Compare commits

..

5 Commits

Author SHA1 Message Date
Claude
9308352131 Add blockedMarketplaces to enterprise managed settings
Add support for blockedMarketplaces in enterprise managed settings,
allowing administrators to prevent specific plugin marketplaces from
being installed. This takes precedence over other marketplace settings.
2025-12-16 23:20:46 +00:00
GitHub Actions
4392352687 chore: Update CHANGELOG.md 2025-12-16 22:06:07 +00:00
kashyap murali
c27c6f4e4a Merge pull request #14071 from anthropics/claude/slack-make-no-comment-default-Qqha8
Make no-comment the default for /code-review
2025-12-16 12:22:18 -08:00
GitHub Actions
0dde1fef97 chore: Update CHANGELOG.md 2025-12-15 23:49:39 +00:00
Claude
e4f682030b Make no-comment the default for /code-review
Change the default behavior of /code-review to output to the terminal
instead of posting a PR comment. Users can use the --comment flag to
explicitly post the review as a PR comment when desired.

This is more suitable for local development workflows where posting
comments to the PR is not always needed.
2025-12-15 17:50:32 +00:00
6 changed files with 48 additions and 82 deletions

View File

@@ -1,5 +1,32 @@
# Changelog
## 2.0.71
- Added `blockedMarketplaces` to enterprise managed settings, allowing administrators to prevent specific plugin marketplaces from being installed
- Added /config toggle to enable/disable prompt suggestions
- Added `/settings` as an alias for the `/config` command
- Fixed @ file reference suggestions incorrectly triggering when cursor is in the middle of a path
- Fixed MCP servers from `.mcp.json` not loading when using `--dangerously-skip-permissions`
- Fixed permission rules incorrectly rejecting valid bash commands containing shell glob patterns (e.g., `ls *.txt`, `for f in *.png`)
- Bedrock: Environment variable `ANTHROPIC_BEDROCK_BASE_URL` is now respected for token counting and inference profile listing
- New syntax highlighting engine for native build
## 2.0.70
- Added Enter key to accept and submit prompt suggestions immediately (tab still accepts for editing)
- Added wildcard syntax `mcp__server__*` for MCP tool permissions to allow or deny all tools from a server
- Added auto-update toggle for plugin marketplaces, allowing per-marketplace control over automatic updates
- Added `plan_mode_required` spawn parameter for teammates to require plan approval before implementing changes
- Added `current_usage` field to status line input, enabling accurate context window percentage calculations
- Fixed input being cleared when processing queued commands while the user was typing
- Fixed prompt suggestions replacing typed input when pressing Tab
- Fixed diff view not updating when terminal is resized
- Improved memory usage by 3x for large conversations
- Improved resolution of stats screenshots copied to clipboard (Ctrl+S) for crisper images
- Removed # shortcut for quick memory entry (tell Claude to edit your CLAUDE.md instead)
- Fix thinking mode toggle in /config not persisting correctly
- Improve UI for file creation permission dialog
## 2.0.69
- Minor bugfixes

View File

@@ -22,23 +22,29 @@ Performs automated code review on a pull request using multiple specialized agen
- **Agent #4**: Analyze git blame/history for context-based issues
5. Scores each issue 0-100 for confidence level
6. Filters out issues below 80 confidence threshold
7. Posts review comment with high-confidence issues only
7. Outputs review (to terminal by default, or as PR comment with `--comment` flag)
**Usage:**
```bash
/code-review
/code-review [--comment]
```
**Options:**
- `--comment`: Post the review as a comment on the pull request (default: outputs to terminal only)
**Example workflow:**
```bash
# On a PR branch, run:
# On a PR branch, run locally (outputs to terminal):
/code-review
# Post review as PR comment:
/code-review --comment
# Claude will:
# - Launch 4 review agents in parallel
# - Score each issue for confidence
# - Post comment with issues ≥80 confidence
# - Skip posting if no high-confidence issues found
# - Output issues ≥80 confidence (to terminal or PR depending on flag)
# - Skip if no high-confidence issues found
```
**Features:**
@@ -114,17 +120,23 @@ This plugin is included in the Claude Code repository. The command is automatica
### Standard PR review workflow:
```bash
# Create PR with changes
# Run local review (outputs to terminal)
/code-review
# Review the automated feedback
# Make any necessary fixes
# Optionally post as PR comment
/code-review --comment
# Merge when ready
```
### As part of CI/CD:
```bash
# Trigger on PR creation or update
# Automatically posts review comments
# Use --comment flag to post review comments
/code-review --comment
# Skip if review already exists
```

View File

@@ -52,7 +52,9 @@ Note: Still review Claude generated PR's.
6. Filter out any issues that were not validated in step 5. This step will give us our list of high signal issues for our review.
7. Finally, comment on the pull request.
7. Finally, output the review.
- If the `--comment` argument is provided, post the review as a comment on the pull request using `gh pr comment`
- Otherwise (default), output the review directly to the terminal for local viewing
When writing your comment, follow these guidelines:
a. Keep your output brief
b. Avoid emojis

View File

@@ -1,45 +0,0 @@
# Plan Auto-Show Plugin
Automatically displays the plan content when it's updated in plan mode, eliminating the need to type `/plan` to preview changes.
## Problem
When in plan mode, Claude updates the plan file and may ask follow-up questions. Users can't see the plan without typing `/plan`, but they also can't type `/plan` while being asked questions - they need to respond to the questions first.
## Solution
This plugin instructs Claude to automatically display the plan content in its response whenever it updates the plan file. The plan is shown before any follow-up questions, giving users the context they need to answer.
## Installation
1. Enable the plugin in your Claude Code settings
2. The SessionStart hook will automatically add instructions for plan auto-display
## How It Works
The plugin adds a SessionStart hook that provides additional context to Claude:
- After updating the plan file, Claude will display the full plan content
- The plan is shown in a markdown code block
- The plan appears before any follow-up questions
## Example
Before this plugin:
```
Claude: I've updated the plan file. Would you prefer approach A or B?
User: (Can't see the plan without typing /plan, but needs to answer the question)
```
After this plugin:
```
Claude: I've updated the plan file:
## Current Plan
1. Implement feature X
2. Add tests
3. Deploy
Would you prefer approach A or B?
User: (Can see the plan and answer the question)
```

View File

@@ -1,15 +0,0 @@
#!/usr/bin/env bash
# Auto-show plan content after updates in plan mode
# This hook adds instructions to automatically display the plan when updated
cat << 'EOF'
{
"hookSpecificOutput": {
"hookEventName": "SessionStart",
"additionalContext": "## Plan Mode Auto-Display\n\nWhen you are in plan mode and you update the plan file:\n\n1. After writing or editing the plan file, ALWAYS display the full plan content in a markdown code block in your response\n2. Use the format:\n ```markdown\n ## Current Plan\n [full plan content here]\n ```\n3. This ensures the user can see the plan without needing to run `/plan`, which is especially important when you're asking follow-up questions\n4. Show the plan BEFORE asking any clarifying questions, so the user has context for their answers\n\nThis improves the user experience by making the plan visible immediately after updates, without requiring separate commands."
}
}
EOF
exit 0

View File

@@ -1,15 +0,0 @@
{
"hooks": {
"SessionStart": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"
}
]
}
]
}
}