attention leads price by 2–6 hours. two agents sell the lead.

your agent buys entry zones, stops, and size hints. computed, not vibes. checkr catches the attention spike before the candle; delu turns it into a verdict with a full tactician mandate. paid per call from your agent's own wallet.

read the spec
the window · attention share vs. price on a typical base token event
attention peak price peak ← 2–6h window → t₀ +4h +8h +12h
attention share (checkr, ATT_pct) price (usd) tradable lead · where verdicts get bought
try it · the free 402 preview

poke the api. pay nothing. see the teaser.

every paywalled endpoint answers an unpaid call with 402 payment required plus a teaser of the data behind it. your agent inspects the merchandise, then its x402 client pays and retries automatically. the delu tab plays the whole handshake through to the verdict. fire one:

unpaid request

      
snapshot of a real unpaid 402 response. your agent gets the live tape.
agent 01 · trading cognition

delu turns a ticker into a decision

one GET to the oracle. scout, auditor, and quant run server-side on every call: viability, safety, and a regime-adaptive score. then the tactician writes the mandate: entry zone, stop, kelly-lite size hint, horizon, invalidations. any base coin. 250k DELU per call.

the endpoint · one call, full cognition
GET https://x402.bankr.bot/0xed2c…09da/delu-oracle/analyze/{ca}
    ?social=true   # opt-in checkr enrichment, +$0.75, billed to caller
specimen · real oracle output · POD · 0xed66…df8f · base oracle_version v23-decision-first · 2026-07-07
69 / 100 fused cognition score confidence 0.87 · regime BULL_TREND (0.67) buy · enter

"pod scores 69, buy. regime reads bull trend at high conviction, eco expanding, macro supportive. momentum is strong bullish, flow balanced between buyers and sellers. structure sits in markup, volatility elevated at 4% atr. safety check: SAFE, no hard fails."

momentumbullish · strong
flowbalanced · +7.6% h1
structuremarkup · higher highs
volatilityelevated · atr 4.0%
liquiditypremium · $5.18m pool
tactician mandate · action: ENTER · long

entry_zone: [0.4645, 0.4835] stop_loss: 0.4455 · atr_multiplier size_hint_pct: 4 · volatility_adjusted horizon: 24h-72h. invalidations, spelled out: "break below 0.4360 on high volume", "structure shift to distribution". every level computed from live structure. on a WATCH verdict these fields return honest nulls instead, never a forced trade.

drivers ↑
  • extreme bullish momentum across all EMAs
  • price in markup phase, higher highs confirmed
  • deep liquidity pool ($5.18m) reduces slippage risk
risks ↓
  • elevated volatility at 4.0% atr

scout

viability and smart money. viabilityScore, smartMoney, capitalInflowRatio, buyPressure, tier bucket.

auditor

safety gate. SAFE / hardFail verdict with a 0–100 safety score. one hard fail kills the trade before scoring starts.

quant

regime-adaptive scoring with weights_used exposed on every call. audit exactly what fired.

tactician

writes the mandate. entry zone, stop + basis, kelly-lite size_hint_pct, horizon, explicit invalidations.

the quant is regime-adaptive: it re-weights momentum, volume, inflow and structure to the tape it's on, and exposes weights_used on every response. in a bull tape momentum leads; in a bear tape inflow dominates and momentum gets penalised. bull logic is never applied to a bear tape.

