parallel-agent-management

parallel-agent-management is a skill for Claude Code, Codex from mlopscommunity/Coding-Agents-Conference-skills. It costs 43 tokens per session (2,112 once invoked), scanned A, original, Apache-2.0.

A method for coordinating several Claude Code agents working at the same time, using Git worktrees or containers and clear task agreements.

In plain words
What is it for?
Use it to split large refactors, independent frontend and backend work, exploratory approaches, or other tasks that can run concurrently.
Why use it?
It keeps parallel work organized and reduces confusion about ownership, communication, and how separate changes will be combined.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is git worktree add ../project-agent-1 -b agent/feature-api.

Good fit Use it to split large refactors, independent frontend and backend work, exploratory approaches, or other tasks that can run concurrently.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mlopscommunity/Coding-Agents-Conference-skills
agentmods
npx agentmods add skills/mlopscommunity/coding-agents-conference-skills/parallel-agent-management

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-agent-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/parallel-agent-management.svg)](https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/parallel-agent-management)
Your own site
<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/parallel-agent-management"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/parallel-agent-management.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,112 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 $0.00043 $0.02112
Opus 5 $0.00022 $0.01056
Sonnet 5 $0.00009 $0.00422
Haiku 4.5 $0.00004 $0.00211

Measured 8d ago against content hash 6cc1303bde3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

parallel-agent-management 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 8d 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.

skills/parallel-agent-management/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Agent Management

Overview

A structured approach to running multiple Claude Code agents in parallel using git worktrees, containers, and explicit communication contracts. The key insight is that the bottleneck with parallel agents is organization, not capability. Invest in the scaffolding before spinning up agents.

Core principle: One main agent orchestrates, one layer of sub-agents executes. Keep the hierarchy flat. Every sub-agent gets an explicit contract specifying exactly what to do and exactly what to return.

Dependencies: Git (for worktrees), optionally Docker (for container isolation).

When to Use

  • Large refactors that touch independent modules simultaneously
  • Feature work where frontend, backend, and tests can proceed in parallel
  • Exploratory work where you want multiple approaches tried at once
  • Any task where you find yourself thinking "I wish I could work on this other part while waiting"

When NOT to Use

  • Small, sequential changes where one agent finishes in minutes
  • Tightly coupled code where every change depends on the previous one
  • When you don't have time to set up the scaffolding (the setup IS the investment)
  • Tasks requiring deep, single-threaded reasoning across the whole codebase

Common Mistakes

Mistake Why it's wrong
Deep agent hierarchies (agents spawning agents spawning agents) Niels: One main agent + one layer of sub-agents is sufficient for most cases. Deeper nesting creates coordination nightmares and lost context.
Vague sub-agent instructions ("fix the tests") Harrison Chase: Sub-agents need explicit communication contracts. Specify the exact task, input format, expected output format, and success criteria.
Running parallel agents in the same worktree Agents will clobber each other's file changes. Each agent needs its own isolated worktree or container.
Skipping the orchestration step Jumping straight to "run 5 agents" without planning which tasks are independent, what the interfaces are, and how results merge back. The organization IS the work.
Using --dangerously-skip-permissions on bare metal Rob: Run agents in containers to safely use --dangerously-skip-permissions. On bare metal, a runaway agent can damage your system.
Not having a switching mechanism between worktrees Without quick switching (Alfred, keybinds, tmux), you lose time context-switching. Sid uses Alfred/AppleScript automation to jump between five predefined worktrees.

Read the full file on GitHub · 200 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. 8d ago First seen · 200 lines · 43 tokens per session scan A 6cc1303bde3c

Subscribe to this mod's changes

parallel-agent-management is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (37 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,112 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens