subtask
Gives Claude Code a skill and command line tool to create tasks, spawn subagents, and track their progress. Each task runs in its own Git worktree so parallel work stays separate, and you can review or request changes.
Searches and resumes your past Claude Code conversations, and also covers Codex, OpenCode and Factory sessions. Useful for developers who want to find and pick up earlier work.
$ brew install zippoxer/tap/recall


Search and resume your Claude Code conversations. Also supports Codex, OpenCode and Factory (Droid).
Tip: Don't like reading? Tell your agent to use recall search --help and it'll search for you.
Homebrew (macOS/Linux):
brew install zippoxer/tap/recall
WinGet (Windows):
winget install zippoxer.recall
Cargo:
cargo install --git https://github.com/zippoxer/recall
Binary: Download from Releases
Run:
recall
That's it. Start typing to search. Enter to jump back in.
| Key | Action |
|---|---|
↑↓ | Navigate sessions |
Pg↑/↓ | Scroll messages |
Ctrl+E | Expand message |
Enter | Resume conversation |
Tab | Copy session ID |
/ | Toggle scope (folder/everywhere) |
Esc | Quit |
Simply tell your agent:
use `recall search --help`
Example:
pls find me the last conversation where we deployed to staging, use `recall search --help`
No MCP required. The recall search CLI fulfills the same purpose. See Ask it to Search for You.
recall's resume commands can be configured with environment variables.
For example, to resume conversations in YOLO mode, add this to your .bashrc or .zshrc:
export RECALL_CLAUDE_CMD="claude --dangerously-skip-permissions --resume {id}"
export RECALL_CODEX_CMD="codex --dangerously-bypass-approvals-and-sandbox resume {id}"
Made with ❤️ by zippoxer and Claude.
Gives Claude Code a skill and command line tool to create tasks, spawn subagents, and track their progress. Each task runs in its own Git worktree so parallel work stays separate, and you can review or request changes.
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
Helps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
Gives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
Developer tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
Searches and resumes your past Claude Code conversations, and also covers Codex, OpenCode and Factory sessions. Useful for developers who want to find and pick up earlier work. Install it with the command on its page. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it