ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

agentcanary

Market intelligence API for AI agents. Macro regime detection, risk scoring, trading signals (IGNITION/ACCUMULATION/DISTRIBUTION/CAPITULATION), whale alerts, funding arbitrage, orderbook analytics, 29 technical indicators, RSI screening (606 coins), breaking news with FinBERT sentiment, economic calendar, treasury tracking, and Polymarket odds. 33 endpoints, 1181 assets, 250+ sources. Use when an agent needs macro regime context, risk assessment, position sizing guidance, market structure data, whale activity monitoring, or news sentiment. API-only — no local execution, no filesystem access, no secrets in prompt.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/mrcerq/agentcanary
Or

AgentCanary

Market intelligence for AI agents. 33 API endpoints. Not raw data — intelligence.

Status: Preview. API access opening soon. Free tier: real-time prices (50 calls/day). Live proof: @AgentCanary on Telegram — 3x/day auto-generated market intelligence from the same API. Website: agentcanary.ai Waitlist: Sign up at agentcanary.ai to get notified when API access opens.

This API powers Proximity, a crypto intelligence iOS app with 6 months of daily usage across 20+ countries.


Security

  • API-only — HTTP GET calls returning JSON. No local code, no binaries, no shell commands.
  • No secrets in the prompt — wallet-based auth when billing is live.
  • Read-only — fetches data. Cannot write, modify, or access your filesystem.

824 malicious skills were found on ClawHub. Crypto and finance is the #1 target category. AgentCanary is the finance skill that can't steal from you.


Default Agent Pattern

1. Call /macro-snapshot/regime every 4–6 hours
2. If Risk-Off → suppress trading, reduce exposure
3. If Risk-On → allow strategy execution
4. Use severity alerts as interrupts, not drivers
5. Call /signal-state before entering positions for confirmation

AgentCanary is risk intelligence middleware. It tells your agent when conditions are favorable — your agent decides what to do.


What It Does Not Do

  • Does not predict prices — classifies regimes and states
  • Does not guarantee returns
  • Does not place orders or replace execution logic
  • Does not provide financial advice

Capabilities (33 Endpoints)

For full endpoint documentation with real response examples, read references/endpoints.md.

Macro & Regime

EndpointWhat it returns
/macro-snapshotRegime, business cycle, risk gauge, z-scores on 26 FRED indicators
/macro-snapshot/regimeRegime label, flags, composite scores, explanation
/market-analysis/latestAI-generated daily report: sentiment, fear & greed, narratives, alerts

Signals & Technicals

EndpointWhat it returns
/signal-state100 coins, IGNITION/ACCUMULATION/DISTRIBUTION/CAPITULATION on 1d + 4h
/cointa?id={coinId}29 technical indicators, composite buy/sell signal, 365 data points
/coin-rsi/statistics606 coins RSI screening, overbought/oversold ranked lists
/coin-rsi/multi?coinids={id}6-timeframe RSI (5m to 1w) per coin
/roc/{coinId}90-day rate of change, acceleration, volatility, percentile bands

Metadata

Author@mrcerq
Stars1401
Views1
Updated2026-02-24
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-mrcerq-agentcanary": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.