feat: Add slack-quote-formatter plugin for better quoted message display

Adds a new plugin that transforms plain Slack forwarded message blocks into
visually distinctive formatted boxes using Unicode box-drawing characters.

Before:
  [Forwarded Message]
  From: Felix Klock
  Message: Here is some text...

After:
  ╔════════════════════════════════════════════════════════════════════╗
  ║  FORWARDED MESSAGE                                                 ║
  ╠════════════════════════════════════════════════════════════════════╣
  ║  From: Felix Klock                                                 ║
  ╟────────────────────────────────────────────────────────────────────╢
  ║    Here is some text...                                            ║
  ╚════════════════════════════════════════════════════════════════════╝

The plugin uses a UserPromptSubmit hook to intercept prompts containing
[Forwarded Message] blocks and reformats them for better visual distinction.

https://claude.ai/code/session_01YNRC6p2gAMSQZPX2NGK5F1

CHANGELOG.md

@@ -1,5 +1,114 @@
 # Changelog
 
+## 2.1.38
+
+- Fixed VS Code terminal scroll-to-top regression introduced in 2.1.37
+- Fixed Tab key queueing slash commands instead of autocompleting
+- Fixed bash permission matching for commands using environment variable wrappers
+- Fixed text between tool uses disappearing when not using streaming
+- Fixed duplicate sessions when resuming in VS Code extension
+- Improved heredoc delimiter parsing to prevent command smuggling
+- Blocked writes to `.claude/skills` directory in sandbox mode
+
+## 2.1.37
+
+- Fixed an issue where /fast was not immediately available after enabling /extra-usage
+
+## 2.1.36
+
+- Fast mode is now available for Opus 4.6. Learn more at https://code.claude.com/docs/en/fast-mode
+
+## 2.1.34
+
+- Fixed a crash when agent teams setting changed between renders
+- Fixed a bug where commands excluded from sandboxing (via `sandbox.excludedCommands` or `dangerouslyDisableSandbox`) could bypass the Bash ask permission rule when `autoAllowBashIfSandboxed` was enabled
+
+## 2.1.33
+
+- Fixed agent teammate sessions in tmux to send and receive messages
+- Fixed warnings about agent teams not being available on your current plan
+- Added `TeammateIdle` and `TaskCompleted` hook events for multi-agent workflows
+- Added support for restricting which sub-agents can be spawned via `Task(agent_type)` syntax in agent "tools" frontmatter
+- Added `memory` frontmatter field support for agents, enabling persistent memory with `user`, `project`, or `local` scope
+- Added plugin name to skill descriptions and `/skills` menu for better discoverability
+- Fixed an issue where submitting a new message while the model was in extended thinking would interrupt the thinking phase
+- Fixed an API error that could occur when aborting mid-stream, where whitespace text combined with a thinking block would bypass normalization and produce an invalid request
+- Fixed API proxy compatibility issue where 404 errors on streaming endpoints no longer triggered non-streaming fallback
+- Fixed an issue where proxy settings configured via `settings.json` environment variables were not applied to WebFetch and other HTTP requests on the Node.js build
+- Fixed `/resume` session picker showing raw XML markup instead of clean titles for sessions started with slash commands
+- Improved error messages for API connection failures — now shows specific cause (e.g., ECONNREFUSED, SSL errors) instead of generic "Connection error"
+- Errors from invalid managed settings are now surfaced
+- VSCode: Added support for remote sessions, allowing OAuth users to browse and resume sessions from claude.ai
+- VSCode: Added git branch and message count to the session picker, with support for searching by branch name
+- VSCode: Fixed scroll-to-bottom under-scrolling on initial session load and session switch
+
+## 2.1.32
+
+- Claude Opus 4.6 is now available!
+- Added research preview agent teams feature for multi-agent collaboration (token-intensive feature, requires setting CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1)
+- Claude now automatically records and recalls memories as it works
+- Added "Summarize from here" to the message selector, allowing partial conversation summarization.
+- Skills defined in `.claude/skills/` within additional directories (`--add-dir`) are now loaded automatically.
+- Fixed `@` file completion showing incorrect relative paths when running from a subdirectory
+- Updated --resume to re-use --agent value specified in previous conversation by default.
+- Fixed: Bash tool no longer throws "Bad substitution" errors when heredocs contain JavaScript template literals like `${index + 1}`, which previously interrupted tool execution
+- Skill character budget now scales with context window (2% of context), so users with larger context windows can see more skill descriptions without truncation
+- Fixed Thai/Lao spacing vowels (สระ า, ำ) not rendering correctly in the input field
+- VSCode: Fixed slash commands incorrectly being executed when pressing Enter with preceding text in the input field
+- VSCode: Added spinner when loading past conversations list
+
+## 2.1.31
+
+- Added session resume hint on exit, showing how to continue your conversation later
+- Added support for full-width (zenkaku) space input from Japanese IME in checkbox selection
+- Fixed PDF too large errors permanently locking up sessions, requiring users to start a new conversation
+- Fixed bash commands incorrectly reporting failure with "Read-only file system" errors when sandbox mode was enabled
+- Fixed a crash that made sessions unusable after entering plan mode when project config in `~/.claude.json` was missing default fields
+- Fixed `temperatureOverride` being silently ignored in the streaming API path, causing all streaming requests to use the default temperature (1) regardless of the configured override
+- Fixed LSP shutdown/exit compatibility with strict language servers that reject null params
+- Improved system prompts to more clearly guide the model toward using dedicated tools (Read, Edit, Glob, Grep) instead of bash equivalents (`cat`, `sed`, `grep`, `find`), reducing unnecessary bash command usage
+- Improved PDF and request size error messages to show actual limits (100 pages, 20MB)
+- Reduced layout jitter in the terminal when the spinner appears and disappears during streaming
+- Removed misleading Anthropic API pricing from model selector for third-party provider (Bedrock, Vertex, Foundry) users
+
+## 2.1.30
+
+- Added `pages` parameter to the Read tool for PDFs, allowing specific page ranges to be read (e.g., `pages: "1-5"`). Large PDFs (>10 pages) now return a lightweight reference when `@` mentioned instead of being inlined into context.
+- Added pre-configured OAuth client credentials for MCP servers that don't support Dynamic Client Registration (e.g., Slack). Use `--client-id` and `--client-secret` with `claude mcp add`.
+- Added `/debug` for Claude to help troubleshoot the current session
+- Added support for additional `git log` and `git show` flags in read-only mode (e.g., `--topo-order`, `--cherry-pick`, `--format`, `--raw`)
+- Added token count, tool uses, and duration metrics to Task tool results
+- Added reduced motion mode to the config
+- Fixed phantom "(no content)" text blocks appearing in API conversation history, reducing token waste and potential model confusion
+- Fixed prompt cache not correctly invalidating when tool descriptions or input schemas changed, only when tool names changed
+- Fixed 400 errors that could occur after running `/login` when the conversation contained thinking blocks
+- Fixed a hang when resuming sessions with corrupted transcript files containing `parentUuid` cycles
+- Fixed rate limit message showing incorrect "/upgrade" suggestion for Max 20x users when extra-usage is unavailable
+- Fixed permission dialogs stealing focus while actively typing
+- Fixed subagents not being able to access SDK-provided MCP tools because they were not synced to the shared application state
+- Fixed a regression where Windows users with a `.bashrc` file could not run bash commands
+- Improved memory usage for `--resume` (68% reduction for users with many sessions) by replacing the session index with lightweight stat-based loading and progressive enrichment
+- Improved `TaskStop` tool to display the stopped command/task description in the result line instead of a generic "Task stopped" message
+- Changed `/model` to execute immediately instead of being queued
+- [VSCode] Added multiline input support to the "Other" text input in question dialogs (use Shift+Enter for new lines)
+- [VSCode] Fixed duplicate sessions appearing in the session list when starting a new conversation
+
+## 2.1.29
+
+- Fixed startup performance issues when resuming sessions that have `saved_hook_context`
+
+## 2.1.27
+
+- Added tool call failures and denials to debug logs
+- Fixed context management validation error for gateway users, ensuring `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` avoids the error
+- Added `--from-pr` flag to resume sessions linked to a specific GitHub PR number or URL
+- Sessions are now automatically linked to PRs when created via `gh pr create`
+- Fixed /context command not displaying colored output
+- Fixed status bar duplicating background task indicator when PR status was shown
+- Windows: Fixed bash command execution failing for users with `.bashrc` files
+- Windows: Fixed console windows flashing when spawning child processes
+- VSCode: Fixed OAuth token expiration causing 401 errors after extended sessions
+
 ## 2.1.25
 
