feat: auto-update Dockerfile with current claude-code npm version

- Add GitHub workflow to automatically check for new claude-code versions daily
- Pin CLAUDE_CODE_VERSION to 2.0.55 (instead of 'latest') in Dockerfile and devcontainer.json
- Workflow creates PRs when new versions are available, ensuring Docker cache invalidation

Fixes #582

.claude-plugin/marketplace.json

@@ -15,14 +15,25 @@
       "category": "development"
     },
     {
-      "name": "pr-review-toolkit",
-      "description": "Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification",
+      "name": "claude-opus-4-5-migration",
+      "description": "Migrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.",
       "version": "1.0.0",
       "author": {
-        "name": "Anthropic",
-        "email": "support@anthropic.com"
+        "name": "William Hu",
+        "email": "whu@anthropic.com"
       },
-      "source": "./plugins/pr-review-toolkit",
+      "source": "./plugins/claude-opus-4-5-migration",
+      "category": "development"
+    },
+    {
+      "name": "code-review",
+      "description": "Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives",
+      "version": "1.0.0",
+      "author": {
+        "name": "Boris Cherny",
+        "email": "boris@anthropic.com"
+      },
+      "source": "./plugins/code-review",
       "category": "productivity"
     },
     {
@@ -36,39 +47,6 @@
       "source": "./plugins/commit-commands",
       "category": "productivity"
     },
-    {
-      "name": "feature-dev",
-      "description": "Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review",
-      "version": "1.0.0",
-      "author": {
-        "name": "Siddharth Bidasaria",
-        "email": "sbidasaria@anthropic.com"
-      },
-      "source": "./plugins/feature-dev",
-      "category": "development"
-    },
-    {
-      "name": "security-guidance",
-      "description": "Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns",
-      "version": "1.0.0",
-      "author": {
-        "name": "David Dworken",
-        "email": "dworken@anthropic.com"
-      },
-      "source": "./plugins/security-guidance",
-      "category": "security"
-    },
-    {
-      "name": "code-review",
-      "description": "Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives",
-      "version": "1.0.0",
-      "author": {
-        "name": "Boris Cherny",
-        "email": "boris@anthropic.com"
-      },
-      "source": "./plugins/code-review",
-      "category": "productivity"
-    },
     {
       "name": "explanatory-output-style",
       "description": "Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)",
@@ -81,15 +59,15 @@
       "category": "learning"
     },
     {
-      "name": "learning-output-style",
-      "description": "Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)",
+      "name": "feature-dev",
+      "description": "Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review",
       "version": "1.0.0",
       "author": {
-        "name": "Boris Cherny",
-        "email": "boris@anthropic.com"
+        "name": "Siddharth Bidasaria",
+        "email": "sbidasaria@anthropic.com"
       },
-      "source": "./plugins/learning-output-style",
-      "category": "learning"
+      "source": "./plugins/feature-dev",
+      "category": "development"
     },
     {
       "name": "frontend-design",
@@ -102,17 +80,6 @@
       "source": "./plugins/frontend-design",
       "category": "development"
     },
-    {
-      "name": "ralph-wiggum",
-      "description": "Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.",
-      "version": "1.0.0",
-      "author": {
-        "name": "Daisy Hollman",
-        "email": "daisy@anthropic.com"
-      },
-      "source": "./plugins/ralph-wiggum",
-      "category": "development"
-    },
     {
       "name": "hookify",
       "description": "Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.",
@@ -124,6 +91,17 @@
       "source": "./plugins/hookify",
       "category": "productivity"
     },
+    {
+      "name": "learning-output-style",
+      "description": "Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)",
+      "version": "1.0.0",
+      "author": {
+        "name": "Boris Cherny",
+        "email": "boris@anthropic.com"
+      },
+      "source": "./plugins/learning-output-style",
+      "category": "learning"
+    },
     {
       "name": "plugin-dev",
       "description": "Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.",
@@ -136,15 +114,37 @@
       "category": "development"
     },
     {
-      "name": "claude-opus-4-5-migration",
-      "description": "Migrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.",
+      "name": "pr-review-toolkit",
+      "description": "Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification",
       "version": "1.0.0",
       "author": {
-        "name": "William Hu",
-        "email": "whu@anthropic.com"
+        "name": "Anthropic",
+        "email": "support@anthropic.com"
       },
-      "source": "./plugins/claude-opus-4-5-migration",
+      "source": "./plugins/pr-review-toolkit",
+      "category": "productivity"
+    },
+    {
+      "name": "ralph-wiggum",
+      "description": "Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.",
+      "version": "1.0.0",
+      "author": {
+        "name": "Daisy Hollman",
+        "email": "daisy@anthropic.com"
+      },
+      "source": "./plugins/ralph-wiggum",
       "category": "development"
+    },
+    {
+      "name": "security-guidance",
+      "description": "Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns",
+      "version": "1.0.0",
+      "author": {
+        "name": "David Dworken",
+        "email": "dworken@anthropic.com"
+      },
+      "source": "./plugins/security-guidance",
+      "category": "security"
     }
   ]
 }

