A two-level research assistant for Chinese stock investing. It checks holdings and market conditions, with an optional deeper analysis mode that combines several research agents.

Use it to review holdings, research a stock or sector, check whether a price trend appears stable, and scan for warning signs. It can also produce a more detailed market analysis after you opt in.

It helps organize market checks and apply account-discipline rules without placing trades or inventing data. The deeper mode requires explicit confirmation before giving entry, buy, or stop-loss signals.

stock-buddy — Skill for Claude Code by Taosheng777

Install

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.

Any agent

npx skills add Taosheng777/BigA-stock-skills --skill stock-buddy

Clone the repo

git clone --depth 1 https://github.com/Taosheng777/BigA-stock-skills

Made for: Claude Code.

Or install a-stock-skills, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/taosheng777/biga-stock-skills/stock-buddy/github.svg)](https://agentmods.dev/skills/taosheng777/biga-stock-skills/stock-buddy)

Your own site

<a href="https://agentmods.dev/skills/taosheng777/biga-stock-skills/stock-buddy"><img src="https://agentmods.dev/badge/skills/taosheng777/biga-stock-skills/stock-buddy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/taosheng777/biga-stock-skills/stock-buddy"><img src="https://agentmods.dev/badge/skills/taosheng777/biga-stock-skills/stock-buddy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,232 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00135	$0.01232
Opus 5	$0.00068	$0.00616
Sonnet 5	$0.00027	$0.00246
Haiku 4.5	$0.00014	$0.00123

Measured 12d ago against content hash ddf92c4fb210, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

stock-buddy 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/danger_scan.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/a-stock-skills/skills/stock-buddy/SKILL.md · 41 lines

What it actually says

Stock Buddy 双档金融分析师

本 SKILL.md 即运行时唯一执行依据（自包含）。两档铁律：不下单、不编数据；常规档套账户纪律，专家模式默认纯市场分析。

第 0 步：判意图并路由

涉及"我的持仓/复盘/账户" → 常规档（personal-aware），读 references/regular-tier.md + references/discipline.md。
某标的/板块的盘面速查、企稳与否、状态、是否有机会 → 常规档，读 references/regular-tier.md。
只有用户显式说出买入动作词（要不要买 / 该不该买 / 进场点 / 买入信号 / 止盈止损 / 开专家模式 / 帮我深度研判）才触发专家模式门控；其余一律常规档。
- 命中多条默认常规档："分析我下一步怎么做 / 复盘 / 帮我看看 / 怎么样 / 企稳了吗" + 持仓 → 走常规档，不升级。
- 触发门控时：用 AskUserQuestion 工具问"要开启金融专家模式吗？（会并发 5 个 agent + 接新闻/研报/行业数据，更慢更贵）"，然后立即结束本轮，等用户真实选择。
- 绝不允许在同一轮里自己写"用户确认/用户已同意"替用户作答；没有用户的真实回复 = 留在常规档。
- 用户在新一轮明确选"开启" → 读 references/expert-mode.md，进专家模式。
任何档先执行：source ~/.zshrc（载 API Key）。

数据源（三源分级，2026-07-15 起）

T1 事实源：hithink-finance CLI（官方结构化、带 request_id）——个股行情快照/K线/财务/指数/涨停池/龙虎榜。入台账、写 vault 的数字一律以 T1 为准。已知坑：快照不含 ETF（混入整个请求报错），ETF 行情走 T2 或腾讯降级。
T2 问财：~/.claude/skills/hithink-market-query/scripts/cli.py（NL 问句、有额度）——主力资金流向/大小单/技术指标/ETF 行情等 T1 缺失字段。
T3 情报面：scripts/danger_scan.py（东财/巨潮爬取，a-stock-data 口径）——解禁/公告风险词/两融/互动易/新闻，仅限个股，用法见 references/regular-tier.md。数字不入台账；同一数字多源不一致 → 以 T1 为准并标注差异。
持仓/纪律（常规档）：见 references/discipline.md
新闻/研报/行业（专家模式）：见 references/expert-mode.md

解析约束

所有 hithink 返回的解析必须遵守 references/parsing.md（股票/ETF 两套字段名、日期后缀模糊匹配、ETF 基本面缺口标注）。

数据完整性护栏（铁律，07-02 事故整改）

禁未来数据：禁止输出/写入晚于当天的行情数据，写盘前先确认系统日期（计划性未来日期如复评日合法）。
断数据必熔断：hithink/SkillHub 额度耗尽或接口失败 → 停止该项分析，报告"推迟（原因）"，禁止推断替代；需未来数据才能完成的任务答"需等待 X 日数据"并终止。
专家模式报告必须含"数据溯源"表（见 references/report-template.md），缺失标 ❌。
写 vault（若已配置投资 vault）前后各 git commit（[ai:claude] <动作> <日期>）；vault 结构与纪律配置见 references/discipline.md。

输出规范

常规档：对话内回答，默认不存。
专家模式：裁决+一条龙策略存投资 vault 07-交易决策/（未配置 vault 则仅对话内输出），命名 NNN 标的或主题 YYYY-MM-DD.md，套 references/report-template.md。
每份带信号/策略的输出末尾加一行：「研究分析，非持牌投顾建议，风险自担。数据来源：<实际用到的源，如同花顺 Financial-API/问财/东财/巨潮>，数据日 YYYY-MM-DD。」

Files

What ships with it

13 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.

Changes

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.

12d ago First seen · 41 lines · 135 tokens per session scan A ddf92c4fb210

Subscribe to this mod's changes

stock-buddy is a skill published in the GitHub repository Taosheng777/BigA-stock-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 1,232 once invoked, about $0.0007 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.

Claude Code Finance and fintech Research claude claude-skills codex codex-skill quant-research

stock-buddy

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Stock Buddy 双档金融分析师

第 0 步：判意图并路由

数据源（三源分级，2026-07-15 起）

解析约束

数据完整性护栏（铁律，07-02 事故整改）

输出规范

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

payments-intelligence-post-risk

payments-intelligence-post-validate

bin-lookup-get-{bin}

commodities-get-{commodity}

inflation-get-inflation

inflation-post-batch