 - Fixed beta header validation error for gateway users on Bedrock and Vertex, ensuring `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` avoids the error

examples/settings/README.md

@@ -0,0 +1,31 @@
+# Settings Examples
+
+Example Claude Code settings files, primarily intended for organization-wide deployments. Use these are starting points — adjust them to fit your needs.
+
+These may be applied at any level of the [settings hierarchy](https://code.claude.com/docs/en/settings#settings-files), though certain properties only take effect if specified in enterprise settings (e.g. `strictKnownMarketplaces`, `allowManagedHooksOnly`, `allowManagedPermissionRulesOnly`).
+
+
+## Configuration Examples
+
+> [!WARNING]
+> These examples are community-maintained snippets which may be unsupported or incorrect. You are responsible for the correctness of your own settings configuration.
+
+| Setting | [`settings-lax.json`](./settings-lax.json) | [`settings-strict.json`](./settings-strict.json) | [`settings-bash-sandbox.json`](./settings-bash-sandbox.json) |
+|---------|:---:|:---:|:---:|
+| Disable `--dangerously-skip-permissions` | ✅ | ✅ | |
+| Block plugin marketplaces | ✅ | ✅ | |
+| Block user and project-defined permission `allow` / `ask` / `deny` | | ✅ | ✅ |
+| Block user and project-defined hooks | | ✅ | |
+| Deny web fetch and search tools | | ✅ | |
+| Bash tool requires approval | | ✅ | |
+| Bash tool must run inside of sandbox | | | ✅ |
+
+## Tips
+- Consider merging snippets of the above examples to reach your desired configuration
+- Settings files must be valid JSON
+- Before deploying configuration files to your organization, test them locally by applying to `managed-settings.json`, `settings.json` or `settings.local.json`
+- The `sandbox` property only applies to the `Bash` tool; it does not apply to other tools (like Read, Write, WebSearch, WebFetch, MCPs), hooks, or internal commands
+
+## Full Documentation
+
+See https://code.claude.com/docs/en/settings for complete documentation on all available managed settings.

examples/settings/settings-bash-sandbox.json

@@ -0,0 +1,18 @@
+{
+  "allowManagedPermissionRulesOnly": true,
+  "sandbox": {
+    "enabled": true,
+    "autoAllowBashIfSandboxed": false,
+    "allowUnsandboxedCommands": false,
+    "excludedCommands": [],
+    "network": {
+      "allowUnixSockets": [],
+      "allowAllUnixSockets": false,
+      "allowLocalBinding": false,
+      "allowedDomains": [],
+      "httpProxyPort": null,
+      "socksProxyPort": null
+    },
+    "enableWeakerNestedSandbox": false
+  }
+}

examples/settings/settings-lax.json

@@ -0,0 +1,6 @@
+{
+  "permissions": {
+    "disableBypassPermissionsMode": "disable"
+  },
+  "strictKnownMarketplaces": []
+}

