fix(security): Resolve symlinks before checking deny rules (CVE-2025-59829)

This commit fixes a security vulnerability where deny rules could be
bypassed by creating symbolic links to restricted files.

Changes:
- Add symlink resolution in rule_engine.py _extract_field method
- Add symlink resolution in security_reminder_hook.py check_patterns
- Create new symlink_deny_hook.py for blocking symlinks to system paths
- Include Read tool in file event handlers for deny rule checking
- Update hooks.json to apply security hooks to Read tool

The vulnerability allowed attackers to bypass deny rules like
Read(/etc/passwd) by creating a symlink (e.g., ln -s /etc/passwd test.txt)
and then reading the symlink instead of the restricted file directly.

The fix uses os.path.realpath() to resolve all symlinks to their canonical
paths before checking against deny patterns, ensuring that deny rules are
enforced regardless of whether the path is accessed directly or via symlink.

.claude/commands/dedupe.md

@@ -1,5 +1,5 @@
 ---
-allowed-tools: Bash(gh issue view:*), Bash(gh search:*), Bash(gh issue list:*), Bash(gh api:*), Bash(gh issue comment:*)
+allowed-tools: Bash(gh issue view:*), Bash(gh search:*), Bash(gh issue list:*), Bash(./scripts/comment-on-duplicates.sh:*)
 description: Find duplicate GitHub issues
 ---
 
@@ -11,28 +11,13 @@ To do this, follow these steps precisely:
 2. Use an agent to view a Github issue, and ask the agent to return a summary of the issue
 3. Then, launch 5 parallel agents to search Github for duplicates of this issue, using diverse keywords and search approaches, using the summary from #1
 4. Next, feed the results from #1 and #2 into another agent, so that it can filter out false positives, that are likely not actually duplicates of the original issue. If there are no duplicates remaining, do not proceed.
-5. Finally, comment back on the issue with a list of up to three duplicate issues (or zero, if there are no likely duplicates)
+5. Finally, use the comment script to post duplicates:
+   ```
+   ./scripts/comment-on-duplicates.sh --base-issue <issue-number> --potential-duplicates <dup1> <dup2> <dup3>
+   ```
 
 Notes (be sure to tell this to your agents, too):
 
 - Use `gh` to interact with Github, rather than web fetch
-- Do not use other tools, beyond `gh` (eg. don't use other MCP servers, file edit, etc.)
+- Do not use other tools, beyond `gh` and the comment script (eg. don't use other MCP servers, file edit, etc.)
 - Make a todo list first
-- For your comment, follow the following format precisely (assuming for this example that you found 3 suspected duplicates):
-
----
-
-Found 3 possible duplicate issues:
-
-1. <link to issue>
-2. <link to issue>
-3. <link to issue>
-
-This issue will be automatically closed as a duplicate in 3 days.
-
-- If your issue is a duplicate, please close it and 👍 the existing issue instead
-- To prevent auto-closure, add a comment or 👎 this comment
-
-🤖 Generated with [Claude Code](https://claude.ai/code)
-
----

