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 agentmods add skills/okx/plugin-store/macro-intelligencenpx skills add okx/plugin-store --skill macro-intelligencegit clone --depth 1 https://github.com/okx/plugin-storeWhat 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 | $0.00030 | $0.04164 |
| Opus 5 | $0.00015 | $0.02082 |
| Sonnet 5 | $0.00006 | $0.00833 |
| Haiku 4.5 | $0.00003 | $0.00416 |
Grade A, and why
macro-intelligence 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 2d 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.
from urllib.request import urlopen How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Macro Intelligence Skill v1.0 — Agent Instructions
Purpose
Unified macro intelligence feed. Reads news from 7 sources (NewsNow, Polymarket, Telegram, 6551.io OpenNews, Finnhub, FRED, Fear & Greed Index), classifies macro events, scores sentiment, generates AI insights, and exposes clean signals via HTTP API. No trading logic — downstream skills consume signals.
Architecture
NewsNow (HTTP, 120s) ──────┐
Polymarket (HTTP, 120s) ────┤
Finnhub (HTTP, 180s) ───────┤──→ process_signal() ──→ UnifiedSignal ──→ API :3252
6551.io OpenNews (WebSocket)─┤ │ noise filter │ classify │ sentiment
Telegram (Telethon WS) ─────┘ │ dedup │ reputation │ AI insight
│ │ token extract │ store
FRED (HTTP, 3600s) ──────────→ context data ──→ /api/fred + significant change → process_signal()
Fear & Greed (HTTP, 300s) ───→ context data ──→ /api/fng
Price Tickers (HTTP, 60s) ───→ context data ──→ /api/prices (SPY, GLD, SLV, BTC, ETH)
Startup Protocol
python3 macro_news.py— starts all collectors + HTTP server on:3252python3 macro_news.py setup— interactive mode to list Telegram groups/channels
Requirements
- Python 3.9+
pip install telethon(optional — runs without it)pip install websockets(optional — needed for 6551.io OpenNews WebSocket)- Env:
ANTHROPIC_API_KEYfor LLM classification + AI insights (optional) - Env:
TG_API_ID,TG_API_HASH(or set in config.py) - Env:
OPENNEWS_TOKENfor 6551.io (free — get token at https://6551.io/mcp) - Env:
FINNHUB_API_KEYfor Finnhub market news (free — register at https://finnhub.io) - Env:
FRED_API_KEYfor FRED macro indicators (free — register at https://fred.stlouisfed.org/docs/api/api_key.html)
All new sources are disabled by default if their API key env var is empty — graceful degradation.
Files
| File | Purpose |
|---|---|
config.py |
All tunable parameters — sources, filters, keywords, playbook, sentiment lexicon |
macro_news.py |
Main runtime — collectors, pipeline, classifier, API server, dashboard |
dashboard.html |
Dark-theme monitoring UI with price tickers, FNG gauge, FRED indicators, signal feed |
skill.md |
This file — agent instructions |
state/state.json |
Persisted state (signals, dedup hashes, reputation, finnhub_last_id) |
What ships with it
10 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.
- 2d ago First seen · 288 lines · 30 tokens per session scan A 35c13070862e
macro-intelligence is a skill published in the GitHub repository okx/plugin-store (11 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 4,164 once invoked, about $0.0002 per session on Opus 5. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.