ai-governance-legal

Claude for Legal for Codex CLI

Codex CLI adaptation of Anthropic's Claude for Legal reference skills. This fork exposes the legal workflows as Codex-compatible skills under .codex/skills/ while preserving the upstream Claude plugin source directories.

New here? Start with QUICKSTART.md — install the Codex skills in 60 seconds. This README is the full reference.

This repository now has three surfaces from one source:

• Codex CLI skills — 151 converted skills in .codex/skills/<plugin>-<skill>/SKILL.md, ready to copy or sync into a Codex skills root.
• Upstream Claude plugins — the original <plugin>/skills/<skill>/SKILL.md, .claude-plugin/plugin.json, .mcp.json, agents, and hooks remain intact for Claude plugin users.
• Claude Managed Agent cookbooks — scheduled-agent templates under managed-agent-cookbooks/ remain unchanged.

[!IMPORTANT] Every output from these skills is a draft for attorney review — not legal advice, not a legal conclusion, not a substitute for a lawyer. They are built with guardrails that reflect that: source attribution on every citation, conservative defaults on privilege and subjective legal calls, jurisdiction assumptions surfaced, and explicit gates before anything is filed, sent, or relied on. A lawyer reviews, verifies, and takes professional responsibility for anything that leaves the building. These skills make that review faster; they do not replace it.

These skills do not represent Anthropic's legal positions. They are tools that help lawyers analyze issues. Where a skill includes a checklist item, a suggested framework, a risk flag, or a characterization of case law or regulatory guidance, that is an aid to the reviewing attorney's own analysis, not a statement of Anthropic's view of the law. The law in many of these areas is unsettled and evolving. The attorney using the skill — not the skill, not this fork, and not Anthropic — is responsible for the legal positions taken in their work product.

What's in the repo:

• Codex practice-area skills covering in-house, firm, and academic legal work — each one adapted from the upstream Claude skill and wired to a Codex-side practice profile under ~/.codex/claude-for-legal/.
• Practice-area Claude plugins covering the same workflows — each one built around a cold-start interview that learns your playbook and a CLAUDE.md practice profile that every skill reads from.
• Managed-agent cookbooks for the scheduled, eyes-on-the-feed workflows (renewal watcher, docket watcher, regulatory feed monitor, diligence grid, launch radar).
• MCP connectors across general productivity (Slack, Google Drive, Box) and legal-specific systems (Ironclad, DocuSign, iManage, Everlaw, CourtListener, and more).
• Named agents — end-to-end workflow agents (Vendor Agreement Reviewer, DSAR Responder, Termination Reviewer, Claim Chart Builder, …) with job-style names and a single command to run each one.

Agents

Each agent is named for the workflow it runs. They're the most common surface — start with the ones that match your work, then tune the underlying skill, the practice profile, and the connectors to how your team does it.

The command column keeps the upstream Claude slash-command form. In Codex CLI, use the converted skill name by replacing /plugin:skill with plugin-skill; for example, /privacy-legal:dsar-response becomes privacy-legal-dsar-response.