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 minguncle/a-share-agent-skills --skill a-share-observation-loopgit clone --depth 1 https://github.com/minguncle/a-share-agent-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/minguncle/a-share-agent-skills/a-share-observation-loop)<a href="https://agentmods.dev/skills/minguncle/a-share-agent-skills/a-share-observation-loop"><img src="https://agentmods.dev/badge/skills/minguncle/a-share-agent-skills/a-share-observation-loop/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/minguncle/a-share-agent-skills/a-share-observation-loop"><img src="https://agentmods.dev/badge/skills/minguncle/a-share-agent-skills/a-share-observation-loop.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 | $0.00064 | $0.01069 |
| Opus 5 | $0.00032 | $0.00535 |
| Sonnet 5 | $0.00013 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
a-share-observation-loop 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 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.
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
A Share Observation Loop
Overview
这个 skill 把研究结论改写成“每天怎么查、查什么、看到什么就做什么”。它每次都基于新数据重建观察表，不依赖前一次会话记忆。
Hard Rules
- 这是无状态观察框架，不默认继承昨天的观察结果。
- 观察项必须能被当天数据验证，不能写成空泛口号。
- 每个观察项都要有“通过动作”和“失败动作”。
- 必须区分盘前、盘中、尾盘、收盘后四类检查点。
- 若盘面已经变了，观察清单也要跟着重排优先级。
When To Use
- 用户说“把观察项落下来”
- 用户要每日复核框架
- 已经有了组合和市场判断，想转成执行清单
- 用户要知道明天、后天每天应该盯哪些变量
Workflow
Step 1: 确认当前主场景
先拿最新盘面确认今天市场处在哪个环境里，再决定观察顺序。不要直接复用上次的清单。
Step 2: 分层观察
至少拆成五层：
- 宏观或事件触发层
- 指数与广度层
- 主线板块层
- 持仓层
- 备用候选层
Step 3: 设定检查时点
默认四个观察窗口：
- 开盘后快速确认
- 上午中段
- 午后关键时段
- 收盘复核
Step 4: 写动作规则
每个观察项都写成：
- 看什么
- 看多久
- 通过时做什么
- 失败时做什么
Step 5: 输出次日延续条件
告诉用户哪些条件出现时，应重新调用：
- 市场扫描
- 组合校准
- 动作路由
- 假设拆解
Tool Rules
- 观察项依赖最新数据，优先当日盘面
- 与持仓相关的观察项要对准用户真实持仓，不做泛化监控
- 若缺实时数据，可给观察框架，但要明确“需在盘中补数”
Output Contract
默认输出：
今日观察主轴检查时点逐项观察表通过动作失败动作何时重开分析
Practical Notes
- 观察清单宁可少而关键，不要列成无法执行的长表
- 同一主线内，优先盯龙头、成交、承接，而不是盯所有跟风票
- 若用户有明确持仓，观察清单里必须单列持仓项
Inputs & Preconditions
- 需要有当前市场主场景、用户持仓或候选方向中的至少一类输入
- 若用户要“每天去看”，应明确时间窗口是盘前、盘中、尾盘还是收盘后
- 若没有最新盘面，只能先给观察框架，不能假装已完成当日复核
Dependency Profile
- 必需依赖：一个支持 skill 的 agent 运行环境
- 建议依赖：当日市场数据源或网页源
- 可选依赖：持仓清单、候选池、宏观观察变量
- 降级策略：若缺实时数据，仍可生成观察模板，但必须单列待补数据
Data Gap Handling
- 缺实时盘面时，用
需在盘中补数明示，不写伪观察结论 - 缺持仓明细时，只保留市场层和主线层观察
- 观察项若无法在当日验证，应下调优先级或移出主清单
- 不伪造通过条件、失败条件和时点变化
Risk Language
- 不把观察清单包装成确定性交易系统
- 不使用收益承诺或过度确定性措辞
- 所有检查点都应允许失败，并配对应动作
Short Disclaimer
本 skill 仅用于投资研究流程、信息整理与教育演示，不构成投资建议、个性化荐股、投顾服务或自动交易指令。
This skill is for research workflow, information organization, and educational use only. It is not investment advice, not personalized recommendation, and not for automated trading.
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.
- 10d ago First seen · 126 lines · 64 tokens per session scan A 765575e9f856
a-share-observation-loop is a skill published in the GitHub repository minguncle/a-share-agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,069 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 2026-08-31.
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.