claude-worktree

A Git worktree management add-on. A worktree is a separate working directory connected to the same Git repository, allowing several branches to be used at once.

In plain words
What is it for?
Use it to share state such as .tickets/ between worktrees, copy per-worktree files, and create worktrees for parallel agent tasks.
Why use it?
It keeps selected shared files available across worktrees while copying other files separately for each worktree. It also prepares worktrees for team agents before they use them.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add phobologic/claude_code_helpers
agentmods
npx agentmods add plugins/phobologic/claude_code_helpers/worktree
Clone the repo
git clone --depth 1 https://github.com/phobologic/claude_code_helpers

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-worktree scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/worktree/.claude-plugin/plugin.json · 6 lines

What it actually says

{
  "name": "claude-worktree",
  "version": "1.2.1",
  "description": "Git worktree management: symlink shared state (e.g. .tickets/) across worktrees via .worktreelinks, copy per-worktree files via .worktreeinclude. Includes PreToolUse guard that pre-creates worktrees for team agents (workaround for anthropics/claude-code#33045)."
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 6 lines scan A b1cc44102487

Subscribe to this mod's changes

claude-worktree is a plugin published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.