examples/settings/settings-strict.json

@@ -0,0 +1,28 @@
+{
+  "permissions": {
+    "disableBypassPermissionsMode": "disable",
+    "ask": [
+      "Bash"
+    ],
+    "deny": [
+      "WebSearch",
+      "WebFetch"
+    ]
+  },
+  "allowManagedPermissionRulesOnly": true,
+  "allowManagedHooksOnly": true,
+  "strictKnownMarketplaces": [],
+  "sandbox": {
+    "autoAllowBashIfSandboxed": false,
+    "excludedCommands": [],
+    "network": {
+      "allowUnixSockets": [],
+      "allowAllUnixSockets": false,
+      "allowLocalBinding": false,
+      "allowedDomains": [],
+      "httpProxyPort": null,
+      "socksProxyPort": null
+    },
+    "enableWeakerNestedSandbox": false
+  }
+}

plugins/README.md

@@ -25,6 +25,7 @@ Learn more in the [official plugins documentation](https://docs.claude.com/en/do
 | [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 |
+| [slack-quote-formatter](./slack-quote-formatter/) | Enhances visual display of Slack forwarded and quoted messages with distinctive Unicode box formatting | **Hook:** UserPromptSubmit - Transforms `[Forwarded Message]` blocks into visually distinctive formatted boxes with clear boundaries and indentation |
 
 ## Installation
 

plugins/slack-quote-formatter/.claude-plugin/plugin.json

@@ -0,0 +1,18 @@
+{
+  "name": "slack-quote-formatter",
+  "version": "1.0.0",
+  "description": "Enhances visual display of Slack forwarded and quoted messages with distinctive formatting",
+  "author": {
+    "name": "Anthropic",
+    "email": "support@anthropic.com"
+  },
+  "license": "MIT",
+  "keywords": [
+    "slack",
+    "formatting",
+    "quotes",
+    "messages",
+    "visual"
+  ],
+  "hooks": "./hooks/hooks.json"
+}

plugins/slack-quote-formatter/README.md

@@ -0,0 +1,87 @@
+# Slack Quote Formatter
+
+Enhances the visual display of Slack forwarded and quoted messages with distinctive Unicode box formatting.
+
+## Overview
+
+When Claude Code receives messages from Slack that include forwarded messages, they typically appear as plain text:
+
+```
+[Forwarded Message]
+From: Felix Klock
+Message: I assume it would be a matter of reviewing the entries...
+```
+
+This plugin transforms these plain blocks into visually distinctive formatted quotes:
+
+```
+╔════════════════════════════════════════════════════════════════════╗
+║  FORWARDED MESSAGE                                                 ║
+╠════════════════════════════════════════════════════════════════════╣
+║  From: Felix Klock                                                 ║
+╟────────────────────────────────────────────────────────────────────╢
+║    I assume it would be a matter of reviewing the entries...       ║
+╚════════════════════════════════════════════════════════════════════╝
+```
+
+## Features
+
+- Unicode box drawing characters for clear visual boundaries
+- Distinct header section highlighting "FORWARDED MESSAGE"
+- Sender information prominently displayed
+- Message content indented for quote-like appearance
+- Automatic text wrapping for long messages
+- Handles multiple forwarded messages in a single prompt
+
+## Installation
+
+This plugin is included in the Claude Code plugins repository. To enable it:
+
+1. Add the plugin to your project's `.claude/settings.json`:
+   ```json
+   {
+     "plugins": [
+       "path/to/plugins/slack-quote-formatter"
+     ]
+   }
+   ```
+
+2. Or install via the Claude Code plugin command:
+   ```
+   /plugin add slack-quote-formatter
+   ```
+
+## How It Works
+
+The plugin registers a `UserPromptSubmit` hook that:
+
+1. Intercepts incoming prompts
+2. Detects `[Forwarded Message]` blocks in the Slack context
+3. Transforms them into formatted boxes with visual distinction
+4. Passes the transformed prompt to Claude
+
+## Configuration
+
+No configuration required. The plugin automatically activates when Slack forwarded messages are detected.
+
+## Plugin Structure
+
+```
+slack-quote-formatter/
+├── .claude-plugin/
+│   └── plugin.json          # Plugin metadata
+├── hooks/
+│   ├── hooks.json           # Hook configuration
+│   └── format_slack_quotes.py  # Transformation logic
+└── README.md
+```
+
+## Why Visual Distinction Matters
+
+When working with Slack context in Claude Code, quoted messages can easily blend into the surrounding text, making it harder to:
+
+- Identify what content is quoted vs. original
+- Understand the source of different pieces of information
+- Parse complex threads with multiple forwarded messages
+
+This plugin makes quoted content immediately recognizable, improving readability and reducing confusion.

