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 Nero1688/claude-academic-skills --skill public-disclosure-scoutgit clone --depth 1 https://github.com/Nero1688/claude-academic-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/nero1688/claude-academic-skills/public-disclosure-scout)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/public-disclosure-scout"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/public-disclosure-scout/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/nero1688/claude-academic-skills/public-disclosure-scout"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/public-disclosure-scout.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 | $0.00533 | $0.02754 |
| Opus 5.5 | $0.00213 | $0.01102 |
| Sonnet 5.5 | $0.00107 | $0.00551 |
| Haiku 4.5 | $0.00053 | $0.00275 |
Grade A, and why
public-disclosure-scout 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
免費公開揭露資料偵察員(Public Disclosure Scout)
核心定位:免費揭露的三種學術角色
- 付費庫的免費替代/補充:沒有 TEJ 授權時的第一線;有 TEJ 時用來補付費庫沒有 或延遲的欄位(重大訊息即時性、非結構化揭露)。
- 事件研究的標準事件源:公司治理/揭露研究的事件(董監改選、股利宣告、 增減資、重大契約、裁罰)幾乎都來自 MOPS 重大訊息。公司「宣布」的日期=事件日, 這是媒體報導或財報數字給不了的。
- 文字資料的原始語料來源:年報 MD&A、法說會逐字稿的原始檔——抓回來後 文字量化交棒 text-analytics-architect。
Step 1|判斷免費源有沒有這筆資料(以台灣為例)
完整源目錄讀 references/taiwan-public-sources.md。快速路由:
| 需求 | 免費官方源 |
|---|---|
| 重大訊息/事件日 | 公開資訊觀測站 MOPS(重大訊息 t05st01) |
| 年報/財報原文 | MOPS(年報/財報公告) |
| 股東會/董監改選 | MOPS(股東會決議、董監事持股) |
| 內部人持股異動 | MOPS(內部人持股、設質) |
| 股價/成交 | TWSE/TPEx 官網(日資料) |
| 裁罰/違規 | 金管會、公平會、環保署裁罰公開資料 |
| 專利 | TIPO 專利檢索 |
| 產業/總體 | 政府開放資料平台 data.gov.tw |
判斷紀律同 tej-data-scout:對不上就標「需確認」+指出去哪查,絕不杜撰某源有某欄位。
Step 2|事件研究就緒度(本 skill 最高價值)
要做事件研究時,把揭露變成乾淨事件檔的三件事:
- 事件日定義(MOPS 每則重大訊息有兩個日期,必須分開處理):
- t = 0 以「發言日期」＋發言時間戳為準:發言時間在 13:30(台股收盤)之後者, 事件日順延至次一交易日(市場當日已無法反應);13:30 前者以當日為 t = 0。 非交易日(週末、國定假日、颱風假)公告一律順延至次一交易日。
- 「事實發生日」另列一欄,不當 t = 0:事實發生日早於發言日期 ≥ 1 個交易日者 (常見於董事會決議、簽約、法院判決等),要另外標記,並在事件窗前期 (如 [−5, −1])檢查異常報酬是否已出現——若有,是資訊外洩或市場已從其他管道 得知,審稿人會問「事實發生日早於發言日期的那些,事前漂移怎麼處理」; 穩健性一律另報「以事實發生日為 t = 0」的版本,兩者差異要解釋。
- 若研究關心市場預期,另分「宣布日 vs 生效日」,兩者分開檢驗 (呼應 causal-inference-architect)。
- 事件檔格式:標準欄位
ticker, event_date, fact_date, announce_time, subject——event_date為依上述規則調整後的 t = 0(西元日期),fact_date為事實發生日,announce_time為原始發言時間戳(保留以供稽核);可直接餵事件研究引擎。 台灣資料注意民國日期轉西元、同日多則揭露的去重與歸併(同公司同日多則:合併為 一事件並在subject保留全部類別,或依研究問題只留主事件並記錄剔除規則)。 - 識別碼對接:MOPS 用股票代號,與 TEJ 面板合併要確認代號一致(上市櫃轉板、 更名、暫停交易的代號變動);跨源用統一編號(統編)最穩。
Step 3|抓取合規與資料品質(紅線)
- 合規先於方法:抓任何官方站台前查該站服務條款與 robots；官方揭露屬公開 資訊可研究用,但禮貌抓取(請求間隔數秒、量小、不打爆站台)是研究倫理也是 自保。政府開放資料多有明確授權(政府資料開放授權條款),優先用。
- 個資:揭露文件含自然人姓名(董監、經理人)時,研究呈現去識別化; 不建個人可識別的彙整檔。
- 品質檢查:官方揭露≠零錯——同一事件多次更正、撤銷公告、補充揭露都有; 事件庫要保留 fetched_at 與原始主旨供回溯,抽樣人工核對。
- 來源標註:論文方法節寫明資料源(MOPS 端點與擷取日期)、事件定義、 去重規則——免費源的可重現性交代要比付費庫更完整(因端點會變)。
- 抓不到時的升級階梯:頁面靠 JS 動態載入、
requests只拿到空殼時,讀references/dynamic-scraping-escalation.md——由輕到重逐級升級(先找背後 API → 官方批次 → 無頭瀏覽器),且合規紅線在任何級別不變:🚫 禁用工具的反偵測/隱身 功能,抓不到就升級到「官方管道/申請/人工」,不是升級到「躲過偵測」。 - 引用永久性與變更監測:論文引用的 MOPS/公司 IR 網頁,審稿人數年後可能點到
404——每個網頁引用都應附 Wayback 存檔連結或至少擷取日期。變更監測(內容雜湊
比對、排程頻率、變更即存檔)與存檔操作(
lookup/save/hash/log)見references/disclosure-monitoring.md與scripts/archive_url.py。
What ships with it
5 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.
- 1mo ago Changed · +19 lines 439112c1c0a4
- 1mo ago Changed · -2 lines 86f7e1753bd5
- 1mo ago First seen · 84 lines · 533 tokens per session scan A 8bb8e53cb3c9
public-disclosure-scout is a skill published in the GitHub repository Nero1688/claude-academic-skills (13 stars, last pushed 5d ago), licensed MIT. It adds 533 tokens to every session and 2,754 once invoked, about $0.0021 per session on Opus 5.5. 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
alterlab-alpha-vantage
Accesses real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API (requires a free API key from alphavantage.co). Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance…
agb-bei-kreditvertraegen-verbraucherdarlehen
Für AGB bei Kreditverträgen Verbraucherdarlehen: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
agb-in-kapitalanlagen-effektenhandel
Für AGB in Kapitalanlagen Effektenhandel: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
bookkeeping-close
Runs small and midsize business bookkeeping operations - categorizes bank and card transactions to a chart of accounts, reconciles a bank or card statement against the ledger, works a month-end close checklist, and produces a close package for the accountant. Works from QuickBooks Online, Xero, bank CSV/OFX, or…
sec-filing-puller
Pulls financial statement numbers for US public companies straight from SEC EDGAR's free official XBRL APIs (companyfacts, companyconcept, frames, submissions) into a cited table. Every value carries its accession number, form, fiscal period, filed date, XBRL tag and a link to the filing, and the tool handles…
budget-optimizer
Analyze spending patterns and find savings. 50/30/20 rule, subscription audit, debt payoff strategies, emergency fund roadmap.