orchestrating-parallel-workers

A coordination guide for splitting independent coding tasks among parallel background agents. Each worker receives its own context, and the guide explains how to define, plan, dispatch, and combine the work.

In plain words
What is it for?
Use it for independent file changes, separate research tasks, or multiple work units that can run at the same time.
Why use it?
It helps handle several unrelated or context-heavy tasks without mixing their instructions or state. It also identifies cases where parallel work would create unnecessary coordination problems.

Skill for Claude CodeCodex

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 skills/qte77/claude-code-plugins/orchestrating-parallel-workers
Any agent
npx skills add qte77/claude-code-plugins --skill orchestrating-parallel-workers
Clone the repo
git clone --depth 1 https://github.com/qte77/claude-code-plugins

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 854 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 $0.00034 $0.00854
Opus 5 $0.00017 $0.00427
Sonnet 5 $0.00007 $0.00171
Haiku 4.5 $0.00003 $0.00085

Measured 2d ago against content hash 986487da5e90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrating-parallel-workers 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 2d 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.

plugins/cc-meta/skills/orchestrating-parallel-workers/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Worker Orchestration

Target: $ARGUMENTS

Decomposes work into independent units and dispatches them to parallel background agents. Each agent gets its own context window, preventing cross-contamination between unrelated tasks.

When to Use

  • Multiple independent tasks (e.g., create 3 unrelated files, research 4 topics)
  • Context-heavy work that would pollute the main session
  • Parallel file creation/editing in different areas of the codebase

When NOT to Use

  • Sequential dependent tasks (output of A feeds into B)
  • Single-file changes or trivial edits
  • Tasks requiring shared mutable state between workers
  • Fewer than 2 independent units

Workflow

1. Decompose

Split the user request into independent work units. Each unit must be:

  • Self-contained (no dependency on other units)
  • Well-scoped (clear input, clear expected output)
  • Worth isolating (non-trivial enough to justify agent overhead)

2. Plan

For each unit, define:

Field Description
Name Short identifier (e.g., worker-auth, worker-docs)
Type worktree for file changes, shared for read-only research
Prompt Complete, self-contained instructions (no shared context)
Output What the agent should produce and where

3. Dispatch

Launch all agents in a single message with multiple Agent tool calls. This ensures true parallel execution. Each agent prompt must include:

  • Full context needed (file paths, requirements, constraints)
  • Expected output format and location
  • No references to other agents or their work

4. Track

Use TaskCreate for each dispatched unit to give the user visibility:

TaskCreate: "worker-auth: implement OAuth module" — status: in_progress
TaskCreate: "worker-docs: write API reference" — status: in_progress

Update tasks as agents complete via TaskUpdate.

5. Collect

After all agents finish:

  • Read each agent's output
  • Validate completeness and correctness
  • Synthesize a summary for the user
  • Handle any git operations (worktree agents lack Bash)

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 34 tokens per session scan A 986487da5e90

Subscribe to this mod's changes

orchestrating-parallel-workers is a skill published in the GitHub repository qte77/claude-code-plugins (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 34 tokens to every session and 854 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 2026-08-31.

Related

Other skills, from other repositories

orchestrator

FULLY AUTONOMOUS Flutter development pipeline orchestrator. Smart routing: PM analyzes -> creates targeted tasks -> Orchestrator executes only needed agents. Supports Asana task URLs. Includes QE verification via Maestro E2E tests. 7-phase flow: PM -> TodoWrite -> Execute -> Review -> Tests -> QE E2E -> Close.

aleksandr-chaika/flutter-clean-arch-skills · 72 tokens

shipping-artifacts

The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…

phuryn/pm-skills · 120 tokens

reflect-tree

Visualize a Claude Code session as a quest/skill tree — a navigable SVG graph where nodes are turns and edges show flow, with distinct visual encoding for normal flow, dead-ends, corrections, retries, reversals, and backtracking. Sibling to /reflect (which produces an incidents+recommendations dashboard); this one…

NikiforovAll/claude-code-rules · 115 tokens

handbook-discover

This skill should be used when users want to discover, browse, or audit cc-handbook marketplace plugins. Shows all available plugins with installation status, versions, and component breakdown (skills, agents, commands, MCP/LSP servers, hooks). Trigger phrases include "discover plugins", "list handbook plugins", "what…

NikiforovAll/claude-code-rules · 75 tokens

auto-loop

TDD-based autonomous development loop with checkpoint recovery and observability changelog.

claude-world/director-mode-lite · 17 tokens

hook-template

Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.

claude-world/director-mode-lite · 39 tokens