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 analyze-jgb-insurer-superlong-flowgit 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/analyze-jgb-insurer-superlong-flow)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/analyze-jgb-insurer-superlong-flow"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-jgb-insurer-superlong-flow/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/analyze-jgb-insurer-superlong-flow"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-jgb-insurer-superlong-flow.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 | $0.03280 |
| Opus 5 | $0.00037 | $0.01640 |
| Sonnet 5 | $0.00015 | $0.00656 |
| Haiku 4.5 | $0.00007 | $0.00328 |
Grade A, and why
analyze-jgb-insurer-superlong-flow 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 11d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
分析日本保險公司超長期 JGB 淨買賣流量 Skill
以 JSDA 公開數據驗證「保險公司創紀錄賣超長端國債」等敘事，提供可複製的摘要（含 streak / record / 累積值）。
<essential_principles>
日本證券業協會（JSDA）自 2018/05 起將投資人別交易統計整併進「Trading Volume of OTC Bonds」資料集。
數據位置：
- 當前財年：https://www.jsda.or.jp/shiryoshitsu/toukei/tentoubaibai/koushasai.xlsx
- 歷史財年：https://www.jsda.or.jp/shiryoshitsu/toukei/tentoubaibai/koushasai{YYYY}.xlsx
關鍵 Sheet：
(Ｊ)合計差引- 淨買賣額（Sell - Purchase）
數據特徵：
- 頻率：月度
- 分類：投資人類型 × 債券類型 × 天期桶
- 單位：億日圓（100 million yen）
- 延遲：約 T+1 個月
注意：2018/05 前的舊版「Trends in Bond Transactions (by investor type)」已停止更新。
JSDA 使用「賣出 - 買入」作為差引計算方式：
net_sale = 賣出金額 - 買入金額
- 正值 = 淨賣出（賣出 > 買入，需求減少）
- 負值 = 淨買入（買入 > 賣出，需求增加）
這與部分新聞報導的符號相反，需特別注意。
JSDA Excel 欄位結構（第 4 列）：
| JSDA 欄位 | 英文 | 說明 |
|---|---|---|
| 超長期 | Interest-bearing Long-term (over 10-year) | 10 年以上利付債 |
| 利付長期 | Interest-bearing Long-term | 5-10 年利付債 |
| 利付中期 | Interest-bearing Medium-term | 2-5 年利付債 |
| 割引 | Zero-Coupon | 零息債 |
| 国庫短期証券等 | Treasury Discount Bills | 短期國庫券 |
本 Skill 使用：超長期（對應新聞常見的「10+ years」或「super-long」口徑）
| JSDA 分類 | 英文 | 說明 |
|---|---|---|
| 生保・損保 | Life & Non-Life Insurance Companies | 壽險 + 產險合計 |
| 都市銀行 | City Banks | 大型商業銀行 |
| 地方銀行 | Regional Banks | 區域性銀行 |
| 信託銀行 | Trust Banks | 含年金管理 |
| 外国人 | Foreigners | 海外投資者 |
本 Skill 使用：生保・損保（保險公司合計）
record_high = max(series) # 最大淨賣出（正值最大）
is_record_sale = (latest == record_high) AND (latest > 0)
注意事項：
- 數據起點會影響「歷史紀錄」的判定，輸出必須說明樣本期間
- 若僅為近期極值，需標註「近 N 個月新高」
</essential_principles>
<quick_start>
最快的方式：執行快速分析
cd .claude/skills/analyze-jgb-insurer-superlong-flow
pip install pandas numpy openpyxl # 首次使用
python scripts/jsda_flow_analyzer.py --quick
輸出範例（2025/12 實測結果）：
## 日本保險公司超長期 JGB 淨買賣驗證報告
**分析期間**：2022-04 ~ 2025-12（45 個月）
### 核心結論
| 指標 | 數值 | 說明 |
|------|------|------|
| 本月（2025-12）| **8,224 億日圓** | 淨賣出 |
| 是否創歷史紀錄 | **✓ 是** | 全樣本 (45 個月) |
| 連續淨賣出月數 | **5 個月** | 自 2025-08 起 |
| 本輪累積淨賣出 | **13,959 億日圓** | 1.40 兆日圓 |
### Headline Takeaways
1. ✓ 驗證屬實：日本保險公司在 2025/12 創下歷史最大單月淨賣出
2. 已連續 5 個月淨賣出超長期國債，累積 1.40 兆日圓
3. 當前淨賣出規模處於歷史極端區間（Z-score: 2.71）
完整分析（含歷史比較）：
python scripts/jsda_flow_analyzer.py --full --format json
強制重新下載數據：
python scripts/jsda_flow_analyzer.py --quick --refresh
</quick_start>
- 快速檢查 - 查看最新月份的淨買賣與連續淨賣出狀態
- 完整分析 - 執行完整的歷史比較與極值判斷
- 驗證新聞 - 輸入新聞的數字，對比 JSDA 原始數據
- JSON 輸出 - 輸出結構化 JSON 供後續處理
請選擇或直接執行分析。
<input_schema>
What ships with it
16 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/sample-output.json 3.0 KB
- manifest.json 2.3 KB
- references/data-sources.md 5.6 KB
- references/input-schema.md 5.5 KB
- references/jsda-structure.md 5.8 KB
- references/methodology.md 7.5 KB
- scripts/fetch_jsda_data.py 9.5 KB runs code
- scripts/generate_flow_chart.py 16 KB runs code
- scripts/jsda_flow_analyzer.py 18 KB runs code
- skill.yaml 9.6 KB
- templates/output-json.md 7.7 KB
- templates/output-markdown.md 5.8 KB
- workflows/full-analysis.md 4.2 KB
- workflows/generate-chart.md 3.2 KB
- workflows/quick-check.md 2.6 KB
- workflows/verify-claim.md 3.8 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.
- 11d ago First seen · 314 lines · 75 tokens per session scan A e6c06ab0f7a5
analyze-jgb-insurer-superlong-flow 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 3,280 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.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
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.