Sharp-money detector for World Cup betting markets |
| get_liq_history | $0.05 | Historical liquidation tape, time-bucketed |
| get_liq_heatmap | $0.05 | Liquidation heatmap by price level from our tape |
| get_cascade_history | $0.03 | Past liquidation cascades from our tape |
| get_squeeze_score | $0.10 | FLAGSHIP: 0-100 short-squeeze / long-flush signal |
| get_venue_liq_share | $0.02 | Which venue is flushing whom |
| get_funding_cross | $0.01 | Funding for any USDT perp across Bybit + OKX + Hyperliquid |
| get_funding_extremes | $0.02 | Most crowded funding trades across ~600 perps |
| get_open_interest | $0.01 | Open interest for any USDT perp with 1h/24h change |
| get_oi_spike_scan | $0.02 | Abnormal open-interest jumps across ~600 perps |
| get_long_short | $0.01 | Long/short account ratio for any USDT perp |
| get_basis | $0.01 | Perp-vs-spot basis for any USDT pair |
| get_volatility | $0.01 | Realized volatility for any USDT perp |
| get_funding_history | $0.005 | Funding-rate history for any USDT perp |
| get_top_movers | $0.01 | 24h top gainers and losers across ~600 perps |
| get_orderbook_imbalance | $0.01 | Bid/ask resting-liquidity imbalance |
| get_orderbook_walls | $0.01 | Largest resting orders each side of the book |
| get_whale_trades | $0.02 | Large prints from the live trade tape |
| get_spread_arb | $0.02 | Best bid/ask across Bybit, OKX and Hyperliquid |
| get_token_holders | $0.02 | Top holders of any SPL token with concentration |
| get_wallet_activity | $0.02 | Recent transactions of any Solana wallet, parsed |
| get_priority_fees | $0.005 | Solana priority-fee estimate, all levels |
| get_jito_tips | $0.005 | Jito bundle tip floor percentiles |
| get_sol_network | $0.005 | Solana network health: TPS, slot, epoch |
| get_tvl | $0.005 | TVL for any DeFi protocol or top-15 chains |
| get_stablecoin_flows | $0.01 | Total stablecoin supply with 7d/30d deltas |
| get_dex_quote | $0.005 | Live Jupiter swap quote for any SPL pair |
| get_peg_deviation | $0.02 | Tokenized-equity peg deviation vs the underlying last trade |
| get_peg_sessions | $0.03 | Peg deviation by session: open, premarket, afterhours, overnight, weekend |
| get_peg_universe | $0.05 | Tracked tokenized equities ranked by off-hours peg risk |

## 47 tools & pricing

**44 paid tools + 3 free tasters.** Every call is metered individually in USDC over x402 — no bundles, no minimums. Calling all 44 paid tools once costs **$0.74** — the entire market read for 74 cents.

The flagship is [`get_squeeze_score`](#the-moat--our-own-liquidation-tape) — a 0-100 short-squeeze / long-flush composite built from funding, crowding, OI build and the liq-skew of our exclusive tape. One number, one dime, answers "is this trade crowded and about to hurt someone."

### The moat — our own liquidation tape

| Tool | Price | Route | What you get |
|---|---|---|---|
| `get_squeeze_score` | $0.1 | `/api/squeeze-score` | FLAGSHIP: short-squeeze / long-flush score 0-100 for any USDT perp |
| `get_liq_history` | $0.05 | `/api/liq-history` | HISTORICAL liquidation tape, time-bucketed: total/long/short USD, prints, biggest print per bucket |
| `get_liq_heatmap` | $0.05 | `/api/liq-heatmap` | Liquidation heatmap by PRICE LEVEL from our own tape: where leverage actually got flushed in the last N hours — USD, prints, long/short s… |
| `get_cascade_history` | $0.03 | `/api/cascade-history` | PAST liquidation cascades reconstructed from our tape: clustered same-side flush events with start/end, prints, USD total, peak print |
| `get_venue_liq_share` | $0.02 | `/api/venue-liq-share` | Which venue is flushing whom: per-exchange liquidation share (Bybit/OKX/Binance) with long/short split and biggest print, any symbol or w… |

### The second moat — our own tokenized-equity peg tape

| Tool | Price | Route | What you get |
|---|---|---|---|
| `get_peg_universe` | $0.05 | `/api/peg-universe` | Every tokenized US equity we track, ranked by off-hours peg risk: p95 and max deviation bps, market-open as control, median liquidity |
| `get_peg_sessions` | $0.03 | `/api/peg-sessions` | Peg deviation by trading session — open, premarket, afterhours, overnight, weekend — worst off-hours window flagged |
| `get_peg_deviation` | $0.02 | `/api/peg-deviation` | Peg deviation for one tokenized equity: on-chain DEX price vs the underlying last real trade, in bps |

Sampled every 5 minutes since 19 July 2026. Deviation is measured against the underlying's last real trade — outside US market hours that is the last print before the close, not a live quote. Dead pools are excluded rather than reported as perfect pegs.

### Live liquidations & cascades

| Tool | Price | Route | What you get |
|---|---|---|---|
| `get_recent_liquidations` | $0.003 | `/api/liquidations` | Recent liquidations across ~600 USDT perps (Bybit complete tape + OKX + Binance) |
| `get_cascade_alert` | $0.01 | `/api/cascade` | Liquidation cascade detector for the 5 majors (SOL/BTC/ETH/XRP/DOGE) across Bybit+OKX+Binance |
| `get_cascade_scan` | $0.05 | `/api/cascade-scan` | FULL-UNIVERSE cascade scan: ~600 USDT perps across Bybit+OKX+Binance |
| `get_liquidation_leaders` | $0.02 | `/api/liquidation-leaders` | What is blowing up right now: top symbols by liquidation USD across ~600 USDT perps, with long/short split, biggest print and venue count |
| `get_liquidation_stats` | $0.004 | `/api/liquidation-stats` | 1h/24h liquidation totals for the 5 majors (SOL/BTC/ETH/XRP/DOGE), long/short split, biggest print, per-exchange breakdown |

### Derivatives

| Tool | Price | Route | What you get |
|---|---|---|---|
| `get_funding_cross` | $0.01 |

Lo que la gente pregunta sobre agentfeed

¿Qué es seekdaseek/agentfeed?

+

seekdaseek/agentfeed es subagents para el ecosistema de Claude AI con 0 estrellas en GitHub.

¿Cómo se instala agentfeed?

+

Puedes instalar agentfeed clonando el repositorio (https://github.com/seekdaseek/agentfeed) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.

¿Es seguro usar seekdaseek/agentfeed?

+

seekdaseek/agentfeed aún no ha sido auditado por nuestro agente de seguridad. Revisa el repositorio original en GitHub antes de usarlo en producción.

¿Quién mantiene seekdaseek/agentfeed?

+

seekdaseek/agentfeed es mantenido por seekdaseek. La última actividad registrada en GitHub es de today, con 0 issues abiertos.

¿Hay alternativas a agentfeed?

+

Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.

Despliega agentfeed en tu cloud

Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.

¿Mantienes este repo? Añade un badge a tu README

Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.

Featured on ClaudeWave: seekdaseek/agentfeed
[![Featured on ClaudeWave](https://claudewave.com/api/badge/seekdaseek-agentfeed)](https://claudewave.com/repo/seekdaseek-agentfeed)
<a href="https://claudewave.com/repo/seekdaseek-agentfeed"><img src="https://claudewave.com/api/badge/seekdaseek-agentfeed" alt="Featured on ClaudeWave: seekdaseek/agentfeed" width="320" height="64" /></a>

Más Subagents

Alternativas a agentfeed