parallel-poc

parallel-poc is a command for Claude Code from basher83/lunar-claude. It costs 5 tokens per session (358 once invoked), scanned A, original, MIT.

A test for measuring whether two agent tasks run at the same time instead of one after the other.

In plain words
What is it for?
Use it to launch two simulated research tasks, record their elapsed times, and save the parallel-versus-sequential results.
Why use it?
It provides timing evidence about parallel dispatch and compares it with a sequential baseline.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions 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/basher83/lunar-claude/parallel-poc
Clone the repo
git clone --depth 1 https://github.com/basher83/lunar-claude

Made for: Claude Code.

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-poc

README.md
[![agentmods](https://agentmods.dev/badge/commands/basher83/lunar-claude/parallel-poc.svg)](https://agentmods.dev/commands/basher83/lunar-claude/parallel-poc)
Your own site
<a href="https://agentmods.dev/commands/basher83/lunar-claude/parallel-poc"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/parallel-poc.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 358 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 5.1 $0.00005 $0.00358
Opus 5 $0.00003 $0.00179
Sonnet 5 $0.00001 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 6d ago against content hash 28611c75e535, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

parallel-poc 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 6d 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.

.claude/commands/research-validation/parallel-poc.md · 63 lines

What it actually says

Parallel Dispatch PoC

Purpose

Test whether Claude Code's Task tool supports true parallel execution with measurable time savings.

Instructions

  1. Record start time
  2. Launch 2 agents in PARALLEL (single message, multiple Task tool calls)
  3. Each agent performs a 10-second simulated task (web fetch + processing)
  4. Record end time
  5. Calculate: parallel time vs expected sequential time (20s)

Workflow

Test 1: Parallel Execution

Launch both agents in ONE message:

Agent A:

subagent_type: general-purpose
description: Agent A - web research

Prompt:
1. Use WebSearch to search for "Claude Code parallel agents"
2. Read the first result
3. Summarize in 2 sentences
4. Return: "Agent A complete: [summary]"

Agent B:

subagent_type: general-purpose
description: Agent B - web research

Prompt:
1. Use WebSearch to search for "multi-agent orchestration patterns"
2. Read the first result
3. Summarize in 2 sentences
4. Return: "Agent B complete: [summary]"

Test 2: Sequential Baseline (for comparison)

Run same two searches sequentially (one after the other) and record time.

Output

Record results in docs/plans/phase-0-results/parallel-dispatch-results.md:

  • Parallel execution time: [X seconds]
  • Sequential execution time: [Y seconds]
  • Speedup ratio: [Y/X]
  • Go/No-Go: [PASS if speedup > 1.5x, FAIL otherwise]
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. 6d ago First seen · 63 lines · 5 tokens per session scan A 28611c75e535

Subscribe to this mod's changes

parallel-poc is a command published in the GitHub repository basher83/lunar-claude (22 stars, last pushed today), licensed MIT. It adds 5 tokens to every session and 358 once invoked, about $0.0000 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 2026-08-30.