kansoku — security grade SAFE, quality 56/100

Security audit verdict: SAFE · quality 56/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by kansoku-trade · Agent Tool · ★ 317

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is kansoku safe to install? View the security audit →

About kansoku

Kansoku 装在你 Mac 上的能查账的 AI 看盘搭子——它说的每句话你都能查:每个结论挂着完整证据链,归档之后不许改口,事后按命中率记分。 Kansoku(観測) 是一个 macOS 桌面应用:行情从你自己的长桥账户拉,指标全部本地实算,AI 用你自己配置的模型盯盘、答疑、改研究稿,结论落成本地文件。数据和 key 都不出你的机器。 下载安装 去 Releases 下载最新 版本的 (macOS · Apple Silicon),拖进「应用程序」即可。应用内置 Sparkle 自动更新(EdDSA 签名 + 增量包),装一次就不用再回来手动下载。 前置依赖:本机安装并登录 longbridge CLI(行情和账户数据都走它)。应用当前没有付费开发者签名,首次打开需要右键 →「打开」,详见 。 首次启动有引导:连上长桥数据,再选一个 AI 接入方式(本机 codex 登录态 / LobeHub Cloud / 自带 API key),也可以先跳过。 AI 能做什么 盘中自动点评,关掉图表还在巡检 —— 打开一只票,AI 结合多周期 K 线、形态标注和实时行情给出短线方向判断,以及 Bull/Base/Bear 三档情景推演(概率合计 100%,附触发条件)。开启跟进后,关掉图表它仍在后台按行情巡检,判断变了就通知你。右栏还带财报与宏观事件日历,页签在预测、环境、消息、复盘和 AI 点评之间切换。 追着分析问下去 —— 每份分析都能就地追问「凭什么」。面板浮在图上,可拖走、可缩放、可全屏。AI 会先读你的画线再结合实时行情回答;让它标关键价位时会直接画到图上(紫色虚线,悬停看说明),工具条可一键只清 AI 画的线。查了什么数据全程留痕,点开就是工具调用详情;答歪了随时停止,半截回答不会丢;空面板会先替你想好三个最该问的问题。已归档的预测是冻结记录,追问只解释、不改写。 研究库 AI 助手 —— 在应用里翻看和搜索本地的股票档案与研究日志,文档内直接对话提问。助手能

agent-skillsfastifylongbridgemarket-intelligencereactstock-analysistrading-journaltypescriptus-stocks

Quick Facts

Stars317
Forks38
LanguageTypeScript
CategoryAgent Tool
Quality Score56.1133064310295/100
Open Issues5
Last Updated2026-09-19
Created2026-06-24
Platformsnode
Est. Tokens~15k

Compatible Skills

These tools work well together with kansoku for enhanced workflows:

  • kansoku — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (75%)
  • trade-skills — semantic(0.70)+rare_topics+same_lang+similar_pop+shared_platform (75%)
  • Opptrix — semantic(0.35)+complementary+rare_topics+same_lang+similar_pop+shared_platform (71%)
  • Vibe-Research — semantic(0.35)+complementary+rare_topics+same_lang+similar_pop+shared_platform (67%)

kansoku alternative? Top 6 similar tools

Looking for a kansoku alternative? If you're comparing kansoku with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • kansoku by Innei · ⭐ 206

    AI Stock Partner on Your Mac – Local Market Information, Multi-timeframe K-line, AI Intraday Comments and Foll

  • trade-skills by Innei · ⭐ 111

    Personal U.S. stock trading research workspace with market-intelligence agent skills and a local realtime char

  • claudex by kunwar-shah · ⭐ 92

    MCP server with persistent memory + FTS5 search for Claude Code conversation history. Index your ~/.claude/pro

  • projx by ukanhaupa · ⭐ 71

    Projx — A CLI tool for scaffolding production-grade projects. Pick your stack (FastAPI, Fastify, React, Flutte

  • tabularis by debba · ⭐ 1.2k

    A lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable

  • ChattyPlay-Agent by P1kaj1uu · ⭐ 920

    🚀 告别多个App!本项目主要基于Python+React+TypeScript+Hono+SQLite3+Redis,打造“All in One”智能工具集。免会员播放爱奇艺、腾讯视频、优酷、抖音、B站、小红书等20

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is kansoku?

kansoku is AI Stock Partner on Your Mac – Local Market Information, Multi-timeframe K-line, AI Intraday Comments and Follow-up Analysis. It is categorized as a Agent Tool with 317 GitHub stars.

What programming language is kansoku written in?

kansoku is primarily written in TypeScript. It covers topics such as agent-skills, fastify, longbridge.

How do I install or use kansoku?

You can find installation instructions and usage details in the kansoku GitHub repository at github.com/kansoku-trade/kansoku. The project has 317 stars and 38 forks, indicating an active community.

What are the best alternatives to kansoku?

The top alternatives to kansoku on Agent Skills Hub include kansoku, trade-skills, claudex. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools