chore: sync content to repo (#10518)

Co-authored-by: nilbuild <4921183+nilbuild@users.noreply.github.com>
2026-10-31 17:06:09 +01:00
1 parent 1a4d631f23
commit 38a96833d3
@@ -1,6 +1,6 @@
 # claude --bare -p

-`--bare` is a minimal startup mode for scripted calls with `-p`. It skips auto-discovery of hooks, skills, custom commands, subagents, installed plugins, MCP servers, auto memory and CLAUDE.md, so a run starts faster and behaves the same on every machine. You pass any context you need with flags such as `--settings`, `--mcp-config` or `--append-system-prompt`. Bare mode never reads OAuth credentials, so it needs an `ANTHROPIC_API_KEY` or a provider credential. The docs recommend it for CI and scripts, and say it will become the default for `-p` in a future release.
+`--bare` is a minimal startup mode for scripted calls with `-p`. It skips auto-discovery of hooks, skills, custom commands, subagents, installed plugins, MCP servers, auto memory and [CLAUDE.md](http://CLAUDE.md), so a run starts faster and behaves the same on every machine. You pass any context you need with flags such as `--settings`, `--mcp-config` or `--append-system-prompt`. Bare mode never reads OAuth credentials, so it needs an `ANTHROPIC_API_KEY` or a provider credential. The docs recommend it for CI and scripts, and say it will become the default for `-p` in a future release.

 Visit the following resources to learn more:

@@ -1,6 +1,6 @@
 # claude --teleport

-`claude --teleport` pulls a cloud session into your local terminal. Claude Code checks that you are in a checkout of the same repository, fetches and checks out the session's branch, and loads the full conversation history. Without an ID it opens an interactive session picker, and `claude --teleport <session-id>` resumes a specific session. You need a claude.ai login, a clean git state (it offers to stash your changes) and a branch that was pushed. The terminal gets its own copy of the session, so new work there does not appear in the cloud session.
+`claude --teleport` pulls a cloud session into your local terminal. Claude Code checks that you are in a checkout of the same repository, fetches and checks out the session's branch, and loads the full conversation history. Without an ID it opens an interactive session picker, and `claude --teleport <session-id>` resumes a specific session. You need a [claude.ai](http://claude.ai) login, a clean git state (it offers to stash your changes) and a branch that was pushed. The terminal gets its own copy of the session, so new work there does not appear in the cloud session.

 Visit the following resources to learn more:

@@ -1,6 +1,6 @@
 # Agent SDK

-The Agent SDK gives you the same tools, agent loop and context management that power Claude Code, as a library for Python and TypeScript. You use it to embed an agent in your own application, with built-in tools for reading files, running commands and searching the web. It also includes hooks, subagents, MCP, permissions and sessions, and it loads skills and CLAUDE.md files from your project. Authentication uses an API key, and the SDK was previously called the Claude Code SDK.
+The Agent SDK gives you the same tools, agent loop and context management that power Claude Code, as a library for Python and TypeScript. You use it to embed an agent in your own application, with built-in tools for reading files, running commands and searching the web. It also includes hooks, subagents, MCP, permissions and sessions, and it loads skills and [CLAUDE.md](http://CLAUDE.md) files from your project. Authentication uses an API key, and the SDK was previously called the Claude Code SDK.

 Visit the following resources to learn more:

@@ -1,6 +1,6 @@
 # Artifacts

-Artifacts turn Claude Code's work into live web pages hosted on claude.ai. When terminal text is the wrong medium, such as an annotated pull request, a dashboard or a set of design options, Claude writes an HTML or Markdown page and publishes it to a private URL. The page updates in place when Claude republishes, and you share it from the page header with specific people, your organization or a public link. Pages can pull live data through your MCP connectors, and `/artifacts` lists the ones you own. They need a claude.ai login and are not available through Amazon Bedrock, Google Cloud's Agent Platform or Microsoft Foundry.
+Artifacts turn Claude Code's work into live web pages hosted on [claude.ai](http://claude.ai). When terminal text is the wrong medium, such as an annotated pull request, a dashboard or a set of design options, Claude writes an HTML or Markdown page and publishes it to a private URL. The page updates in place when Claude republishes, and you share it from the page header with specific people, your organization or a public link. Pages can pull live data through your MCP connectors, and `/artifacts` lists the ones you own. They need a [claude.ai](http://claude.ai) login and are not available through Amazon Bedrock, Google Cloud's Agent Platform or Microsoft Foundry.

 Visit the following resources to learn more:

@@ -1,6 +1,6 @@
 # CI/CD

-CI/CD integration runs Claude Code inside your pipelines to review pull requests, triage issues and turn requests into code changes. It is built on the CLI and Agent SDK, so a job runs `claude -p` with a prompt and a limited set of allowed tools. Claude follows your CLAUDE.md rules, and its changes arrive as pull or merge requests that go through your normal approvals. Claude Code provides ready integrations for GitHub Actions and GitLab CI/CD.
+CI/CD integration runs Claude Code inside your pipelines to review pull requests, triage issues and turn requests into code changes. It is built on the CLI and Agent SDK, so a job runs `claude -p` with a prompt and a limited set of allowed tools. Claude follows your [CLAUDE.md](http://CLAUDE.md) rules, and its changes arrive as pull or merge requests that go through your normal approvals. Claude Code provides ready integrations for GitHub Actions and GitLab CI/CD.