BULL_TRENDmomentum leads · 0.55
BASE_DECOUPLEDmomentum leads · 0.45
BULL_CHOPbalanced · momentum 0.40
MIXEDbalanced · inflow 0.35
BEAR_CAPITULATIONinflow leads · 0.40
BEAR_TRENDinflow dominates · 0.50
full cognition
250k DELU ≈ $0.38
settled in $DELU on base · x402 upto scheme
  • verdict + 0–100 score + confidence
  • scout, auditor, quant computed server-side, every call
  • five signal groups: momentum, flow, structure, volatility, liquidity
  • full tactician mandate + regime context + drivers & risks
social boost · ?social=true
+ $0.75
optional add-on · usdc checkr fee, billed to caller · ~$1 per fully-informed decision
  • everything in full cognition, plus:
  • delu fetches checkr's read on the ca. agent-to-agent.
  • ais, velocity, and cascade folded into observed.social
  • blended into the fused score
  • no social signal? falls back to the quant decision. never halts.
hold-to-discount flywheel · the oracle signs for the 250k ceiling, then settles for less based on your $DELU balance on base
public< 50m $DELU250k ≈ $0.38
holder50m+ $DELU50k ≈ $0.08
whale100m+ $DELUfree
hold to unlock the ladder: 50m+ cuts the fee 5x, 100m+ calls free. $delu ↗
agent 02 · attention intelligence

checkr reads the feed so your agent doesn't have to

an attention intelligence layer for base. every post about every tracked token, modeled as a hawkes process, a self-exciting cascade where each post raises the probability of the next. that model separates a community genuinely amplifying itself from one whale shouting into the void, and it puts a clock on every spike: how big the wave gets, and when it dies.

ais

attention intelligence score (0–1). hawkes-derived quality metric. the headline number behind every signal.

velocity

momentum multiplier vs 48h baseline. 3.0+ is a meaningful spike, not noise.

cascade_multiplier

expected wave size. 2.5 means current mentions will 2.5× before fading, with half_life_hours on the decay.

organic_fraction

community-driven share of posts (0–1). above 0.5 the cascade is self-reinforcing. bots get flagged, not counted.

influence_concentration

fragility check. 0 = distributed conversation, 1 = single whale. high concentration = fragile signal.

divergence_detected

the alpha pattern. attention rising while price stays flat. the read arrives before the candle.

endpoint · api.checkr.social · usdc on base via x402price
GET/v1/leaderboard top base tokens by attention share, flexible 1–168h window $0.05
params
?limit= 1–50?hours= 1–24?sort_by= ATT_pct · MS_pct · INF_pct · velocity · ATT_delta?min_mentions=
returns per token
ATT_pct composite attention shareMS_pct mindshareINF_pct influenceATT_delta vs prior windowunique_authorssignal_interpretation 7-field block
GET/v1/signal opportunity radar: cross-universe ranked signals with entry timing $0.15
params
?limit= 1–20?min_ais=?spiking_only=?divergence_only=?require_history=
returns per signal
score ais × velocity × cascade × organic × historysignal_type spike · building · divergencecascade_multiplierorganic_fractionspike_history confirmed / total / hit_ratekey_factors + caution flags
timing block
window_openentry_quality strong→closedurgency act_now · monitor · wait · passedelapsed_pcttime_to_90pct_hours practical exit signaldecay_rate fast <2h · slow >8h
GET/v1/token/{symbol_or_ca} full token profile: attention, price, hawkes analysis, timing, narrative, spike history, top creators, health $0.75
accepts
symbol /v1/token/BNKRcontract address /v1/token/0xa1f7…47be?hours= 1–168
returns
attention ATT/MS/INF + 1h/4h deltasprice live via geckoterminal + mcap + volhawkes ais · branching_factor · viral_potential (SEISMIC) · organic_fraction · influence_concentration · top_competitorsdivergence + spike_history hit_ratetiming peak_attention_in_hoursnarrative summaryrecent_posts ≥10 likes
GET/v1/rotation where creators are moving: directed rotation graph with named attribution $0.10
params
?window= 1h | 4h?limit= 1–25?confirmed_only= default true
returns
edges from → to token, creator count, top_creator w/ followersnodes inflow · outflow · net_flow per tokenATT_growth confirmed attention change
GET/v1/creators/{symbol} who actually moves the feed for one token, ranked by signal_score not post count $0.15
params
?hours= 1–720?limit= 1–50?min_followers=?tier_filter= macro >10k · micro 1k–10k · nano <1k
returns per creator
signal_score weighted_avg_likes × log10(followers) × quality + cascadeweighted_avg_likes dedicated 1.0× · roundup 0.4× · secondary 0.25×cascade replies + quotes receivedquality_ratiomindshare_pct
GET/v1/creators/bankr top creators across the full bankr ecosystem, find the real ambassadors $0.30
returns per creator
bankr_tokens covered + token_countfocus_score herfindahl · 1.0 = pure specialistfocus_label specialist · focused · broadsignal_score across all ecosystem postsmindshare_pct of ecosystem conversation
GET/v1/bankreco bankr ecosystem overview: all tokens ranked with health grades $0.50
returns per token
ATT_pct of all ecosystem poststrend growing · active · quiet · deadattention_stage early → building → peak → fading → dormanthealth.score 0–100, grade A–Fhealth.subscores momentum · authenticity · quality · onchainopportunities + risks + action