plugins/slack-quote-formatter/hooks/format_slack_quotes.py

@@ -0,0 +1,185 @@
+#!/usr/bin/env python3
+"""
+Slack Quote Formatter - UserPromptSubmit Hook
+
+Transforms plain Slack forwarded/quoted messages into visually distinctive
+formatted blocks with Unicode box characters and better layout.
+
+Before:
+    [Forwarded Message]
+    From: John Doe
+    Message: Here is some text...
+
+After:
+    ╔═══════════════════════════════════════════════════════════╗
+    ║  FORWARDED MESSAGE                                        ║
+    ╠═══════════════════════════════════════════════════════════╣
+    ║  From: John Doe                                           ║
+    ╟───────────────────────────────────────────────────────────╢
+    ║    Here is some text...                                   ║
+    ╚═══════════════════════════════════════════════════════════╝
+"""
+
+import json
+import re
+import sys
+
+
+def format_forwarded_message(from_line: str, message_content: str) -> str:
+    """Format a single forwarded message with visual box styling."""
+
+    # Box drawing characters
+    TOP_LEFT = "╔"
+    TOP_RIGHT = "╗"
+    BOTTOM_LEFT = "╚"
+    BOTTOM_RIGHT = "╝"
+    HORIZONTAL = "═"
+    VERTICAL = "║"
+    LEFT_T = "╠"
+    RIGHT_T = "╣"
+    LEFT_LIGHT = "╟"
+    RIGHT_LIGHT = "╢"
+    LIGHT_HORIZONTAL = "─"
+
+    # Configuration
+    BOX_WIDTH = 70
+    INNER_WIDTH = BOX_WIDTH - 4  # Account for "║  " and "  ║"
+
+    def pad_line(text: str, width: int = INNER_WIDTH) -> str:
+        """Pad a line to fill the box width."""
+        if len(text) > width:
+            return text[:width]
+        return text + " " * (width - len(text))
+
+    def wrap_text(text: str, width: int) -> list:
+        """Wrap text to fit within the specified width."""
+        words = text.split()
+        lines = []
+        current_line = []
+        current_length = 0
+
+        for word in words:
+            word_len = len(word)
+            if current_length + word_len + (1 if current_line else 0) <= width:
+                current_line.append(word)
+                current_length += word_len + (1 if len(current_line) > 1 else 0)
+            else:
+                if current_line:
+                    lines.append(" ".join(current_line))
+                current_line = [word]
+                current_length = word_len
+
+        if current_line:
+            lines.append(" ".join(current_line))
+
+        return lines if lines else [""]
+
+    lines = []
+
+    # Top border with header
+    lines.append(f"{TOP_LEFT}{HORIZONTAL * (BOX_WIDTH - 2)}{TOP_RIGHT}")
+
+    # Header line
+    header = "FORWARDED MESSAGE"
+    lines.append(f"{VERTICAL}  {pad_line(header)}{VERTICAL}")
+
+    # Separator after header
+    lines.append(f"{LEFT_T}{HORIZONTAL * (BOX_WIDTH - 2)}{RIGHT_T}")
+
+    # From line
+    from_display = from_line.strip()
+    lines.append(f"{VERTICAL}  {pad_line(from_display)}{VERTICAL}")
+
+    # Light separator before message
+    lines.append(f"{LEFT_LIGHT}{LIGHT_HORIZONTAL * (BOX_WIDTH - 2)}{RIGHT_LIGHT}")
+
+    # Message content (indented and wrapped)
+    message_lines = message_content.strip().split("\n")
