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 ZICXR/A-Stock-Skills --skill astock-cachegit clone --depth 1 https://github.com/ZICXR/A-Stock-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/zicxr/a-stock-skills/astock-cache)<a href="https://agentmods.dev/skills/zicxr/a-stock-skills/astock-cache"><img src="https://agentmods.dev/badge/skills/zicxr/a-stock-skills/astock-cache/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/zicxr/a-stock-skills/astock-cache"><img src="https://agentmods.dev/badge/skills/zicxr/a-stock-skills/astock-cache.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 | $0.00065 | $0.00593 |
| Opus 5 | $0.00032 | $0.00296 |
| Sonnet 5 | $0.00013 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
astock-cache 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.
What it actually says
astock-cache
何时使用
- 全市场筛选太慢 (每次 30 分钟)
- 反复拉同一只股票 K 线
- 跑 screener 跑 2 遍
- 想要"盘后更新一次,白天用一天"
🚀 快速上手
# 看缓存多少了
python main.py kline-stats
# 跑一次全市场 K 线更新 (15-30 分钟, 但之后都是 5 秒)
python daily_update.py
# 单独看某只股票
python main.py kline-stats
# {"count": 5028, "size_mb": 18.4}
提供能力
通用 Key-Value 缓存
cache_set/get/delete/clearcached(key, ttl)装饰器- 存储:
~/.astock_skills/cache/*.pkl
K 线 parquet 缓存 (新,推荐)
kline_save(code, df, days)存 parquetkline_load(code, days, max_age_hours)读kline_get_or_fetch(code, fetch_fn, days)智能模式- 存储:
~/.astock_skills/cache/kline/{code}_{days}d.parquet
screener 集成示例
from skills.01-infra.astock-cache.main import kline_get_or_fetch
from skills.01-infra.astock-data-source.main import get_kline
def smart_kline(code, days=60):
"""优先读缓存, 缓存没有才拉网络"""
return kline_get_or_fetch(code, get_kline, days=days)
# 第一次慢 (拉网络), 之后 5 秒
df = smart_kline("601991", 60)
性能
| 场景 | 无缓存 | 有缓存 | 加速比 |
|---|---|---|---|
| 单股 60 日 K 线 | 1.2s | 0.05s | 24x |
| 全市场 5028 只 60 日 | 30min | 5s | 360x |
依赖
pandas>=1.5.0
pyarrow>=10.0.0 # parquet 引擎
What ships with it
2 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.
- 11d ago First seen · 69 lines · 65 tokens per session scan A 28635fac8e49
astock-cache is a skill published in the GitHub repository ZICXR/A-Stock-Skills (25 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 593 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
private-company-research
A research workflow for private companies, meaning businesses whose shares are not traded on a public stock exchange. It uses several research roles to investigate the company in depth.
bottleneck-hunter
A research workflow for finding supply-chain bottlenecks—parts of global production where shortages or limited capacity may create investment opportunities.
investment-research
A broad stock-research workflow combining ideas associated with Warren Buffett, Charlie Munger, Duan Yongping, and Li Lu. It examines the business, its quality, its risks, and its value.
earnings-review
A workflow for closely reading and interpreting a company's financial reports using original source material.
industry-research
An industry-research workflow that maps how an industry works from suppliers to customers, then examines individual companies within it. The value-investing analysis looks at business quality, risks, and price.
investment-checklist
A pre-purchase checklist for value investing, which means buying shares based on a company’s business quality and estimated worth. It is based on the investing approach associated with Warren Buffett.