CHANGELOG.md

@@ -1,5 +1,141 @@
 # Changelog
 
+## 2.1.0
+
+- Added automatic skill hot-reload - skills created or modified in `~/.claude/skills` or `.claude/skills` are now immediately available without restarting the session
+- Added support for running skills and slash commands in a forked sub-agent context using `context: fork` in skill frontmatter
+- Added support for `agent` field in skills to specify agent type for execution
+- Added `language` setting to configure Claude's response language (e.g., language: "japanese")
+- Changed Shift+Enter to work out of the box in iTerm2, WezTerm, Ghostty, and Kitty without modifying terminal configs
+- Added `respectGitignore` support in `settings.json` for per-project control over @-mention file picker behavior
+- Added `IS_DEMO` environment variable to hide email and organization from the UI, useful for streaming or recording sessions
+- Fixed security issue where sensitive data (OAuth tokens, API keys, passwords) could be exposed in debug logs
+- Fixed files and skills not being properly discovered when resuming sessions with `-c` or `--resume`
+- Fixed pasted content being lost when replaying prompts from history using up arrow or Ctrl+R search
+- Fixed Esc key with queued prompts to only move them to input without canceling the running task
+- Reduced permission prompts for complex bash commands
+- Fixed command search to prioritize exact and prefix matches on command names over fuzzy matches in descriptions
+- Fixed PreToolUse hooks to allow `updatedInput` when returning `ask` permission decision, enabling hooks to act as middleware while still requesting user consent
+- Fixed plugin path resolution for file-based marketplace sources
+- Fixed LSP tool being incorrectly enabled when no LSP servers were configured
+- Fixed background tasks failing with "git repository not found" error for repositories with dots in their names
+- Fixed Claude in Chrome support for WSL environments
+- Fixed Windows native installer silently failing when executable creation fails
+- Improved CLI help output to display options and subcommands in alphabetical order for easier navigation
+- Added wildcard pattern matching for Bash tool permissions using `*` at any position in rules (e.g., `Bash(npm *)`, `Bash(* install)`, `Bash(git * main)`)
+- Added unified Ctrl+B backgrounding for both bash commands and agents - pressing Ctrl+B now backgrounds all running foreground tasks simultaneously
+- Added support for MCP `list_changed` notifications, allowing MCP servers to dynamically update their available tools, prompts, and resources without requiring reconnection
+- Added `/teleport` and `/remote-env` slash commands for claude.ai subscribers, allowing them to resume and configure remote sessions
+- Added support for disabling specific agents using `Task(AgentName)` syntax in settings.json permissions or the `--disallowedTools` CLI flag
+- Added hooks support to agent frontmatter, allowing agents to define PreToolUse, PostToolUse, and Stop hooks scoped to the agent's lifecycle
+- Added hooks support for skill and slash command frontmatter
+- Added new Vim motions: `;` and `,` to repeat f/F/t/T motions, `y` operator for yank with `yy`/`Y`, `p`/`P` for paste, text objects (`iw`, `aw`, `iW`, `aW`, `i"`, `a"`, `i'`, `a'`, `i(`, `a(`, `i[`, `a[`, `i{`, `a{`), `>>` and `<<` for indent/dedent, and `J` to join lines
+- Added `/plan` command shortcut to enable plan mode directly from the prompt
+- Added slash command autocomplete support when `/` appears anywhere in input, not just at the beginning
+- Added `--tools` flag support in interactive mode to restrict which built-in tools Claude can use during interactive sessions
+- Added `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS` environment variable to override the default file read token limit
+- Added support for `once: true` config for hooks
+- Added support for YAML-style lists in frontmatter `allowed-tools` field for cleaner skill declarations
+- Added support for prompt and agent hook types from plugins (previously only command hooks were supported)
+- Added Cmd+V support for image paste in iTerm2 (maps to Ctrl+V)
+- Added left/right arrow key navigation for cycling through tabs in dialogs
+- Added real-time thinking block display in Ctrl+O transcript mode
+- Added filepath to full output in background bash task details dialog
+- Added Skills as a separate category in the context visualization
+- Fixed OAuth token refresh not triggering when server reports token expired but local expiration check disagrees
+- Fixed session persistence getting stuck after transient server errors by recovering from 409 conflicts when the entry was actually stored
+- Fixed session resume failures caused by orphaned tool results during concurrent tool execution
+- Fixed a race condition where stale OAuth tokens could be read from the keychain cache during concurrent token refresh attempts
+- Fixed AWS Bedrock subagents not inheriting EU/APAC cross-region inference model configuration, causing 403 errors when IAM permissions are scoped to specific regions
+- Fixed API context overflow when background tasks produce large output by truncating to 30K chars with file path reference
+- Fixed a hang when reading FIFO files by skipping symlink resolution for special file types
+- Fixed terminal keyboard mode not being reset on exit in Ghostty, iTerm2, Kitty, and WezTerm
+- Fixed Alt+B and Alt+F (word navigation) not working in iTerm2, Ghostty, Kitty, and WezTerm
+- Fixed `${CLAUDE_PLUGIN_ROOT}` not being substituted in plugin `allowed-tools` frontmatter, which caused tools to incorrectly require approval
+- Fixed files created by the Write tool using hardcoded 0o600 permissions instead of respecting the system umask
+- Fixed commands with `$()` command substitution failing with parse errors
+- Fixed multi-line bash commands with backslash continuations being incorrectly split and flagged for permissions
+- Fixed bash command prefix extraction to correctly identify subcommands after global options (e.g., `git -C /path log` now correctly matches `Bash(git log:*)` rules)
+- Fixed slash commands passed as CLI arguments (e.g., `claude /context`) not being executed properly
