parallel-worktrees

parallel-worktrees is a skill for Claude Code, Codex from strikersam/autonomous-ai-agency. It costs 38 tokens per session (1,009 once invoked), scanned A, original, MIT.

A Git workflow for keeping several branches of the same code project checked out in separate folders. Git worktrees share the repository data while each folder has its own files and current branch.

In plain words
What is it for?
Use it to create folders for main, feature, hotfix, or reference branches and work on them in parallel.
Why use it?
It lets you work on a feature, inspect another branch, or run tests on a stable branch at the same time. This avoids repeatedly changing branches or temporarily hiding changes with Git stash.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents).

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/local-llm-server/.

Good fit Use it to create folders for main, feature, hotfix, or reference branches and work on them in parallel.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for parallel-worktrees

README.md
[![agentmods](https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/parallel-worktrees/github.svg)](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/parallel-worktrees)
Your own site
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/parallel-worktrees"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/parallel-worktrees/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for parallel-worktrees

Your own site · 80×15
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/parallel-worktrees"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/parallel-worktrees.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,009 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01009
Opus 5 $0.00019 $0.00504
Sonnet 5 $0.00008 $0.00202
Haiku 4.5 $0.00004 $0.00101

Measured 10d ago against content hash f8067f19d86f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

parallel-worktrees 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 10d ago.

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.

.agents/skills/parallel-worktrees/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: parallel-worktrees

When to Use

Use this skill when you need to:

  • Run the test suite on main while implementing on a feature branch
  • Keep a clean reference copy of the code for comparison during refactors
  • Work on a hotfix without disturbing in-progress feature work
  • Avoid git stash / git checkout cycles that interrupt flow

Concept

Git worktrees let you check out multiple branches of the same repo into different directories simultaneously. Each worktree shares the .git database but has its own working tree and index.

/home/user/local-llm-server/          ← main worktree (your current branch)
/home/user/local-llm-server-main/     ← linked worktree (main branch, read reference)
/home/user/local-llm-server-hotfix/   ← linked worktree (hotfix branch)

Instructions

Step 1 — Create a worktree for reference/parallel work

# Create a linked worktree for the main branch (read reference)
git worktree add ../local-llm-server-main main

# Create a linked worktree for a new feature branch
git worktree add ../local-llm-server-feature -b feature/my-feature

# Create a linked worktree for an existing remote branch
git worktree add ../local-llm-server-hotfix origin/hotfix/issue-42

Step 2 — List active worktrees

git worktree list

Output shows each worktree's path, HEAD commit, and branch.

Step 3 — Work across worktrees

Each worktree is an independent directory. You can:

# Run tests on main without switching branches
cd ../local-llm-server-main && pytest -x

# Edit files in the feature worktree
cd ../local-llm-server-feature && $EDITOR proxy.py

# Compare files across worktrees
diff ../local-llm-server-main/proxy.py ./proxy.py

Step 4 — Remove a worktree when done

# Remove the linked worktree (does not delete the branch)
git worktree remove ../local-llm-server-main

# Force remove if worktree has uncommitted changes
git worktree remove --force ../local-llm-server-main

# Prune stale worktree references
git worktree prune

Read the full file on GitHub · 151 lines

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. 10d ago First seen · 151 lines · 38 tokens per session scan A f8067f19d86f

Subscribe to this mod's changes

parallel-worktrees is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,009 once invoked, about $0.0002 per session on Opus 5. 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.