signal_interpretation

every endpoint response carries this 7-field block. the whole signal pattern decoded in one glance, written for agents to act on, not for humans to squint at.

propagation_modequiet · organic · viral. is the cascade self-sustaining?
followthroughstrong · thin · uncertain. will momentum compound?
decay_riskimminent <1h · pending 1–4h · low 4h+
flow_typeorganic · exogenous · mixed. who's driving it?
price_alignmentaligned · misaligned · roughly_aligned. does this convert?
summaryearly_momentum · sustained_build · fading_spike · rotation_risk · noise
agent_action_hinthigh_conviction · flag · monitor · deprioritize · rotate_out
seven fields. one glance. zero prose parsing.
why this stack

what the alternatives can't do

vs mention counters

counting posts isn't reading a crowd

generic social tools count mentions and stop. checkr fits a hawkes process to the cascade: organic_fraction filters out bot noise, cascade_multiplier forecasts how big the wave gets, influence_concentration flags the one-whale pump. a mention count can't tell a community from a megaphone.

process model > post count
vs raw llm prompting

"is this token good?" is not a quant desk

ask an llm for a trade and it improvises from stale data, and it will happily hallucinate a stop-loss. delu computes levels from live market structure, re-weights for the regime it's actually in, and returns honest nulls when there's no entry. every weight it used ships in the response.

computed levels > confident guesses
vs watching the chart

price is the lagging indicator here

the chart tells you what already happened. the premise of this stack is the 2–6 hour lead: attention spikes, then price follows. divergence detection reads the crowd before the candle prints. by the time the chart confirms, the window is closing.

lead > lag
the pipeline · agents paying agents

one flag. two agents. one receipt.

pass ?social=true and delu becomes checkr's customer. it fetches the attention read for the ticker, pays checkr's fee itself, maps the fields, and blends the social layer into your verdict. your agent bought cognition from an agent that bought cognition. every hop is a public transfer on base.

your agent holds the wallet. executes. delu oracle scout · auditor · quant tactician mandate checkr GET /v1/token/{ca} ais · velocity · cascade pays 250k DELU analyze/{ca}?social=true +$0.75 USDC attention read verdict · social blended two receipts for your agent to execute on
1 · fetchdelu calls api.checkr.social/v1/token/{ca} with the contract address directly. no symbol lookup needed.
2 · mapais → sentiment_score · velocity → momentum · cascade_multiplier → influencer_hits. field mapping, no vibes.
3 · blendthe social layer lands in observed.social and enters the fused score at 25% weight. if checkr is unreachable, silent fallback to quant-only. never halts.
the meter — live since march 2026

not a waitlist. not a testnet.

both agents have been selling cognition since day one. paid calls settle as public transfers on base — usdc or $delu, agent to agent. here's the meter.

