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 fatfingererr/macro-skills --skill track-agri-hedge-fund-positioninggit clone --depth 1 https://github.com/fatfingererr/macro-skillsWrote 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/fatfingererr/macro-skills/track-agri-hedge-fund-positioning)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/track-agri-hedge-fund-positioning"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/track-agri-hedge-fund-positioning/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/fatfingererr/macro-skills/track-agri-hedge-fund-positioning"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/track-agri-hedge-fund-positioning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00075 | $0.03090 |
| Opus 5 | $0.00037 | $0.01545 |
| Sonnet 5 | $0.00015 | $0.00618 |
| Haiku 4.5 | $0.00007 | $0.00309 |
Grade A, and why
track-agri-hedge-fund-positioning 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
CFTC Commitments of Traders 報告是追蹤對沖基金農產品部位的核心資料:
- 截止日:每週二收盤
- 發布日:每週五下午 3:30 ET
- 交易者分類:非商業(投機/基金)、商業(避險)、非報告
資金流 = 本週淨部位 - 上週淨部位(以合約口數計)
使用 CFTC 原生分組(commodity_subgroup_name):
| 群組 | CFTC 分組名稱 | 包含商品 |
|---|---|---|
| Grains | GRAINS | Corn, Wheat (SRW/HRW/HRS), Oats |
| Oilseeds | OILSEED and PRODUCTS | Soybeans, Soybean Oil/Meal, Canola |
| Meats | LIVESTOCK/MEAT PRODUCTS | Live Cattle, Lean Hogs, Feeder |
| Softs | FOODSTUFFS/SOFTS | Coffee, Sugar, Cocoa, OJ |
| Fiber | FIBER | Cotton |
| Dairy | DAIRY PRODUCTS | Milk, Butter, Cheese |
Total Flow = Grains + Oilseeds + Meats + Softs + Fiber + Dairy
火力衡量基金是否還有加碼空間:
net_pos_percentile = rank(current_net_pos, past_N_weeks)
firepower = 1 - net_pos_percentile
- 高火力(>0.6):部位處於歷史低檔,仍有大量買進空間
- 低火力(<0.3):部位已接近歷史高檔,擁擠風險高
整合三個風險偏好指標:
| 指標 | 訊號解讀 |
|---|---|
| 美元 (DXY) | 走弱(負報酬)= 利於商品 |
| 原油 (WTI) | 走強(正報酬)= 風險偏好上升 |
| 金屬 | 走強(正報酬)= 循環需求樂觀 |
macro_tailwind_score = (DXY弱 + WTI強 + Metals強) / 3
COT 只到週二,週三~週五需用代理證據:
- 價格動能:農產品/代理指數 Wed-Fri 累積報酬
- 未平倉變化:OI 擴張 = 新倉(非純換手)
- 宏觀共振:與 USD↓、油價↑、金屬↑ 同時性
</essential_principles>
- 取得資料:COT 週報、宏觀指標(DXY/WTI/金屬)、基本面觸發(出口/USDA)
- 計算流量:淨部位週變化,分組彙總(Grains/Oilseeds/Meats/Softs/Total)
- 量化火力:用歷史分位數估算基金加碼空間
- 整合訊號:判斷「基金回來買」+ 「宏觀順風」+ 「基本面支持」
- 產出敘事:將圖表標註(如 Strong Corn Demand)轉為可重複的規則
輸出:週流量時序、最新狀態、火力分數、宏觀評分、可交易註解。
<quick_start>
快速開始:分析最新 COT 資料
cd .claude/skills/track-agri-hedge-fund-positioning/scripts
pip install pandas numpy requests yfinance pyarrow # 首次使用
python analyze_positioning.py --start 2023-01-01
輸出範例(真實資料):
{
"skill": "track-agri-hedge-fund-positioning",
"as_of": "2026-01-20",
"data_source": "CFTC Socrata API (real data)",
"summary": {
"call": "Funds continue selling",
"all_signals": ["Funds continue selling", "Extreme short - watch for reversal", "Macro mood bullish"],
"confidence": 0.90
},
"latest_metrics": {
"flow_total_contracts": -24559,
"flow_by_group_contracts": {"grains": -31279, "oilseeds": 11517, "meats": 18972, "softs": -23887, "fiber": 1607, "dairy": -1489},
"buying_firepower": {"total": 0.86, "grains": 0.58, "oilseeds": 0.62, "meats": 0.31, "softs": 0.99, "fiber": 0.58, "dairy": 0.99},
"macro_tailwind_score": 0.67
}
}
視覺化圖表:
python visualize_flows.py --weeks 52
# 輸出:output/agri_fund_positioning_YYYY-MM-DD.png
</quick_start>
- 快速檢查 - 查看最新一週的基金部位變化與狀態
- 完整分析 - 指定日期範圍的資金流向分析與回測
- 視覺化圖表 - 生成分組柱狀圖與火力時序圖
- 監控模式 - 設定週度更新與訊號警報
- 方法論學習 - 了解 COT 分析與火力計算邏輯
請選擇或直接提供分析參數。
What ships with it
20 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.
- examples/full_analysis_result.json 5.2 KB
- examples/weekly_flow_sample.json 853 B
- manifest.json 2.6 KB
- references/contracts-map.md 5.5 KB
- references/data-sources.md 7.1 KB
- references/input-schema.md 7.0 KB
- references/macro-indicators.md 8.0 KB
- references/methodology.md 6.6 KB
- scripts/analyze_positioning.py 14 KB runs code
- scripts/fetch_cot_data.py 7.9 KB runs code
- scripts/fetch_macro_data.py 9.9 KB runs code
- scripts/visualize_flows.py 23 KB runs code
- skill.yaml 17 KB
- templates/annotations.md 9.7 KB
- templates/output-json.md 6.1 KB
- templates/output-markdown.md 6.6 KB
- workflows/analyze.md 5.2 KB
- workflows/cross-check.md 8.0 KB
- workflows/monitor.md 5.1 KB
- workflows/visualize.md 5.7 KB
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.
- 12d ago First seen · 259 lines · 75 tokens per session scan A 0ed7904450aa
track-agri-hedge-fund-positioning is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 75 tokens to every session and 3,090 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.