+- Fixed pressing Enter after Tab-completing a slash command selecting a different command instead of submitting the completed one
+- Fixed slash command argument hint flickering and inconsistent display when typing commands with arguments
+- Fixed Claude sometimes redundantly invoking the Skill tool when running slash commands directly
+- Fixed skill token estimates in `/context` to accurately reflect frontmatter-only loading
+- Fixed subagents sometimes not inheriting the parent's model by default
+- Fixed model picker showing incorrect selection for Bedrock/Vertex users using `--model haiku`
+- Fixed duplicate Bash commands appearing in permission request option labels
+- Fixed noisy output when background tasks complete - now shows clean completion message instead of raw output
+- Fixed background task completion notifications to appear proactively with bullet point
+- Fixed forked slash commands showing "AbortError" instead of "Interrupted" message when cancelled
+- Fixed cursor disappearing after dismissing permission dialogs
+- Fixed `/hooks` menu selecting wrong hook type when scrolling to a different option
+- Fixed images in queued prompts showing as "[object Object]" when pressing Esc to cancel
+- Fixed images being silently dropped when queueing messages while backgrounding a task
+- Fixed large pasted images failing with "Image was too large" error
+- Fixed extra blank lines in multiline prompts containing CJK characters (Japanese, Chinese, Korean)
+- Fixed ultrathink keyword highlighting being applied to wrong characters when user prompt text wraps to multiple lines
+- Fixed collapsed "Reading X files…" indicator incorrectly switching to past tense when thinking blocks appear mid-stream
+- Fixed Bash read commands (like `ls` and `cat`) not being counted in collapsed read/search groups, causing groups to incorrectly show "Read 0 files"
+- Fixed spinner token counter to properly accumulate tokens from subagents during execution
+- Fixed memory leak in git diff parsing where sliced strings retained large parent strings
+- Fixed race condition where LSP tool could return "no server available" during startup
+- Fixed feedback submission hanging indefinitely when network requests timeout
+- Fixed search mode in plugin discovery and log selector views exiting when pressing up arrow
+- Fixed hook success message showing trailing colon when hook has no output
+- Multiple optimizations to improve startup performance
+- Improved terminal rendering performance when using native installer or Bun, especially for text with emoji, ANSI codes, and Unicode characters
+- Improved performance when reading Jupyter notebooks with many cells
+- Improved reliability for piped input like `cat refactor.md | claude`
+- Improved reliability for AskQuestion tool
+- Improved sed in-place edit commands to render as file edits with diff preview
+- Improved Claude to automatically continue when response is cut off due to output token limit, instead of showing an error message
+- Improved compaction reliability
+- Improved subagents (Task tool) to continue working after permission denial, allowing them to try alternative approaches
+- Improved skills to show progress while executing, displaying tool uses as they happen
+- Improved skills from `/skills/` directories to be visible in the slash command menu by default (opt-out with `user-invocable: false` in frontmatter)
+- Improved skill suggestions to prioritize recently and frequently used skills
+- Improved spinner feedback when waiting for the first response token
+- Improved token count display in spinner to include tokens from background agents
+- Improved incremental output for async agents to give the main thread more control and visibility
+- Improved permission prompt UX with Tab hint moved to footer, cleaner Yes/No input labels with contextual placeholders
+- Improved the Claude in Chrome notification with shortened help text and persistent display until dismissed
+- Improved macOS screenshot paste reliability with TIFF format support
+- Improved `/stats` output
+- Updated Atlassian MCP integration to use a more reliable default configuration (streamable HTTP)
+- Changed "Interrupted" message color from red to grey for a less alarming appearance
+- Removed permission prompt when entering plan mode - users can now enter plan mode without approval
+- Removed underline styling from image reference links
+- [SDK] Changed minimum zod peer dependency to ^4.0.0
+- [VSCode] Added currently selected model name to the context menu
+- [VSCode] Added descriptive labels on auto-accept permission button (e.g., "Yes, allow npm for this project" instead of "Yes, and don't ask again")
+- [VSCode] Fixed paragraph breaks not rendering in markdown content
+- [VSCode] Fixed scrolling in the extension inadvertently scrolling the parent iframe
+- [Windows] Fixed issue with improper rendering
+
+## 2.0.76
+
+- Fixed issue with macOS code-sign warning when using Claude in Chrome integration
+
+## 2.0.75
+
+- Minor bugfixes
+
+## 2.0.74
+
+- Added LSP (Language Server Protocol) tool for code intelligence features like go-to-definition, find references, and hover documentation
+- Added `/terminal-setup` support for Kitty, Alacritty, Zed, and Warp terminals
+- Added ctrl+t shortcut in `/theme` to toggle syntax highlighting on/off
+- Added syntax highlighting info to theme picker
+- Added guidance for macOS users when Alt shortcuts fail due to terminal configuration
+- Fixed skill `allowed-tools` not being applied to tools invoked by the skill
+- Fixed Opus 4.5 tip incorrectly showing when user was already using Opus
+- Fixed a potential crash when syntax highlighting isn't initialized correctly
+- Fixed visual bug in `/plugins discover` where list selection indicator showed while search box was focused
+- Fixed macOS keyboard shortcuts to display 'opt' instead of 'alt'
+- Improved `/context` command visualization with grouped skills and agents by source, slash commands, and sorted token count
+- [Windows] Fixed issue with improper rendering
+- [VSCode] Added gift tag pictogram for year-end promotion message
+
 ## 2.0.73
 
