shinkoku — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 kazukinagata · Agent Tool · ★ 359

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

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

About shinkoku

shinkoku 確定申告を自動化する AI コーディングエージェント向けプラグイン。個人事業主・会社員の所得税・消費税の確定申告を、帳簿の記帳から確定申告書等作成コーナーへの入力代行までエンドツーエンドで支援します。 Claude Code Plugin として動作するほか、SKILL.md オープン標準 に準拠した Agent Skills パッケージとして、Claude Code / Cursor / Windsurf / GitHub Copilot / Gemini CLI / Codex / Cline / Roo Code / Antigravity など 40 以上の AI コーディングエージェントで利用できます。 想定ユーザー 非対応 以下のケースには対応していません。 ⚠️ 免責事項 確定申告は自己責任で行ってください。 本ツールが生成した申告書・計算結果は、提出前に必ずご自身で内容を確認してください 税法の解釈や申告内容に不安がある場合は、税理士等の専門家に相談することを強く推奨します 本ツールの利用によって生じたいかなる損害についても、開発者は責任を負いません 税制は毎年改正されます。本ツールは令和7年分(2025年課税年度)の税制に基づいています インストール 前提条件 Python 3.11 以上 uv パッケージマネージャ CLI のインストール スキルが内部で コマンドを呼び出します。通常は スキルが自動でインストールしますが、手動で行う場合は以下を実行してください。 bash インストール u

agent-skillsbookkeepingclaude-code-pluginclaude-code-skillsjapanpythontax-filing

Quick Facts

Stars359
Forks34
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score61.2835189958553/100
Last Updated2026-09-09
Created2026-02-11
Platformsclaude-code, python
Est. Tokens~15k

Compatible Skills

These tools work well together with shinkoku for enhanced workflows:

  • cc-thingz — semantic(0.34)+complementary+same_lang+similar_pop+shared_platform (62%)
  • x64dbg-skills — semantic(0.30)+complementary+same_lang+similar_pop+shared_platform (60%)
  • claude-prime — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (60%)
  • bria-skill — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (59%)
  • pg-aiguide — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)

shinkoku alternative? Top 6 similar tools

Looking for a shinkoku alternative? If you're comparing shinkoku 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.

  • itr-wala by karanb192 · ⭐ 846

    File your Indian income tax return (ITR) from your terminal. Deterministic tax engine, both regimes, AY 2026-2

  • babysitter by a5c-ai · ⭐ 1.8k

    Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and wor

  • getspecstory by specstoryai · ⭐ 1.3k

    Install our local first extensions for your favorite AI IDE or Terminal Agent. Process your histories into reu

  • claude-code-ios-dev-guide by keskinonur · ⭐ 816

    A comprehensive guide for setting up Claude Code CLI with PRD-driven workflows, extended thinking (ultrathink)

  • ai-maestro by 23blocks-OS · ⭐ 789

    AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen

  • claude-code-skills by levnikolaevich · ⭐ 564

    Help your AI agent finish the job: solve the right problem, keep changes focused, and show what was verified.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is shinkoku?

shinkoku is 確定申告自動化 AI エージェントプラグイン — 帳簿管理から e-Tax 入力代行まで. It is categorized as a Agent Tool with 359 GitHub stars.

What programming language is shinkoku written in?

shinkoku is primarily written in Python. It covers topics such as agent-skills, bookkeeping, claude-code-plugin.

How do I install or use shinkoku?

You can find installation instructions and usage details in the shinkoku GitHub repository at github.com/kazukinagata/shinkoku. The project has 359 stars and 34 forks, indicating an active community.

What license does shinkoku use?

shinkoku is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to shinkoku?

The top alternatives to shinkoku on Agent Skills Hub include itr-wala, babysitter, getspecstory. 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