Claude Code Adds Owner-Wildcard Marketplace Controls, Letting One Rule Allow or Block an Entire GitHub Org

An allowlist policy nobody can keep up with is effectively no policy at all — owner wildcards solve exactly the problem of rules falling behind an organization's growth.

Grace Lindqvist · August 14, 2026

A recent Claude Code update gives administrators finer-grained Plugin marketplace controls: through the strictKnownMarketplaces managed setting, admins can now use an owner-wildcard form to allow or Block every marketplace repository under a given GitHub organization with a single rule, instead of listing each repository name individually. Alongside this, a new Plugin distribution method called archive has been added, letting a plugin be installed by downloading a zip file over HTTPS — no...

reviews

Reviewing Superpowers: A TDD Framework That Literally Deletes Code Written Before Tests Exist

Most frameworks tell you how to write tests. Superpowers writes "no...

advanced

CLAUDE.md, Rules, Skills, Hooks, Subagents — Which One? Anthropic's Official Seven-Method Decision Framework

"Never do this" written in CLAUDE.md is a hope. Written as a hook, it's an...

reviews

Reviewing Anthropic's Frontend Design Skill: Why Is It Installed 57× More Than the Runner-Up?

It doesn't tell Claude which color to use — it tells Claude not to keep...

Glossary

View All →

Few-Shot Prompting

Instead of describing in words what output you want, giving a few concrete input-output example pairs directly, letting Claude infer the style and format you're after from the examples themselves — often conveying detail more precisely than a written description can.

What is <a href="/en/glossary/prompt-engineering/few-shot-prompting/">Few-Shot Prompting</a>, and how does it differ from purely describing the...

beginner

Prompt Chaining

Breaking a complex task into a sequence of smaller prompts where each step's output feeds the next, trading a single mega-prompt for checkpoints you can inspect and correct along the way.

What is <a href="/en/glossary/prompt-engineering/prompt-chaining/">Prompt Chaining</a>, and how does it differ from one large...

intermediate

Inference Hooks

Before every request reaches the model, an organization's own security server inspects the content first and returns an allow-or-deny verdict, which Claude enforces in real time — rather than relying on after-the-fact audits to catch problems retroactively.

What are Inference Hooks, and how do they differ from typical content filtering? Inference Hooks are a mechanism that intercepts a request before...

advanced

Weekly Picks

prompt-examples

Writing Your First System Prompt: From "You Are an Assistant" to a Role Setup That Actually Works

"You are a senior expert" doesn't make Claude any more expert — telling it how that expert would...

Ryan Castillo

news

New MCP Spec Ships: Connectors No Longer Need to Maintain Session State, Claude's Directory Passes 950 Servers

Connectors no longer having to manage their own connection state sounds technical, but the real...

Adrian Koch

news

Claude Can Now Load Skills Straight from a GitHub Repo — and the Docs Warn This Widens Your Trust Boundary

Letting skills travel with the codebase is convenient — but it also means anyone who can merge a...

Grace Lindqvist

beginners

A Developer's First Code Review with Claude Code: The Full Walkthrough and Common Pitfalls

Treat a code review result as a rulebook, and you'll follow it blindly. Treat it as feedback...

Adrian Koch