.devcontainer/Dockerfile

@@ -3,7 +3,7 @@ FROM node:20
 ARG TZ
 ENV TZ="$TZ"
 
-ARG CLAUDE_CODE_VERSION=latest
+ARG CLAUDE_CODE_VERSION=2.0.55
 
 # Install basic development tools and iptables/ipset
 RUN apt-get update && apt-get install -y --no-install-recommends \

.devcontainer/devcontainer.json

@@ -4,7 +4,7 @@
     "dockerfile": "Dockerfile",
     "args": {
       "TZ": "${localEnv:TZ:America/Los_Angeles}",
-      "CLAUDE_CODE_VERSION": "latest",
+      "CLAUDE_CODE_VERSION": "2.0.55",
       "GIT_DELTA_VERSION": "0.18.2",
       "ZSH_IN_DOCKER_VERSION": "1.2.0"
     }

.github/workflows/update-devcontainer-version.yml

@@ -0,0 +1,62 @@
+name: Update DevContainer Claude Code Version
+
+on:
+  schedule:
+    # Run daily at 00:00 UTC
+    - cron: '0 0 * * *'
+  workflow_dispatch:  # Allow manual trigger
+
+jobs:
+  update-version:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pull-requests: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683  # v4
+
+      - name: Get latest npm version
+        id: npm-version
+        run: |
+          LATEST_VERSION=$(npm view @anthropic-ai/claude-code version)
+          echo "version=$LATEST_VERSION" >> $GITHUB_OUTPUT
+          echo "Latest npm version: $LATEST_VERSION"
+
+      - name: Get current version from Dockerfile
+        id: current-version
+        run: |
+          CURRENT_VERSION=$(grep -oP 'ARG CLAUDE_CODE_VERSION=\K[^\s]+' .devcontainer/Dockerfile)
+          echo "version=$CURRENT_VERSION" >> $GITHUB_OUTPUT
+          echo "Current version: $CURRENT_VERSION"
+
+      - name: Update version if changed
+        if: steps.npm-version.outputs.version != steps.current-version.outputs.version
+        run: |
+          NEW_VERSION="${{ steps.npm-version.outputs.version }}"
+
+          # Update Dockerfile
+          sed -i "s/ARG CLAUDE_CODE_VERSION=.*/ARG CLAUDE_CODE_VERSION=$NEW_VERSION/" .devcontainer/Dockerfile
+
+          # Update devcontainer.json
+          sed -i "s/\"CLAUDE_CODE_VERSION\": \".*\"/\"CLAUDE_CODE_VERSION\": \"$NEW_VERSION\"/" .devcontainer/devcontainer.json
+
+          echo "Updated version to $NEW_VERSION"
+
+      - name: Create Pull Request
+        if: steps.npm-version.outputs.version != steps.current-version.outputs.version
+        uses: peter-evans/create-pull-request@v7
+        with:
+          commit-message: "chore: update devcontainer claude-code to v${{ steps.npm-version.outputs.version }}"
+          title: "chore: update devcontainer claude-code to v${{ steps.npm-version.outputs.version }}"
+          body: |
+            This PR automatically updates the claude-code version in the devcontainer configuration.
+
+            **Changes:**
+            - Updated `CLAUDE_CODE_VERSION` from `${{ steps.current-version.outputs.version }}` to `${{ steps.npm-version.outputs.version }}`
+
+            This ensures Docker cache is invalidated when rebuilding images, allowing users to get the latest claude-code version.
+
+            Related: #582
+          branch: chore/update-claude-code-version
+          delete-branch: true

