Chrome Extension for bulk operations on Jules tasks via batchexecute API -- archive tasks and start code suggestions at scale.
Sister projects from n24q02m (click to expand)
| Project | Tagline | Tag |
|---|---|---|
| better-code-review-graph | Knowledge graph for token-efficient code reviews -- semantic search and call-... | MCP |
| better-email-mcp | IMAP/SMTP email for AI agents -- read, send, organize folders, and manage att... | MCP |
| better-godot-mcp | Composite MCP server for Godot Engine -- 17 composite tools for AI-assisted g... | MCP |
| better-notion-mcp | Markdown-first Notion for AI agents -- pages, databases, blocks, and comments... | MCP |
| better-telegram-mcp | Telegram for AI agents -- messages, chats, media, and contacts across both bo... | MCP |
| claude-plugins | Claude Code plugin marketplace for the n24q02m MCP servers -- install web sea... | Marketplace |
| imagine-mcp | Image and video understanding + generation for AI agents -- across Gemini, Op... | MCP |
| jules-task-archiver | Chrome Extension for bulk operations on Jules tasks via batchexecute API -- a... | Tooling |
| mcp-core | Shared foundation for building MCP servers -- Streamable HTTP transport, OAut... | MCP |
| mnemo-mcp | Persistent AI memory with hybrid search and embedded sync. Open, free, unlimi... | MCP |
| qwen3-embed | Lightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUF | Library |
| skret | Secrets without the server. | CLI |
| tacet | TACET: a self-distilling neuro-symbolic cascade that amortises LLM cost in kn... | Tooling |
| web-core | Shared web infrastructure package for search, scraping, HTTP security, and st... | Library |
| wet-mcp | Open-source MCP server for AI agents: web search, content extraction, and lib... | MCP |
- Features
- Installation
- Usage
- How It Works
- Permissions
- Development
- Related Projects
- Contributing
- License
- Bulk archive -- archive all completed tasks for repos with zero open PRs in one click
- GitHub PR check -- skips repos with open PRs to avoid archiving active work
- Force mode -- skip PR check and archive everything
- Bulk start -- start all recommended code suggestions (security, performance, testing, cleanup) across repos
- Category-aware prompts -- generates tailored prompts per suggestion category (security fix, performance optimization, test coverage, code cleanup)
- Config capture -- observes Jules UI to capture model config and experiment IDs for accurate reproduction
- Multi-account -- processes all Jules tabs (
/u/0,/u/1, etc.) automatically - Dry run mode -- preview what would happen without making changes
- batchexecute API -- direct HTTP calls, no DOM automation, 10x faster than UI clicks
- Live progress -- real-time log and progress bar in popup UI
- State persistence -- operation continues even if popup is closed; progress restored on reopen
- Download the latest
jules-task-archiver.zipfrom Releases - Extract the zip
- Open
chrome://extensionsin Chrome - Enable Developer mode (top right toggle)
- Click Load unpacked and select the extracted folder
- Open one or more
jules.google.comtabs (supports multiple accounts) - Click the extension icon in the toolbar
- Configure:
- Operation -- Archive Tasks or Start Suggestions
- GitHub Owner -- your GitHub username (for PR checks in archive mode)
- GitHub Token -- optional, for private repos
- Mode -- Dry Run (preview) or Run (execute)
- Force -- archive every task regardless of state or open PRs (archive mode only)
- Scope -- current tab only or all Jules tabs
- Click Start
- For best results, manually click "Start" on any suggestion in the Jules UI first -- the extension captures the model config and experiment IDs from that request
- Without this capture, the extension uses sensible defaults that may differ from Jules' current configuration
popup.js (UI) <-> background.js (batchexecute client) <-> content.js (message relay)
| |
fetch() to jules.google.com main-world.js (MAIN world)
/_/Swebot/data/batchexecute reads WIZ_global_data tokens
main-world.jsruns in the page's MAIN world, reads auth tokens fromWIZ_global_data, and observes fetch calls for StartSuggestion configcontent.jsrelays tokens and config to the background service workerbackground.jsmakes direct HTTP calls to Jules' batchexecute API endpointpopup.jsdisplays real-time progress and manages settings
| RPC | ID | Purpose |
|---|---|---|
| ListTasks | p1Takd |
Fetch all active tasks |
| ArchiveTask | Tjmm5c |
Archive a single task |
| ListSuggestions | hQP40d |
Fetch code suggestions for a repo |
| StartSuggestion | Rja83d |
Start a suggestion as a new task |
| Permission | Why |
|---|---|
storage |
Save settings and operation state |
tabs |
Query all Jules tabs for multi-account support |
scripting |
Inject content script into pre-existing tabs |
jules.google.com |
Content script for token extraction |
api.github.com |
Check open PRs via GitHub REST API |
# Lint and format
npx @biomejs/biome check .
npx @biomejs/biome check --write .
# Run tests
node --test
# Load unpacked in chrome://extensions for testingNo build step, no dependencies. Pure vanilla JavaScript with node:test for unit tests.
Check out these MCP servers for AI-powered development:
- wet-mcp -- Web search, extract, and media MCP server
- better-notion-mcp -- Notion API MCP server
- mnemo-mcp -- Persistent AI memory MCP server
See CONTRIBUTING.md for guidelines.