 - Added clickable `[Image #N]` links that open attached images in the default viewer

README.md

@@ -6,7 +6,7 @@
 
 Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows -- all through natural language commands. Use it in your terminal, IDE, or tag @claude on Github.
 
-**Learn more in the [official documentation](https://docs.anthropic.com/en/docs/claude-code/overview)**.
+**Learn more in the [official documentation](https://code.claude.com/docs/en/overview)**.
 
 <img src="./demo.gif" />
 
@@ -56,7 +56,7 @@ When you use Claude Code, we collect feedback, which includes usage data (such a
 
 ### How we use your data
 
-See our [data usage policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
+See our [data usage policies](https://code.claude.com/docs/en/data-usage).
 
 ### Privacy safeguards
 

hook-selection-bug-issue.md

@@ -1,64 +0,0 @@
-# Bug Report: /hooks command always selects PreToolUse on first attempt
-
-## Summary
-
-When using the `/hooks` command to create a new hook, the hook type selector always selects `PreToolUse` on the first attempt, regardless of which option the user scrolls to and selects with Enter. The selection works correctly on subsequent attempts after pressing Escape.
-
-## Steps to Reproduce
-
-1. Open Claude Code
-2. Type `/hooks` to open the hooks management interface
-3. Navigate to create a new hook
-4. When the hook type selector appears (showing PreToolUse, PostToolUse, Stop, UserPromptSubmit, etc.), scroll down using arrow keys to select a different hook type (e.g., `PostToolUse`)
-5. Press Enter to confirm selection
-6. **Bug:** `PreToolUse` is selected instead of the highlighted option
-
-## Workaround
-
-1. Press Escape to cancel the selection
-2. Re-enter the hook type selector
-3. Scroll to desired hook type
-4. Press Enter
-5. **Result:** Correct hook type is now selected
-
-## Expected Behavior
-
-The hook type selector should select the option that is visually highlighted when the user presses Enter, on both first and subsequent attempts.
-
-## Root Cause Analysis
-
-This appears to be a **state synchronization issue** where:
-
-1. On first render of the hook type selector, the internal selected index is initialized to `0` (PreToolUse is the first item)
-2. The visual highlight updates correctly when scrolling with arrow keys (the user sees a different item highlighted)
-3. However, when pressing Enter, the handler reads from the internal state (which may still be `0`) rather than the current highlighted position
-4. After pressing Escape and re-opening the selector, the state is properly synchronized
-
-### Potential Code Areas
-
-Based on similar issues and the CHANGELOG history, the fix likely involves one of these patterns:
-
-1. **Initial state not synced**: The selection state may need to be initialized differently, or there's a race condition between render and state initialization
-
-2. **Event handler reading stale state**: The Enter key handler might be using a captured/stale reference to the selection index rather than the current value
-
-3. **Scroll handler not updating state**: The arrow key navigation might only be updating the visual highlight without updating the underlying state that Enter reads from
-
-### Similar Fixed Issues
-
-- **CHANGELOG v2.0.35**: "Fixed menu navigation getting stuck on items with empty string or other falsy values (e.g., in the `/hooks` menu)"
-- **CHANGELOG v0.2.69**: "Fixed UI glitches with improved Select component behavior"
-- **Issue #6674**: Hook Navigation Infinite Loop on Duplicate Entries (related Select component issue)
-
-## Environment
-
-- Reported on: Multiple environments
-- Claude Code Version: Current latest
-
-## Slack Thread Reference
-
-https://anthropic.slack.com/archives/C07VBSHV7EV/p1766159670734839?thread_ts=1766158844.979909&cid=C07VBSHV7EV
-
-## Labels
-
-`bug`, `hooks`, `ui`, `select-component`

plugins/hookify/core/rule_engine.py

@@ -141,6 +141,39 @@ class RuleEngine:
         patterns = matcher.split('|')
         return tool_name in patterns
 
+    def _resolve_symlink_path(self, file_path: str) -> str:
+        """Resolve symlinks in file path to get canonical path.
+
+        Security fix for CVE-2025-59829: Deny rules could be bypassed by creating
+        a symlink to a restricted file. This method resolves the symlink to its
+        target path so that deny rules are checked against the actual file.
+
+        Args:
+            file_path: The file path that may contain symlinks
+
+        Returns:
+            The canonical path with symlinks resolved, or original path if
+            resolution fails (e.g., file doesn't exist yet)
+        """
+        import os
+
+        if not file_path:
+            return file_path
+
+        try:
+            # Expand user home directory first
+            expanded_path = os.path.expanduser(file_path)
+
+            # Use realpath to resolve all symlinks and get canonical path
+            # This handles nested symlinks and relative path components
+            resolved = os.path.realpath(expanded_path)
+
+            return resolved
+        except (OSError, ValueError):
+            # If resolution fails (e.g., permission denied, invalid path),
+            # return the original path to avoid blocking legitimate operations
+            return file_path
+
     def _check_condition(self, condition: Condition, tool_name: str,
                         tool_input: Dict[str, Any], input_data: Dict[str, Any] = None) -> bool:
         """Check if a single condition matches.
@@ -196,6 +229,10 @@ class RuleEngine:
         if field in tool_input:
             value = tool_input[field]
             if isinstance(value, str):
+                # Security fix: resolve symlinks for file_path fields to prevent bypass
+                # CVE-2025-59829: Deny rules could be bypassed via symlinks
+                if field == 'file_path':
+                    value = self._resolve_symlink_path(value)
                 return value
             return str(value)
 