 Visit the following resources to learn more:

@@ -6,4 +6,5 @@ Visit the following resources to learn more:

 - [@official@Code Review](https://code.claude.com/docs/en/code-review)
 - [@official@Set up Code Review](https://code.claude.com/docs/en/code-review-setup)
- [@official@Customize Code Review](https://code.claude.com/docs/en/code-review-customize)
+- [@official@Customize Code Review](https://code.claude.com/docs/en/code-review-customize)
+- [@article@Claude Code Review: /code-review for Diffs and PRs](https://claudcod.com/blog/claude-code-review-command/)
@@ -1,6 +1,6 @@
 # /desktop

-`/desktop` continues your current terminal session in the Claude Code Desktop app, where you can review diffs visually. The handoff needs a claude.ai subscription and works on macOS and x64 Windows. `/app` is an alias.
+`/desktop` continues your current terminal session in the Claude Code Desktop app, where you can review diffs visually. The handoff needs a [claude.ai](http://claude.ai) subscription and works on macOS and x64 Windows. `/app` is an alias.

 Visit the following resources to learn more:

@@ -5,6 +5,6 @@ Claude Code desktop is a software application that allows an AI assistant to int
 Visit the following resources to learn more:

 - [@official@Claude Code on desktop](https://code.claude.com/docs/en/desktop)
- [@official@Get started with the desktop app](https://code.claude.com/docs/en/desktop-quickstart)
+- [@article@I Discovered Claude Code Desktop: The (New) Way to Build Faster Than Your Terminal](https://medium.com/@joe.njenga/i-discovered-claude-code-desktop-the-new-way-to-build-faster-than-your-terminal-1679aa6ce790)
 - [@video@Claude Code on desktop](https://www.youtube.com/watch?v=zrcCS9oHjtI)
 - [@video@Claude Code for Desktop is the BEST way to build apps with AI EVER](https://www.youtube.com/watch?v=pZ2N7CJFbBk)
@@ -0,0 +1,10 @@
+# Fable
+
+Claude Fable is the most capable model family in Claude Code, built for demanding reasoning and long-running agentic work such as root-cause investigations and architecture decisions. Fable 5.1 (claude-fable-5-1) is the current version, and you select it with /model fable because it is not the default on any plan. It has a 1M token context window and costs more than Opus, and depending on your plan its usage can bill to usage credits.
+
+Visit the following resources to learn more:
+
+- [@official@Claude Fable](https://www.anthropic.com/claude/fable)
+- [@official@Claude Fable features](https://platform.claude.com/docs/en/models/fable-5-1/overview)
+- [@article@Anthropic’s Fable 5.1 is a bit cheaper, a bit smarter, and refuses a lot less](https://thenewstack.io/anthropic-fable-5-1-launch/)
+- [@video@Claude Fable 5.1 in 9 Minutes](https://www.youtube.com/watch?v=c8BMPPaw5g4)
@@ -4,4 +4,6 @@ Claude Code GitLab CI/CD runs Claude Code in GitLab pipeline jobs. You add a job

 Visit the following resources to learn more:

- [@official@Claude Code GitLab CI/C](https://code.claude.com/docs/en/gitlab-ci-cd)
+- [@official@Claude Code GitLab CI/C](https://code.claude.com/docs/en/gitlab-ci-cd)
+- [@article@Secure every commit to production with Claude and GitLab](https://about.gitlab.com/blog/claude-security-and-gitlab/)
+- [@video@How To Use Claude Code With GitLab (Full Guide) \[Step By Step Guide\]](https://www.youtube.com/watch?v=-t8Lk16YQpo)
@@ -1,6 +1,6 @@
 # Remote Control

-Remote Control connects claude.ai/code or the Claude mobile app to a Claude Code session running on your own machine. Claude keeps running locally, so your filesystem, MCP servers and project configuration stay available while you drive the session from a phone, tablet or another browser. You start it with `claude remote-control`, with `/remote-control` in an open session, or with the `--remote-control` flag. The conversation stays in sync across every connected device, and you can send photos and files from the app.
+Remote Control connects [claude.ai/code](http://claude.ai/code) or the Claude mobile app to a Claude Code session running on your own machine. Claude keeps running locally, so your filesystem, MCP servers and project configuration stay available while you drive the session from a phone, tablet or another browser. You start it with `claude remote-control`, with `/remote-control` in an open session, or with the `--remote-control` flag. The conversation stays in sync across every connected device, and you can send photos and files from the app.

