start-parallel

start-parallel is a command for coding agents from ArieGoldkin/ai-agent-hub. It costs 0 tokens per session (3,193 once invoked), scanned A, original, MIT.

A command for gathering requirements and preparing several coding agents to work on separate tasks at the same time.

In plain words
What is it for?
Use it to search for real requirements, ask the user for missing details, and organize parallel agent work.
Why use it?
It prevents implementation from starting without confirmed requirements and helps find relevant project plans or GitHub issues first.

Command

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/ariegoldkin/ai-agent-hub/start-parallel
Clone the repo
git clone --depth 1 https://github.com/ArieGoldkin/ai-agent-hub

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 start-parallel

README.md
[![agentmods](https://agentmods.dev/badge/commands/ariegoldkin/ai-agent-hub/start-parallel.svg)](https://agentmods.dev/commands/ariegoldkin/ai-agent-hub/start-parallel)
Your own site
<a href="https://agentmods.dev/commands/ariegoldkin/ai-agent-hub/start-parallel"><img src="https://agentmods.dev/badge/commands/ariegoldkin/ai-agent-hub/start-parallel.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 3,193 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 $0.03193
Opus 5 $0.00000 $0.01597
Sonnet 5 $0.00000 $0.00639
Haiku 4.5 $0.00000 $0.00319

Measured 4d ago against content hash f392745faed8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start-parallel 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 4d 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.

.squad/commands/start-parallel.md · 441 lines

How it starts

The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start Parallel Agent Execution

INTERACTION MODE: REQUIRED

This command requires user interaction. You MUST wait for user input if no requirements are found.

Instructions for launching multiple agents to work simultaneously on allocated tasks.

STEP 1: Check for Requirements

FIRST ACTION: Check if requirements were provided with this command.

CRITICAL: When searching for PRDs:

  • EXCLUDE any files in .squad/examples/ - These are example templates
  • EXCLUDE any files in .claude/ - These are agent templates
  • EXCLUDE any files in templates/ or test/ - These are not real requirements
  • If only example PRDs are found, treat as NO PRD FOUND

If NO requirements were provided:

  • Proceed to Step 2 to gather requirements
  • DO NOT skip to implementation
  • DO NOT create any files until requirements are confirmed
  • DO NOT use example PRDs as actual requirements

Step 1: Discover or Gather Requirements

Search for Existing Requirements

Search for any existing requirements or documentation:

# Search for PRD or requirements files (EXCLUDING examples and templates)
# IMPORTANT: Exclude .squad/examples/, .claude/, templates/, and test/ directories
find . -type f \( -name "*prd*.md" -o -name "*requirements*.md" -o -name "README.md" -o -name "TODO.md" -o -name "ROADMAP.md" \) \
    -not -path "*/node_modules/*" \
    -not -path "*/.git/*" \
    -not -path "*/.squad/examples/*" \
    -not -path "*/.claude/*" \
    -not -path "*/templates/*" \
    -not -path "*/test/*" \
    2>/dev/null

# Check README for features section (if not in excluded directories)
if [ -f "README.md" ]; then
    grep -i "features\|requirements\|user stories" README.md 2>/dev/null
fi

# Check for GitHub issues
if [ -d ".github/ISSUE_TEMPLATE" ]; then
    cat .github/ISSUE_TEMPLATE/*.md 2>/dev/null | head -50
fi

If Requirements Found

Summarize what you found and confirm:

📄 Found existing requirements in [filename]:
"[1-2 sentence summary of what the project is building]"

Is this what you're building? (Y/n):

Read the full file on GitHub · 441 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. 4d ago First seen · 441 lines · 0 tokens per session scan A f392745faed8

Subscribe to this mod's changes

start-parallel is a command published in the GitHub repository ArieGoldkin/ai-agent-hub (11 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,193 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.