@@ -241,11 +278,18 @@ class RuleEngine:
             elif field == 'old_text' or field == 'old_string':
                 return tool_input.get('old_string', '')
             elif field == 'file_path':
-                return tool_input.get('file_path', '')
+                # Security fix: resolve symlinks to prevent deny rule bypass
+                return self._resolve_symlink_path(tool_input.get('file_path', ''))
+
+        elif tool_name == 'Read':
+            # Security fix for CVE-2025-59829: Read tool symlink bypass
+            if field == 'file_path':
+                return self._resolve_symlink_path(tool_input.get('file_path', ''))
 
         elif tool_name == 'MultiEdit':
             if field == 'file_path':
-                return tool_input.get('file_path', '')
+                # Security fix: resolve symlinks to prevent deny rule bypass
+                return self._resolve_symlink_path(tool_input.get('file_path', ''))
             elif field in ['new_text', 'content']:
                 # Concatenate all edits
                 edits = tool_input.get('edits', [])

plugins/hookify/hooks/pretooluse.py

@@ -45,7 +45,9 @@ def main():
         event = None
         if tool_name == 'Bash':
             event = 'bash'
-        elif tool_name in ['Edit', 'Write', 'MultiEdit']:
+        elif tool_name in ['Edit', 'Write', 'MultiEdit', 'Read']:
+            # Include Read tool in file events to check symlink bypass
+            # Security fix for CVE-2025-59829
             event = 'file'
 
         # Load rules

plugins/ralph-wiggum/commands/cancel-ralph.md

@@ -1,26 +1,18 @@
 ---
 description: "Cancel active Ralph Wiggum loop"
-allowed-tools: ["Bash"]
+allowed-tools: ["Bash(test -f .claude/ralph-loop.local.md:*)", "Bash(rm .claude/ralph-loop.local.md)", "Read(.claude/ralph-loop.local.md)"]
 hide-from-slash-command-tool: "true"
 ---
 
 # Cancel Ralph
 
-```!
-if [[ -f .claude/ralph-loop.local.md ]]; then
-  ITERATION=$(grep '^iteration:' .claude/ralph-loop.local.md | sed 's/iteration: *//')
-  echo "FOUND_LOOP=true"
-  echo "ITERATION=$ITERATION"
-else
-  echo "FOUND_LOOP=false"
-fi
-```
+To cancel the Ralph loop:
 
-Check the output above:
+1. Check if `.claude/ralph-loop.local.md` exists using Bash: `test -f .claude/ralph-loop.local.md && echo "EXISTS" || echo "NOT_FOUND"`
 
-1. **If FOUND_LOOP=false**:
-   - Say "No active Ralph loop found."
+2. **If NOT_FOUND**: Say "No active Ralph loop found."
 
-2. **If FOUND_LOOP=true**:
-   - Use Bash: `rm .claude/ralph-loop.local.md`
-   - Report: "Cancelled Ralph loop (was at iteration N)" where N is the ITERATION value from above.
+3. **If EXISTS**:
+   - Read `.claude/ralph-loop.local.md` to get the current iteration number from the `iteration:` field
+   - Remove the file using Bash: `rm .claude/ralph-loop.local.md`
+   - Report: "Cancelled Ralph loop (was at iteration N)" where N is the iteration value

plugins/ralph-wiggum/commands/ralph-loop.md

@@ -1,7 +1,7 @@
 ---
 description: "Start Ralph Wiggum loop in current session"
 argument-hint: "PROMPT [--max-iterations N] [--completion-promise TEXT]"
-allowed-tools: ["Bash(${CLAUDE_PLUGIN_ROOT}/scripts/setup-ralph-loop.sh)"]
+allowed-tools: ["Bash(${CLAUDE_PLUGIN_ROOT}/scripts/setup-ralph-loop.sh:*)"]
 hide-from-slash-command-tool: "true"
 ---
 
