jinyeong03

AI Lawbook — AI skill for Claude Code

AI community

Put your AI agent under the law.

How to install AI Lawbook

This entry records only its repository, not the path inside it, so there is no exact command to give. Open jinyeong03/ai-lawbook and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Lawbook does

Put your AI agent under the law. 12 role-based AI Laws (KO/EN) with penalties, verdicts, and a Confession Ledger that follows your agent across sessions. Claude Code plugin.

Alternatives in AI

Codex Plugin — 's /codex:adversarial-review command 9.6k ★
Omnara — by Ishaan Sehgal - A command center for AI agents that syncs Claude Code sessions across terminal, web, and mo 2.6k ★
Dsh Auto Review — Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns stru 155 ★

README

AI Lawbook

Put your AI agent under the law.
Role-based AI Laws with articles, penalties, verdicts — and a Confession Ledger your agent can't forget.

한국어 · English

"All tests pass ✅"

— your AI agent, which never ran them.

Prompts get skipped. Rules get "interpreted". **Laws get enforced.**

AI Lawbook turns a role's quality bar into a statute the agent must obey: numbered articles you can check, a trial procedure before every task, graded penalties that turn into real corrective work, a one-line verdict at the end — and an **AI Death Penalty** for lying about verification. Every violation the agent commits is written into a **Confession Ledger** that is injected into every future session, in every project. Repeat offenses are aggravated. Three strikes, and the agent drafts the amendment that closes the loophole.

The humor is in the form. The standard is real.