CHANGELOG.md

@@ -1,5 +1,36 @@
 # Changelog
 
+## 2.0.55
+
+- Fixed proxy DNS resolution being forced on by default. Now opt-in via `CLAUDE_CODE_PROXY_RESOLVES_HOSTS=true` environment variable
+- Fixed keyboard navigation becoming unresponsive when holding down arrow keys in memory location selector
+- Improved AskUserQuestion tool to auto-submit single-select questions on the last question, eliminating the extra review screen for simple question flows
+- Improved fuzzy matching for `@` file suggestions with faster, more accurate results
+
+## 2.0.54
+
+- Hooks: Enable PermissionRequest hooks to process 'always allow' suggestions and apply permission updates
+- Fix issue with excessive iTerm notifications
+
+## 2.0.52
+
+- Fixed duplicate message display when starting Claude with a command line argument
+- Fixed `/usage` command progress bars to fill up as usage increases (instead of showing remaining percentage)
+- Fixed image pasting not working on Linux systems running Wayland (now falls back to wl-paste when xclip is unavailable)
+- Permit some uses of `$!` in bash commands
+
+## 2.0.51
+
+- Added Opus 4.5! https://www.anthropic.com/news/claude-opus-4-5
+- Introducing Claude Code for Desktop: https://claude.com/download
+- To give you room to try out our new model, we've updated usage limits for Claude Code users. See the Claude Opus 4.5 blog for full details
+- Pro users can now purchase extra usage for access to Opus 4.5 in Claude Code
+- Plan Mode now builds more precise plans and executes more thoroughly
+- Usage limit notifications now easier to understand
+- Switched `/usage` back to "% used"
+- Fixed handling of thinking errors
+- Fixed performance regression
+
 ## 2.0.50
 
 - Fixed bug preventing calling MCP tools that have nested references in their input schemas

plugins/README.md

@@ -10,50 +10,21 @@ Learn more in the [official plugins documentation](https://docs.claude.com/en/do
 