@@ -11,36 +11,6 @@ Execute the setup script to initialize the Ralph loop:
 
 ```!
 "${CLAUDE_PLUGIN_ROOT}/scripts/setup-ralph-loop.sh" $ARGUMENTS
-
-# Extract and display completion promise if set
-if [ -f .claude/ralph-loop.local.md ]; then
-  PROMISE=$(grep '^completion_promise:' .claude/ralph-loop.local.md | sed 's/completion_promise: *//' | sed 's/^"\(.*\)"$/\1/')
-  if [ -n "$PROMISE" ] && [ "$PROMISE" != "null" ]; then
-    echo ""
-    echo "═══════════════════════════════════════════════════════════"
-    echo "CRITICAL - Ralph Loop Completion Promise"
-    echo "═══════════════════════════════════════════════════════════"
-    echo ""
-    echo "To complete this loop, output this EXACT text:"
-    echo "  <promise>$PROMISE</promise>"
-    echo ""
-    echo "STRICT REQUIREMENTS (DO NOT VIOLATE):"
-    echo "  ✓ Use <promise> XML tags EXACTLY as shown above"
-    echo "  ✓ The statement MUST be completely and unequivocally TRUE"
-    echo "  ✓ Do NOT output false statements to exit the loop"
-    echo "  ✓ Do NOT lie even if you think you should exit"
-    echo ""
-    echo "IMPORTANT - Do not circumvent the loop:"
-    echo "  Even if you believe you're stuck, the task is impossible,"
-    echo "  or you've been running too long - you MUST NOT output a"
-    echo "  false promise statement. The loop is designed to continue"
-    echo "  until the promise is GENUINELY TRUE. Trust the process."
-    echo ""
-    echo "  If the loop should stop, the promise statement will become"
-    echo "  true naturally. Do not force it by lying."
-    echo "═══════════════════════════════════════════════════════════"
-  fi
-fi
 ```
 
 Please work on the task. When you try to exit, the Ralph loop will feed the SAME PROMPT back to you for the next iteration. You'll see your previous work in files and git history, allowing you to iterate and improve.

plugins/ralph-wiggum/scripts/setup-ralph-loop.sh

@@ -174,3 +174,30 @@ if [[ -n "$PROMPT" ]]; then
   echo ""
   echo "$PROMPT"
 fi
+
+# Display completion promise requirements if set
+if [[ "$COMPLETION_PROMISE" != "null" ]]; then
+  echo ""
+  echo "═══════════════════════════════════════════════════════════"
+  echo "CRITICAL - Ralph Loop Completion Promise"
+  echo "═══════════════════════════════════════════════════════════"
+  echo ""
+  echo "To complete this loop, output this EXACT text:"
+  echo "  <promise>$COMPLETION_PROMISE</promise>"
+  echo ""
+  echo "STRICT REQUIREMENTS (DO NOT VIOLATE):"
+  echo "  ✓ Use <promise> XML tags EXACTLY as shown above"
+  echo "  ✓ The statement MUST be completely and unequivocally TRUE"
+  echo "  ✓ Do NOT output false statements to exit the loop"
+  echo "  ✓ Do NOT lie even if you think you should exit"
+  echo ""
+  echo "IMPORTANT - Do not circumvent the loop:"
+  echo "  Even if you believe you're stuck, the task is impossible,"
+  echo "  or you've been running too long - you MUST NOT output a"
+  echo "  false promise statement. The loop is designed to continue"
+  echo "  until the promise is GENUINELY TRUE. Trust the process."
+  echo ""
+  echo "  If the loop should stop, the promise statement will become"
+  echo "  true naturally. Do not force it by lying."
+  echo "═══════════════════════════════════════════════════════════"
+fi

plugins/security-guidance/hooks/hooks.json

@@ -1,7 +1,16 @@
 {
-  "description": "Security reminder hook that warns about potential security issues when editing files",
+  "description": "Security hooks for file access validation and security pattern warnings",
   "hooks": {
     "PreToolUse": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python3 ${CLAUDE_PLUGIN_ROOT}/hooks/symlink_deny_hook.py"
+          }
+        ],
+        "matcher": "Edit|Write|MultiEdit|Read"
+      },
       {
         "hooks": [
           {
@@ -9,7 +18,7 @@
             "command": "python3 ${CLAUDE_PLUGIN_ROOT}/hooks/security_reminder_hook.py"
           }
         ],
-        "matcher": "Edit|Write|MultiEdit"
+        "matcher": "Edit|Write|MultiEdit|Read"
       }
     ]
   }

plugins/security-guidance/hooks/security_reminder_hook.py

@@ -180,10 +180,46 @@ def save_state(session_id, shown_warnings):
         pass  # Fail silently if we can't save state
 
