chore: Update CHANGELOG.md

refactor(code-review): improve issue flagging and agent behavior

.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 +1,150 @@
 # Changelog
 
+## 2.1.2
+
+- Added source path metadata to images dragged onto the terminal, helping Claude understand where images originated
+- Added clickable hyperlinks for file paths in tool output in terminals that support OSC 8 (like iTerm)
+- Added support for Windows Package Manager (winget) installations with automatic detection and update instructions
+- Added Shift+Tab keyboard shortcut in plan mode to quickly select "auto-accept edits" option
+- Added `FORCE_AUTOUPDATE_PLUGINS` environment variable to allow plugin autoupdate even when the main auto-updater is disabled
+- Added `agent_type` to SessionStart hook input, populated if `--agent` is specified
+- Fixed a command injection vulnerability in bash command processing where malformed input could execute arbitrary commands
+- Fixed a memory leak where tree-sitter parse trees were not being freed, causing WASM memory to grow unbounded over long sessions
+- Fixed binary files (images, PDFs, etc.) being accidentally included in memory when using `@include` directives in CLAUDE.md files
+- Fixed updates incorrectly claiming another installation is in progress
+- Fixed crash when socket files exist in watched directories (defense-in-depth for EOPNOTSUPP errors)
+- Fixed remote session URL and teleport being broken when using `/tasks` command
+- Fixed MCP tool names being exposed in analytics events by sanitizing user-specific server configurations
+- Improved Option-as-Meta hint on macOS to show terminal-specific instructions for native CSIu terminals like iTerm2, Kitty, and WezTerm
+- Improved error message when pasting images over SSH to suggest using `scp` instead of the unhelpful clipboard shortcut hint
+- Improved permission explainer to not flag routine dev workflows (git fetch/rebase, npm install, tests, PRs) as medium risk
+- Changed large bash command outputs to be saved to disk instead of truncated, allowing Claude to read the full content
+- Changed large tool outputs to be persisted to disk instead of truncated, providing full output access via file references
+- Changed `/plugins` installed tab to unify plugins and MCPs with scope-based grouping
+- Deprecated Windows managed settings path `C:\ProgramData\ClaudeCode\managed-settings.json` - administrators should migrate to `C:\Program Files\ClaudeCode\managed-settings.json`
+- [SDK] Changed minimum zod peer dependency to ^4.0.0
+- [VSCode] Fixed usage display not updating after manual compact
+
+## 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

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
 

plugins/code-review/commands/code-review.md

@@ -5,6 +5,10 @@ description: Code review a pull request
 
 Provide a code review for the given pull request.
 
+**Agent assumptions (applies to all agents and subagents):**
+- All tools are functional and will work without error. Do not test tools or make exploratory calls.
+- Only call a tool if it is required to complete the task. Every tool call should have a clear purpose.
+
 To do this, follow these steps precisely:
 
 1. Launch a haiku agent to check if any of the following are true:
@@ -34,15 +38,15 @@ Note: Still review Claude generated PR's.
    Agent 4: Opus bug agent (parallel subagent with agent 3)
    Look for problems that exist in the introduced code. This could be security issues, incorrect logic, etc. Only look for issues that fall within the changed code.
 
-   **CRITICAL: We only want HIGH SIGNAL issues.** This means:
-   - Objective bugs that will cause incorrect behavior at runtime
+   **CRITICAL: We only want HIGH SIGNAL issues.** Flag issues where:
+   - The code will fail to compile or parse (syntax errors, type errors, missing imports, unresolved references)
+   - The code will definitely produce wrong results regardless of inputs (clear logic errors)
    - Clear, unambiguous CLAUDE.md violations where you can quote the exact rule being broken
 
-   We do NOT want:
-   - Subjective concerns or "suggestions"
-   - Style preferences not explicitly required by CLAUDE.md
-   - Potential issues that "might" be problems
-   - Anything requiring interpretation or judgment calls
+   Do NOT flag:
+   - Code style or quality concerns
+   - Potential issues that depend on specific inputs or state
+   - Subjective suggestions or improvements
 
    If you are not certain an issue is real, do not flag it. False positives erode trust and waste reviewer time.
 
@@ -57,23 +61,10 @@ Note: Still review Claude generated PR's.
    If NO issues were found, post a summary comment using `gh pr comment` (if `--comment` argument is provided):
    "No issues found. Checked for bugs and CLAUDE.md compliance."
 
-8. Post inline comments for each issue using `mcp__github_inline_comment__create_inline_comment`:
-   - `path`: the file path
-   - `line` (and `startLine` for ranges): select the buggy lines so the user sees them
-   - `body`: Brief description of the issue (no "Bug:" prefix). For small fixes (up to 5 lines changed), include a committable suggestion:
-     ```suggestion
-     corrected code here
-     ```
-
-     **Suggestions must be COMPLETE.** If a fix requires additional changes elsewhere (e.g., renaming a variable requires updating all usages), do NOT use a suggestion block. The author should be able to click "Commit suggestion" and have a working fix - no followup work required.
-
-     For larger fixes (6+ lines, structural changes, or changes spanning multiple locations), do NOT use suggestion blocks. Instead:
-     1. Describe what the issue is
-     2. Explain the suggested fix at a high level
-     3. Include a copyable prompt for Claude Code that the user can use to fix the issue, formatted as:
-        ```
-        Fix [file:line]: [brief description of issue and suggested fix]
-        ```
+8. Post inline comments for each issue using `mcp__github_inline_comment__create_inline_comment`. For each comment:
+   - Provide a brief description of the issue
+   - For small, self-contained fixes, include a committable suggestion block
+   - For larger fixes (6+ lines, structural changes, or changes spanning multiple locations), describe the issue and suggested fix without a suggestion block
 
    **IMPORTANT: Only post ONE comment per unique issue. Do not post duplicate comments.**
 

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

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"