parallelize

A command that creates separate Git worktrees and runs AI agents in them for the same feature. A worktree is an additional working copy of a Git repository, allowing changes to be developed independently.

In plain words
What is it for?
Use it to validate a feature task file, create the requested number of worktrees, and assign agents to work on the tasks concurrently.
Why use it?
It lets several implementation tasks proceed at the same time while keeping their files and changes separate.

Command 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.

agentmods
npx agentmods add commands/bluewings1211/codebase-rag/parallelize
Clone the repo
git clone --depth 1 https://github.com/bluewings1211/codebase-RAG

Made for: Claude Code.

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 1,112 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 $0.01112
Opus 5 $0.00000 $0.00556
Sonnet 5 $0.00000 $0.00222
Haiku 4.5 $0.00000 $0.00111

Measured yesterday against content hash eeff81719e00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallelize 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.

.claude/commands/parallelize.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/parallelize

Create N git worktrees and run AI agents in each worktree for concurrent development.

Variables

FEATURE_NAME: $ARGUMENTS NUMBER_OF_PARALLEL_WORKTREES: $ARGUMENTS

Task File Discovery and Validation

Task File Location: I will locate the task file at tasks/tasks-prd-{FEATURE_NAME}.md.

Validation Steps:

  1. Verify that tasks/tasks-prd-{FEATURE_NAME}.md exists
  2. Confirm the file contains a valid task list structure
  3. If the file doesn't exist, I will exit with an error message: "Task file not found: tasks/tasks-prd-{FEATURE_NAME}.md. Please generate the task list first using @ai_docs/generate-tasks.mdc"

Task File Contents: The discovered task file will serve as the implementation plan for all subagents.

Execute Phase 1: Environment Setup

Parameter Validation: Before proceeding, I will validate:

  1. FEATURE_NAME is provided and not empty
  2. NUMBER_OF_PARALLEL_WORKTREES is a positive integer
  3. Task file tasks/tasks-prd-{FEATURE_NAME}.md exists and is readable
  4. The progress/ directory exists (create if it doesn't)

Safety Check: I will check for any uncommitted changes in the current directory. If changes are found, I will exit with an error, prompting you to commit or stash them.

Directory Setup: I will ensure the trees/ directory exists at the project root.

The following steps will be executed in parallel for each worktree to ensure efficiency. I will use absolute paths for all commands.

For each instance from 1 to NUMBER_OF_PARALLEL_WORKTREES, I will:

  1. Create Worktree: git worktree add -b <FEATURE_NAME>-<instance-number> ./trees/<FEATURE_NAME>-<instance-number>
  2. Copy Environment: Copy the .env file to ./trees/<FEATURE_NAME>-<instance-number>/.env if it exists.
  3. Copy Task File: Copy the task file from tasks/tasks-prd-{FEATURE_NAME}.md to ./trees/<FEATURE_NAME>-<instance-number>/tasks/tasks-prd-{FEATURE_NAME}.md
  4. Install Dependencies: Change directory to ./trees/<FEATURE_NAME>-<instance-number> and run uv sync to install dependencies specified in uv.lock.

Read the full file on GitHub · 98 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 · 98 lines · 0 tokens per session scan A eeff81719e00

Subscribe to this mod's changes

parallelize is a command published in the GitHub repository bluewings1211/codebase-RAG (15 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,112 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 2026-08-30.