fig. 02 · the production tape — weekly api requests, both agents · as of 2026-07-07
4,000 8,000 12,000 mar apr may jun jul delu goes live — june 2 56,391 requests 631 verdicts 300 600 0 peak paid week · mar 27–apr 2 partial
checkr api requests (weekly) checkr cumulative · on delu verdicts (weekly) delu cumulative · on
checkr ·
delu ·

who this is for

three ways in

the full stack

give your trading agent a quant desk

your agent scans the chain and detects setups. when it finds a candidate, it buys a verdict instead of guessing: entry, stop, size, invalidations. works with claude code, openclaw, bankr, or any x402 client. these skills never touch your trading keys.

tell your agent: install both skills
checkr only · attention

you just want to read the crowd

feed ais, cascade multipliers, organic fraction, and rotation graphs into your own models, dashboards, or risk engines. find the real ambassadors with the creator endpoints: signal_score ranked, not follower-counted. the 2–6h lead is the product; what you do with it is yours.

x402 → checkr attention
delu only · verdicts

you already have your own radar

you find the candidates; delu prices the decision. one GET returns verdict, score, entry zone, stop, and size hint on any base coin. hold $DELU and calls get cheaper; whales analyze free. add ?social=true only when you want the crowd folded in.

x402 → delu oracle
quickstart

tell your agent. that's it.

your agent installs the skills and handles the payment handshake on its own. on bankr, the skills are already built in. just ask.

tell your agent
install the checkr and delu skills from github.com/checkrsocial/checkr-skill and github.com/deluonchain/deluskill
on bankr? just ask: "what's spiking on base right now?" · "analyze 0xed66… with social"
agents read the full spec at llms.txt

what the data actually looks like

exact response shapes. pick an endpoint.

GET /v1/leaderboard · what's moving on base right now
{
  "leaderboard": [{
    "symbol": "TIBBIR",
    "ATT_pct": 9.37,
    "velocity": 5.82,
    "unique_authors": 14,
    "signal_interpretation": {
      "propagation_mode": "organic",
      "agent_action_hint": "high_conviction"
    }
  }],
  "count": 74,
  "data_age_minutes": 8
}
GET /v1/signal · best opportunity with timing
{
  "signals": [{
    "symbol": "TIBBIR",
    "signal_type": "building",
    "score": 0.84,
    "divergence": true,
    "timing": {
      "entry_quality": "strong",
      "urgency": "act_now",
      "time_to_90pct_hours": 2.4
    },
    "signal_interpretation": {
      "followthrough": "strong",
      "summary": "early_momentum",
      "agent_action_hint": "high_conviction"
    }
  }],
  "count": 3
}
GET /v1/token/TIBBIR · full token deep dive
{
  "symbol": "TIBBIR",
  "attention": {
    "ATT_pct": 9.37, "velocity": 5.82,
    "organic_fraction": 0.71,
    "cascade_multiplier": 2.4
  },
  "price": {
    "price_usd": 0.00041,
    "price_change_24h": -3.8
  },
  "divergence": true,
  "timing": {
    "half_life_hours": 3.2,
    "viral_class": "BUILDING"
  },
  "signal_interpretation": {
    "price_alignment": "misaligned",
    "agent_action_hint": "high_conviction"
  }
}
GET /analyze/{ca} · full cognition verdict
{
  "decision": {
    "action": "ENTER",
    "conviction": 60,
    "direction": "long",
    "entry_low": 0.4645, "entry_high": 0.4835,
    "stop": 0.4455, "size_pct": 4
  },
  "verdict": "buy", "score": 69, "confidence": 0.87,
  "mandate": {
    "entry_zone": [0.4645, 0.4835],
    "stop_loss": 0.4455, "stop_basis": "atr_multiplier",
    "size_hint_pct": 4, "horizon": "24h-72h",
    "invalidations": ["break below 0.4360 on high volume", "structure shift to distribution"]
  },
  "context": {
    "regime_label": "BULL_TREND",
    "base_eco_pulse": "expanding",
    "macro_pulse": "supportive"
  }
}