 Visit the following resources to learn more:

@@ -1,6 +1,6 @@
 # /remote-control

-`/remote-control` makes the current session available through Remote Control, so you can continue it from claude.ai/code or the Claude mobile app. Claude keeps running on your machine, so your filesystem, MCP servers and project configuration stay available. You can also start it from the shell with `claude remote-control`. It requires a claude.ai subscription.
+`/remote-control` makes the current session available through Remote Control, so you can continue it from [claude.ai/code](http://claude.ai/code) or the Claude mobile app. Claude keeps running on your machine, so your filesystem, MCP servers and project configuration stay available. You can also start it from the shell with `claude remote-control`. It requires a [claude.ai](http://claude.ai) subscription.

 Visit the following resources to learn more:

@@ -5,4 +5,5 @@ The sandboxed Bash tool wraps the shell commands Claude runs, and the processes
 Visit the following resources to learn more:

 - [@official@Configure the sandboxed Bash tool](https://code.claude.com/docs/en/sandboxing)
- [@official@Security](https://code.claude.com/docs/en/security)
+- [@official@Security](https://code.claude.com/docs/en/security)
+- [@article@Claude Code Sandboxing](https://cobusgreyling.medium.com/claude-code-sandboxing-b33d42b61888)
@@ -1,6 +1,6 @@
 # /schedule

-`/schedule` creates and manages cloud scheduled tasks, formerly called routines, from inside a session. Claude asks about the schedule, repositories and prompt, then saves the task to your account. You can pass a description directly, such as `/schedule daily PR review at 9am`, or a one-off like `/schedule in 2 weeks, open a cleanup PR`. `/schedule list`, `update` and `run` manage tasks you already have, and `/routines` is an alias. The command needs a claude.ai subscription login and a plan that includes cloud sessions.
+`/schedule` creates and manages cloud scheduled tasks, formerly called routines, from inside a session. Claude asks about the schedule, repositories and prompt, then saves the task to your account. You can pass a description directly, such as `/schedule daily PR review at 9am`, or a one-off like `/schedule in 2 weeks, open a cleanup PR`. `/schedule list`, `update` and `run` manage tasks you already have, and `/routines` is an alias. The command needs a [claude.ai](http://claude.ai) subscription login and a plan that includes cloud sessions.

 Visit the following resources to learn more:

@@ -4,4 +4,7 @@ Ultrareview is a deep code review that runs as a cloud session on Anthropic's in

 Visit the following resources to learn more:

- [@official@Find bugs with ultrareview](https://code.claude.com/docs/en/ultrareview)
+- [@official@Find bugs with ultrareview](https://code.claude.com/docs/en/ultrareview)
+- [@article@Claude Code /ultra review: 5 Things You Need to Know Before Running It](https://www.mindstudio.ai/blog/claude-code-ultra-review-5-things-to-know-before-running)
+- [@article@Claude Code Ultrareview: A Verified Multi-Agent Review](https://www.matthewswong.com/en/blog/claude-code-code-review-ultrareview/)
+- [@video@Claude Code advanced features: /review and the new /ultrareview](https://www.youtube.com/watch?v=vzbkBc3PyUY)
@@ -1,7 +1,6 @@
 # /ultrareview

-
-`ultrareview` is an alias of `/code-review ultra`. It starts an ultrareview, a deep review that runs as a cloud session on Anthropic's infrastructure. A fleet of reviewer agents explores the change in parallel, and each finding is independently reproduced and verified. It reviews your branch or a pull request, takes roughly 15 to 25 minutes in the background, and needs a claude.ai login. Pro and Max accounts get three free runs, then it bills as usage credits. `/ultrareview` is an alias when it is available to your account.
+`ultrareview` is an alias of `/code-review ultra`. It starts an ultrareview, a deep review that runs as a cloud session on Anthropic's infrastructure. A fleet of reviewer agents explores the change in parallel, and each finding is independently reproduced and verified. It reviews your branch or a pull request, takes roughly 15 to 25 minutes in the background, and needs a [claude.ai](http://claude.ai) login. Pro and Max accounts get three free runs, then it bills as usage credits. `/ultrareview` is an alias when it is available to your account.

 Visit the following resources to learn more:

@@ -1,6 +1,6 @@
 # Web

-Claude Code on the web runs sessions on cloud infrastructure instead of your machine. You start one at claude.ai/code, from the Code tab in the Claude app, from the Desktop app, or from the terminal with `claude --cloud`. The session keeps running after you close your laptop, and you can check on it or steer it from any device. Each session clones your GitHub repository into a cloud environment that controls network access, environment variables and setup scripts, and cloud sessions are available on Pro, Max, Team and Enterprise plans.
+Claude Code on the web runs sessions on cloud infrastructure instead of your machine. You start one at [claude.ai/code](http://claude.ai/code), from the Code tab in the Claude app, from the Desktop app, or from the terminal with `claude --cloud`. The session keeps running after you close your laptop, and you can check on it or steer it from any device. Each session clones your GitHub repository into a cloud environment that controls network access, environment variables and setup scripts, and cloud sessions are available on Pro, Max, Team and Enterprise plans.

 Visit the following resources to learn more: