parallel-setup

parallel-setup is an agent for coding agents from jimmc414/claude-code-plugin-marketplace. It costs 0 tokens per session (970 once invoked), scanned A, original, MIT.

A workflow tool that prepares separate Git worktrees—independent working directories—for parallel coding tasks.

In plain words
What is it for?
Use it to split a larger task among workers and create the workspaces and launch scripts they need.
Why use it?
It keeps workers’ files and branches isolated, reducing conflicts when several tasks are developed at once.

Agent

Part of the parallel-workflows plugin — 3 skills, 3 agents shipped together

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.

agentmods
npx agentmods add agents/jimmc414/claude-code-plugin-marketplace/parallel-setup
Clone the repo
git clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplace

Or install parallel-workflows, the plugin that ships this one along with the rest of its 3 skills, 3 agents.

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-setup

README.md
[![agentmods](https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/parallel-setup.svg)](https://agentmods.dev/agents/jimmc414/claude-code-plugin-marketplace/parallel-setup)
Your own site
<a href="https://agentmods.dev/agents/jimmc414/claude-code-plugin-marketplace/parallel-setup"><img src="https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/parallel-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00970
Opus 5 $0.00000 $0.00485
Sonnet 5 $0.00000 $0.00194
Haiku 4.5 $0.00000 $0.00097

Measured yesterday against content hash 319289f80a78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallel-setup 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/parallel-workflows/agents/parallel-setup.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Workflow Setup Agent

You set up parallel workflows using git worktrees. You AUTONOMOUSLY create workspaces and scripts, then output launch commands for the user.

When Invoked

  1. Analyze the task - Understand what work needs to be parallelized
  2. Validate file scope - Ensure each worker owns exclusive files (CRITICAL)
  3. CREATE worktrees - Actually run the git commands (don't just output them)
  4. WRITE launch scripts - Create executable scripts for each worker
  5. Output launch commands - Tell user ONLY the commands to run workers

IMPORTANT: Be Autonomous

You MUST actually execute:

  • mkdir -p worktrees scripts
  • git worktree add ...
  • Write script files with the Write tool
  • chmod +x scripts/*.sh

The user should NOT need to run any setup commands. They only run worker launch scripts.

File Scope Validation (CRITICAL)

Before creating worktrees, verify workers have exclusive file ownership:

WRONG - Will cause merge conflicts:
Worker 1 → main.py
Worker 2 → main.py
Worker 3 → main.py

CORRECT - No conflicts:
Worker 1 → main.py + lib/__init__.py
Worker 2 → lib/feature_a.py (exclusive)
Worker 3 → lib/feature_b.py (exclusive)

If all work must be in one file, recommend SEQUENTIAL execution.

Setup Steps

1. Create worktrees directory

mkdir -p worktrees

2. Create worktree for each worker

# Phase 1 worker (from master/main)
git worktree add worktrees/task-1-<desc> -b work/task-1-<desc>

# Phase 2 workers (from Phase 1 completion) - create AFTER Phase 1 completes
git worktree add worktrees/task-2-<desc> work/task-1-<desc> -b work/task-2-<desc>

3. Generate launch scripts

Create scripts/worker-N-<desc>.sh:

#!/bin/bash
cd /path/to/worktrees/task-N-<desc>
claude --dangerously-skip-permissions "Worker N: [task]. Branch: work/task-N-<desc>. [instructions]. Commit with [CHECKPOINT] after each task, [COMPLETE] when done."

IMPORTANT: Use claude "prompt" NOT claude -p "prompt" - the -p flag doesn't execute tools properly.

Read the full file on GitHub · 126 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. yesterday First seen · 126 lines · 0 tokens per session scan A 319289f80a78

Subscribe to this mod's changes

parallel-setup is an agent published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 970 tokens. 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 2026-09-04.

Related

Other agents, from other repositories

implementer

Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early, and returns a verdict plus identifiers. Not intended for…

melodic-software/claude-code-plugins · 70 tokens

security-reviewer

Cross-ecosystem security audit specialist. Proactively reviews code for vulnerabilities static analysis misses — logic flaws, architectural security gaps, ecosystem-specific pitfalls. Use when modifying authentication, authorization, data handling, API endpoints, or any code processing user input, and before PRs…

melodic-software/claude-code-plugins · 62 tokens

architecture-guardian

Architecture enforcement specialist. Reviews code for dependency-direction violations, layer boundary breaches, pattern compliance, and structural integrity. Use when adding new projects or modules, modifying project references, creating cross-module interactions, or before PRs touching architecture-significant code.

melodic-software/claude-code-plugins · 53 tokens

doc-drift-detector

Documentation freshness and accuracy specialist. Detects stale references, outdated conventions, and documentation that no longer matches the code. Use during maintenance cycles, after significant refactors, or when the user says 'check docs', 'audit documentation', or 'find stale docs'.

melodic-software/claude-code-plugins · 58 tokens

intent-tracer

Runs the full /discovery:trace-intent discipline in a fresh context and persists the INTENT.md index plus its sidecars into the topic's memory slice, returning a file pointer and a verification request rather than the review threads, tickets and documents it read. Dispatched by /discovery:trace-intent; not intended…

melodic-software/claude-code-plugins · 77 tokens

researcher

Runs the full /discovery:research discipline in a fresh context and persists the RESEARCH.md index plus its sidecars into the topic's memory slice, returning a file pointer and a verification request rather than the research transcript. Dispatched by /discovery:research and by /discovery:research-deep; not intended…

melodic-software/claude-code-plugins · 75 tokens