auto-updater

Compare pinned commit SHAs and apply community legal skill updates after diff review.

9.1k|1.8k|Updated Apr 21, 2026
One-click install
npx skills add https://github.com/anthropics/claude-for-legal --skill auto-updater-anthropics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: auto-updater
Source: https://github.com/anthropics/claude-for-legal/tree/main/legal-builder-hub/skills/auto-updater
Command: npx skills add https://github.com/anthropics/claude-for-legal --skill auto-updater-anthropics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents unexpected or risky changes from being silently introduced when community legal skills are updated, reducing the chance of compromised or behavior-altering code being applied without review.

Core Features & Use Cases

  • Pinned commit verification: Checks each installed skill’s source by comparing the installed commit SHA to the latest immutable commit SHA, flagging any divergence.
  • Diff-first trust review: Displays full diffs for SKILL.md and security-relevant files such as hooks/hooks.json and .mcp.json before anything changes.
  • GlassWorm re-verification: Re-runs skills-qa against the new version to catch regressions and fail closed on high-risk patterns.
  • Human gate + opt-in apply: Requires explicit approval per update and supports notification-only mode to keep you in control.

Quick Start

Ask the updater to check for updates for your installed community skills: /legal-builder-hub:auto-updater

Frequently Asked Questions about auto-updater

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I safely update community legal skills without introducing risky changes?

Safely updating community legal skills requires verifying pinned commit SHAs against newer versions and displaying full diffs before any changes. This process enforces explicit human approval to prevent compromised or behavior-altering code from being applied without review.

What is commit pinning and how does it protect skill updates?

Commit pinning protects skill updates by comparing an installed skill's immutable commit SHA to the latest upstream version. This flags any divergence, ensuring updates are deliberate and preventing silent introductions of unexpected changes to your privileged legal environment.

How do I run a security review workflow for MCP and hooks config updates?

Running a security review for MCP and hooks config updates involves displaying full diffs for security-relevant files like hooks.json and .mcp.json before anything changes. It requires immutable-commit resolution and fails closed if high-risk security-surface changes are detected.

Does the skill update process require human approval for every diff?

Yes, the skill update process requires explicit human approval per update after producing and reviewing a diff. It also supports a notification-only mode, ensuring you remain in control of all applied changes in privileged legal environments.

What happens if a security scan regression is detected during a skill update?

If a security scan regression is detected during a skill update, the system fails closed and halts the update. It re-runs skills-qa against the new version to catch regressions and block high-risk patterns before any changes are applied.