+    for msg_line in message_lines:
+        # Handle each line, wrapping if necessary
+        wrapped = wrap_text(msg_line, INNER_WIDTH - 2)  # Extra indent
+        for wrapped_line in wrapped:
+            indented = "  " + wrapped_line  # Add indent for quote appearance
+            lines.append(f"{VERTICAL}  {pad_line(indented)}{VERTICAL}")
+
+    # Bottom border
+    lines.append(f"{BOTTOM_LEFT}{HORIZONTAL * (BOX_WIDTH - 2)}{BOTTOM_RIGHT}")
+
+    return "\n".join(lines)
+
+
+def transform_slack_context(text: str) -> str:
+    """
+    Find and transform [Forwarded Message] blocks in the text.
+
+    Matches patterns like:
+        [Forwarded Message]
+        From: Name Here
+        Message: Content here that may span
+        multiple lines until we hit the next section
+    """
+
+    # Pattern to match forwarded message blocks
+    # This handles the common format from Slack context
+    pattern = r'\[Forwarded Message\]\s*\n\s*From:\s*([^\n]+)\s*\nMessage:\s*(.+?)(?=\n\s*\[|\n\[pnkfelix\]|\n<|\Z)'
+
+    def replace_match(match):
+        from_name = match.group(1).strip()
+        message = match.group(2).strip()
+
+        formatted = format_forwarded_message(f"From: {from_name}", message)
+        return f"\n{formatted}\n"
+
+    # Apply transformation
+    result = re.sub(pattern, replace_match, text, flags=re.DOTALL)
+
+    return result
+
+
+def main():
+    """Main entry point for the UserPromptSubmit hook."""
+    try:
+        # Read input from stdin
+        input_data = json.load(sys.stdin)
+
+        # Get the user prompt if available
+        user_prompt = input_data.get("user_prompt", "")
+
+        if not user_prompt:
+            # No prompt to transform, just pass through
+            print(json.dumps({}))
+            sys.exit(0)
+
+        # Check if there are forwarded messages to format
+        if "[Forwarded Message]" not in user_prompt:
+            # Nothing to transform
+            print(json.dumps({}))
+            sys.exit(0)
+
+        # Transform the prompt
+        transformed_prompt = transform_slack_context(user_prompt)
+
+        # If we made changes, return the transformed prompt
+        if transformed_prompt != user_prompt:
+            result = {
+                "transformedPrompt": transformed_prompt
+            }
+            print(json.dumps(result))
+        else:
+            print(json.dumps({}))
+
+    except json.JSONDecodeError:
+        # No valid JSON input, pass through
+        print(json.dumps({}))
+    except Exception as e:
+        # Log error but don't block
+        error_output = {
+            "systemMessage": f"[slack-quote-formatter] Warning: {str(e)}"
+        }
+        print(json.dumps(error_output))
+
+    sys.exit(0)
+
+
+if __name__ == "__main__":
+    main()

plugins/slack-quote-formatter/hooks/hooks.json

@@ -0,0 +1,14 @@
+{
+  "UserPromptSubmit": [
+    {
+      "matcher": ".*",
+      "hooks": [
+        {
+          "type": "command",
+          "command": "python3 ${CLAUDE_PLUGIN_ROOT}/hooks/format_slack_quotes.py",
+          "timeout": 5000
+        }
+      ]
+    }
+  ]
+}