 
+def resolve_symlink_path(file_path):
+    """Resolve symlinks in file path to get canonical path.
+
+    Security fix for CVE-2025-59829: Deny rules could be bypassed by creating
+    a symlink to a restricted file. This method resolves the symlink to its
+    target path so that security patterns are checked against the actual file.
+
+    Args:
+        file_path: The file path that may contain symlinks
+
+    Returns:
+        The canonical path with symlinks resolved, or original path if
+        resolution fails (e.g., file doesn't exist yet)
+    """
+    if not file_path:
+        return file_path
+
+    try:
+        # Expand user home directory first
+        expanded_path = os.path.expanduser(file_path)
+
+        # Use realpath to resolve all symlinks and get canonical path
+        # This handles nested symlinks and relative path components
+        resolved = os.path.realpath(expanded_path)
+
+        return resolved
+    except (OSError, ValueError):
+        # If resolution fails (e.g., permission denied, invalid path),
+        # return the original path to avoid blocking legitimate operations
+        return file_path
+
+
 def check_patterns(file_path, content):
     """Check if file path or content matches any security patterns."""
+    # Security fix: resolve symlinks before checking patterns
+    # CVE-2025-59829: Security patterns could be bypassed via symlinks
+    resolved_path = resolve_symlink_path(file_path)
+
     # Normalize path by removing leading slashes
-    normalized_path = file_path.lstrip("/")
+    normalized_path = resolved_path.lstrip("/")
 
     for pattern in SECURITY_PATTERNS:
         # Check path-based patterns
@@ -241,7 +277,7 @@ def main():
     tool_input = input_data.get("tool_input", {})
 
     # Check if this is a relevant tool
-    if tool_name not in ["Edit", "Write", "MultiEdit"]:
+    if tool_name not in ["Edit", "Write", "MultiEdit", "Read"]:
         sys.exit(0)  # Allow non-file tools to proceed
 
     # Extract file path from tool_input

plugins/security-guidance/hooks/symlink_deny_hook.py

@@ -0,0 +1,137 @@
+#!/usr/bin/env python3
+"""
+Symlink Deny Hook for Claude Code
+Security fix for CVE-2025-59829: Deny rules could be bypassed via symlinks.
+
+This hook resolves symlinks before checking file paths against deny patterns,
+preventing attackers from using symlinks to access restricted files.
+"""
+
+import json
+import os
+import re
+import sys
+from fnmatch import fnmatch
+
+
+# System directories that should be blocked by default
+# These match common deny rule patterns
+BLOCKED_PATHS = [
+    "/etc/**",
+    "/etc/passwd",
+    "/etc/shadow",
+    "/etc/sudoers",
+    "/etc/ssh/**",
+    "/etc/ssl/**",
+    "/root/**",
+    "/var/log/**",
+    "/proc/**",
+    "/sys/**",
+    "/boot/**",
+]
+
+
+def resolve_symlink_path(file_path: str) -> str:
+    """Resolve symlinks in file path to get canonical path.
+
+    Args:
+        file_path: The file path that may contain symlinks
+
+    Returns:
+        The canonical path with symlinks resolved, or original path if
+        resolution fails (e.g., file doesn't exist)
+    """
+    if not file_path:
+        return file_path
+
+    try:
+        # Expand user home directory first
+        expanded_path = os.path.expanduser(file_path)
+
+        # Use realpath to resolve all symlinks and get canonical path
+        resolved = os.path.realpath(expanded_path)
+
+        return resolved
+    except (OSError, ValueError):
+        return file_path
+
+
+def is_path_blocked(resolved_path: str, original_path: str) -> tuple:
+    """Check if the resolved path matches any blocked patterns.
+
+    Only blocks if:
+    1. The path was a symlink (resolved != original)
+    2. The resolved path matches a blocked pattern
+
+    Args:
+        resolved_path: The canonical path after symlink resolution
+        original_path: The original path before resolution
+
+    Returns:
+        Tuple of (is_blocked: bool, reason: str)
+    """
+    # Only apply symlink protection if path was actually a symlink
+    original_real = os.path.realpath(os.path.expanduser(original_path))
+    if original_real == resolved_path:
+        # Check if original was a symlink
+        expanded_original = os.path.expanduser(original_path)
+        if not os.path.islink(expanded_original):
+            # Not a symlink, allow normal deny rule checking to handle this
+            return False, ""
+
+    # Check if resolved path matches any blocked patterns
+    for pattern in BLOCKED_PATHS:
+        if pattern.endswith("/**"):
+            # Directory wildcard pattern
+            base_dir = pattern[:-3]
+            if resolved_path.startswith(base_dir + "/") or resolved_path == base_dir:
+                return True, f"Symlink bypass blocked: '{original_path}' resolves to '{resolved_path}' which matches blocked pattern '{pattern}'"
+        elif fnmatch(resolved_path, pattern):
+            return True, f"Symlink bypass blocked: '{original_path}' resolves to '{resolved_path}' which matches blocked pattern '{pattern}'"
+
+    return False, ""
+
+
+def main():
+    """Main hook function."""
+    try:
+        input_data = json.load(sys.stdin)
+    except json.JSONDecodeError:
+        sys.exit(0)  # Allow on parse error
+
+    tool_name = input_data.get("tool_name", "")
+    tool_input = input_data.get("tool_input", {})
+
+    # Only check file-related tools
+    if tool_name not in ["Read", "Edit", "Write", "MultiEdit"]:
+        sys.exit(0)
+
+    # Extract file path
+    file_path = tool_input.get("file_path", "")
+    if not file_path:
+        sys.exit(0)
+
+    # Resolve symlinks
+    resolved_path = resolve_symlink_path(file_path)
+
+    # Check if blocked
+    is_blocked, reason = is_path_blocked(resolved_path, file_path)
+
+    if is_blocked:
+        # Output denial response
+        response = {
+            "hookSpecificOutput": {
+                "hookEventName": "PreToolUse",
+                "permissionDecision": "deny"
+            },
+            "systemMessage": f"Security: {reason}"
+        }
+        print(json.dumps(response))
+        sys.exit(0)
+
+    # Allow the operation
+    sys.exit(0)
+
+
+if __name__ == "__main__":
+    main()