 ## Plugins in This Directory
 
-### [agent-sdk-dev](./agent-sdk-dev/)
-
-**Claude Agent SDK Development Plugin**
-
-Streamlines the development of Claude Agent SDK applications with scaffolding commands and verification agents.
-
-- **Command**: `/new-sdk-app` - Interactive setup for new Agent SDK projects
-- **Agents**: `agent-sdk-verifier-py` and `agent-sdk-verifier-ts` - Validate SDK applications against best practices
-- **Use case**: Creating and verifying Claude Agent SDK applications in Python or TypeScript
-
-### [commit-commands](./commit-commands/)
-
-**Git Workflow Automation Plugin**
-
-Simplifies common git operations with streamlined commands for committing, pushing, and creating pull requests.
-
-- **Commands**:
-  - `/commit` - Create a git commit with appropriate message
-  - `/commit-push-pr` - Commit, push, and create a PR in one command
-  - `/clean_gone` - Clean up stale local branches marked as [gone]
-- **Use case**: Faster git workflows with less context switching
-
-### [code-review](./code-review/)
-
-**Automated Pull Request Code Review Plugin**
-
-Provides automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives.
-
-- **Command**:
-  - `/code-review` - Automated PR review workflow
-- **Use case**: Automated code review on pull requests with high-confidence issue detection (threshold ≥80)
-
-### [feature-dev](./feature-dev/)
-
-**Comprehensive Feature Development Workflow Plugin**
-
-Provides a structured 7-phase approach to feature development with specialized agents for exploration, architecture, and review.
-
-- **Command**: `/feature-dev` - Guided feature development workflow
-- **Agents**:
-  - `code-explorer` - Deeply analyzes existing codebase features
-  - `code-architect` - Designs feature architectures and implementation blueprints
-  - `code-reviewer` - Reviews code for bugs, quality issues, and project conventions
-- **Use case**: Building new features with systematic codebase understanding and quality assurance
+| Name | Description | Contents |
+|------|-------------|----------|
+| [agent-sdk-dev](./agent-sdk-dev/) | Development kit for working with the Claude Agent SDK | **Command:** `/new-sdk-app` - Interactive setup for new Agent SDK projects<br>**Agents:** `agent-sdk-verifier-py`, `agent-sdk-verifier-ts` - Validate SDK applications against best practices |
+| [claude-opus-4-5-migration](./claude-opus-4-5-migration/) | Migrate code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5 | **Skill:** `claude-opus-4-5-migration` - Automated migration of model strings, beta headers, and prompt adjustments |
+| [code-review](./code-review/) | Automated PR code review using multiple specialized agents with confidence-based scoring to filter false positives | **Command:** `/code-review` - Automated PR review workflow<br>**Agents:** 5 parallel Sonnet agents for CLAUDE.md compliance, bug detection, historical context, PR history, and code comments |
+| [commit-commands](./commit-commands/) | Git workflow automation for committing, pushing, and creating pull requests | **Commands:** `/commit`, `/commit-push-pr`, `/clean_gone` - Streamlined git operations |
+| [explanatory-output-style](./explanatory-output-style/) | Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style) | **Hook:** SessionStart - Injects educational context at the start of each session |
+| [feature-dev](./feature-dev/) | Comprehensive feature development workflow with a structured 7-phase approach | **Command:** `/feature-dev` - Guided feature development workflow<br>**Agents:** `code-explorer`, `code-architect`, `code-reviewer` - For codebase analysis, architecture design, and quality review |
+| [frontend-design](./frontend-design/) | Create distinctive, production-grade frontend interfaces that avoid generic AI aesthetics | **Skill:** `frontend-design` - Auto-invoked for frontend work, providing guidance on bold design choices, typography, animations, and visual details |
+| [hookify](./hookify/) | Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or explicit instructions | **Commands:** `/hookify`, `/hookify:list`, `/hookify:configure`, `/hookify:help`<br>**Agent:** `conversation-analyzer` - Analyzes conversations for problematic behaviors<br>**Skill:** `writing-rules` - Guidance on hookify rule syntax |
+| [learning-output-style](./learning-output-style/) | Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style) | **Hook:** SessionStart - Encourages users to write meaningful code (5-10 lines) at decision points while receiving educational insights |
+| [plugin-dev](./plugin-dev/) | Comprehensive toolkit for developing Claude Code plugins with 7 expert skills and AI-assisted creation | **Command:** `/plugin-dev:create-plugin` - 8-phase guided workflow for building plugins<br>**Agents:** `agent-creator`, `plugin-validator`, `skill-reviewer`<br>**Skills:** Hook development, MCP integration, plugin structure, settings, commands, agents, and skill development |
+| [pr-review-toolkit](./pr-review-toolkit/) | Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification | **Command:** `/pr-review-toolkit:review-pr` - Run with optional review aspects (comments, tests, errors, types, code, simplify, all)<br>**Agents:** `comment-analyzer`, `pr-test-analyzer`, `silent-failure-hunter`, `type-design-analyzer`, `code-reviewer`, `code-simplifier` |
+| [ralph-wiggum](./ralph-wiggum/) | Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly until completion | **Commands:** `/ralph-loop`, `/cancel-ralph` - Start/stop autonomous iteration loops<br>**Hook:** Stop - Intercepts exit attempts to continue iteration |
+| [security-guidance](./security-guidance/) | Security reminder hook that warns about potential security issues when editing files | **Hook:** PreToolUse - Monitors 9 security patterns including command injection, XSS, eval usage, dangerous HTML, pickle deserialization, and os.system calls |
 
 ## Installation