threads

Coordinate Codex-native threads into parallel lanes with ownership and gates.

258|26|Updated Dec 9, 2025
One-click install
npx skills add https://github.com/majiayu000/spellbook --skill threads-majiayu000
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: threads
Source: https://github.com/majiayu000/spellbook/tree/main/skills/threads
Command: npx skills add https://github.com/majiayu000/spellbook --skill threads-majiayu000

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate Codex-native threads to split broad tasks into parallel lanes with explicit ownership, gates, and verifiable closure, reducing coordination overhead and miscommunication.

Core Features & Use Cases

  • Lane-based planning and execution for GitHub issues/PRs using Codex-native subagents.
  • Capability gates, thread dispatch, and remote truth checks to maintain auditability.
  • Closure audit workflows for complete end-to-end task resolution.

Quick Start

Describe the current queue and initiate Codex-native thread planning for a bounded tranche.

Frequently Asked Questions about threads

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate parallel subagents for GitHub issues and PRs?

You can split broad GitHub issue and PR queues into concurrent lanes using Codex-native subagents, each with explicit ownership, base gates, and verifiable closure to reduce coordination overhead and miscommunication.

What is lane-based planning for parallel thread orchestration?

Lane-based planning divides broad tasks into parallel execution threads with explicit ownership and capability gates. This mechanism maintains auditability through remote truth checks and closure audit workflows for complete end-to-end task resolution.

How do I enforce a no-merge default policy with parallel thread workflows?

Enforce a no-merge default by applying truth level management (A-D) and capability gates to each parallel lane. Threads must provide evidence-backed results using prescribed prompts, run logs, and lane outputs before verifiable closure is authorized.

Can I run cross-repo workflows concurrently using Codex-native threads?

Yes, you can apply Codex-native threads to cross-repo workflows where independent lanes run concurrently. Each thread receives writable files, base gates, and remote truth checks to satisfy constraints like default no-merge and truth level management.

How do I start parallel lane execution for a bounded task tranche?

Describe the current queue and initiate Codex-native thread planning for a bounded tranche. This dispatches threads with capability gates and remote truth checks to maintain auditability throughout the closure audit workflow.

What are the limitations of using threads for parallel task orchestration?

Threads require evidence-backed results using prescribed prompts, run logs, and lane outputs for verifiable closure. The default no-merge constraint and truth level management (A-D) must be satisfied, meaning lanes cannot merge without explicit authorization.