scripts/comment-on-duplicates.sh

@@ -0,0 +1,100 @@
+#!/usr/bin/env bash
+#
+# Comments on a GitHub issue with a list of potential duplicates.
+# Usage: ./comment-on-duplicates.sh --base-issue 123 --potential-duplicates 456 789 101
+#
+
+set -euo pipefail
+
+REPO="anthropics/claude-code"
+BASE_ISSUE=""
+DUPLICATES=()
+
+# Parse arguments
+while [[ $# -gt 0 ]]; do
+  case $1 in
+    --base-issue)
+      BASE_ISSUE="$2"
+      shift 2
+      ;;
+    --potential-duplicates)
+      shift
+      while [[ $# -gt 0 && ! "$1" =~ ^-- ]]; do
+        DUPLICATES+=("$1")
+        shift
+      done
+      ;;
+    *)
+      echo "Unknown option: $1" >&2
+      exit 1
+      ;;
+  esac
+done
+
+# Validate base issue
+if [[ -z "$BASE_ISSUE" ]]; then
+  echo "Error: --base-issue is required" >&2
+  exit 1
+fi
+
+if ! [[ "$BASE_ISSUE" =~ ^[0-9]+$ ]]; then
+  echo "Error: --base-issue must be a number, got: $BASE_ISSUE" >&2
+  exit 1
+fi
+
+# Validate duplicates
+if [[ ${#DUPLICATES[@]} -eq 0 ]]; then
+  echo "Error: --potential-duplicates requires at least one issue number" >&2
+  exit 1
+fi
+
+if [[ ${#DUPLICATES[@]} -gt 3 ]]; then
+  echo "Error: --potential-duplicates accepts at most 3 issues" >&2
+  exit 1
+fi
+
+for dup in "${DUPLICATES[@]}"; do
+  if ! [[ "$dup" =~ ^[0-9]+$ ]]; then
+    echo "Error: duplicate issue must be a number, got: $dup" >&2
+    exit 1
+  fi
+done
+
+# Validate that base issue exists
+if ! gh issue view "$BASE_ISSUE" --repo "$REPO" &>/dev/null; then
+  echo "Error: issue #$BASE_ISSUE does not exist in $REPO" >&2
+  exit 1
+fi
+
+# Validate that all duplicate issues exist
+for dup in "${DUPLICATES[@]}"; do
+  if ! gh issue view "$dup" --repo "$REPO" &>/dev/null; then
+    echo "Error: issue #$dup does not exist in $REPO" >&2
+    exit 1
+  fi
+done
+
+# Build comment body
+COUNT=${#DUPLICATES[@]}
+if [[ $COUNT -eq 1 ]]; then
+  HEADER="Found 1 possible duplicate issue:"
+else
+  HEADER="Found $COUNT possible duplicate issues:"
+fi
+
+BODY="$HEADER"$'\n\n'
+INDEX=1
+for dup in "${DUPLICATES[@]}"; do
+  BODY+="$INDEX. https://github.com/$REPO/issues/$dup"$'\n'
+  ((INDEX++))
+done
+
+BODY+=$'\n'"This issue will be automatically closed as a duplicate in 3 days."$'\n\n'
+BODY+="- If your issue is a duplicate, please close it and 👍 the existing issue instead"$'\n'
+BODY+="- To prevent auto-closure, add a comment or 👎 this comment"$'\n\n'
+BODY+="🤖 Generated with [Claude Code](https://claude.ai/code)"
+
+# Post the comment
+gh issue comment "$BASE_ISSUE" --repo "$REPO" --body "$BODY"
+
+echo "Posted duplicate comment on issue #$BASE_ISSUE"