Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KCNyu/clawocknpx agentmods add skills/kcnyu/clawock/hk-stock-analysisWrote 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/kcnyu/clawock/hk-stock-analysis)<a href="https://agentmods.dev/skills/kcnyu/clawock/hk-stock-analysis"><img src="https://agentmods.dev/badge/skills/kcnyu/clawock/hk-stock-analysis/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/kcnyu/clawock/hk-stock-analysis"><img src="https://agentmods.dev/badge/skills/kcnyu/clawock/hk-stock-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00126 | $0.09748 |
| Opus 5 | $0.00063 | $0.04874 |
| Sonnet 5 | $0.00025 | $0.01950 |
| Haiku 4.5 | $0.00013 | $0.00975 |
Grade A, and why
hk-stock-analysis 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 10d 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.
sp = StealthyFetcher.fetch(f"https://xueqiu.com/S/HK{TICKER}", headless=True) How it starts
The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HK Stock Analysis
Workspace-native Hong Kong stock analyst. Uses the local fetch pipeline for live price + 恒指/恒科 baseline, then layers HK-specific analysis.
Required reads before answering
In this order:
/root/.openclaw/workspace/MEMORY.md— data rules, traps, 00100-only-Tencent warning/root/.openclaw/workspace/TOOLS.md— HK fallback chain detail, skill routing/root/.openclaw/workspace/INVESTMENT_SOP.md— standard startup sequence/root/.openclaw/workspace/portfolio.json— if the ticker is in the active book
Data source rule (non-negotiable)
Default path — use the workspace script, not web search:
# Full analysis: refreshes price + 恒指/恒科基准 + RSI/MA + Finnhub news + signal
/root/.local/bin/clawock analyze-hk {TICKER}
/root/.local/bin/clawock analyze-hk {TICKER} --no-news # skip news
/root/.local/bin/clawock analyze-hk --no-fetch # use cached, analysis only
HK fallback chain (inside script):
- Tencent
qt.gtimg.cn/q=r_hk{CODE}— primary; batch first, then single-code retry for misses - Eastmoney HK
push2.eastmoney.com/.../ulist.np/get(secid prefix 116) — requested for every ticker as an independent batch, even when Tencent succeeded. When both succeed, prefer Tencent but comparecandpc; divergence >1% is stored in_divergenceand warned on stdout. When Tencent misses, Eastmoney is the first fallback. - stooq.com CSV — only for tickers still unresolved; same-day OHLCV; caveat: new IPOs (e.g. 00100) not covered,
prev_closeapproximated fromopen - yfinance — only for tickers still unresolved; frequently rate-limited, last-resort fallback
Removed routes (do not retry):
- ❌ AAStocks / 富途网页 — anti-scraping, not worth the fight; use Tencent
基本面路由（行情之外，2026-06-14 接入）： 港股财报/关键指标走东财 datacenter — clawock fundamentals（datacenter-web + searchapi 子域实测稳定；行情链的 push2 由共享客户端独立尝试）。详见 Mode 3。⚠️ 资金流 clawock fundflow 写好但 push2his 在本服务器 IP 被封，暂不可用。
Critical trap — 00100 MINIMAX has only Tencent. As a new IPO it has no stooq/yfinance coverage. If Tencent fails on 00100, say so explicitly before falling back — do not silently use yesterday's cache.
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.
- 10d ago First seen · 344 lines · 126 tokens per session scan A a8108e5df81a
hk-stock-analysis is a skill published in the GitHub repository KCNyu/clawock (14 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 9,748 once invoked, about $0.0006 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
tushare
A Python interface to Tushare, a financial-data service providing market, company, fund, futures, and other finance-related data. It shows how to authenticate and query the service into pandas tables.
financial-expense-automation
An expense-receipt workflow that reads PDF and image attachments, extracts their details, checks whether they are valid expense receipts, and records them in Feishu Bitable, a cloud table service.
credit-analysis
A framework for analysing bonds and other fixed-income investments, including issuer credit quality, interest-rate sensitivity, credit spreads, and default risk. A credit rating estimates how likely an issuer or specific bond is to repay its debt.
crypto-monitor
A scheduled cryptocurrency price checker that uses CoinGecko, a service providing market data. It tracks Bitcoin, Ethereum, and Litecoin in US dollars and Chinese yuan, including their change over the past 24 hours.
vibe-trading
Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 79 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest →…
quant-statistics
Quantitative statistical methods: ADF unit-root / cointegration tests, GARCH volatility modeling, regression diagnostics (heteroskedasticity / autocorrelation), Bootstrap, and hypothesis testing.